diff --git a/mlc-chat-config.json b/mlc-chat-config.json
new file mode 100644
index 0000000000000000000000000000000000000000..eb830750cba05e65f8e4ad1ee024886be4107cc4
--- /dev/null
+++ b/mlc-chat-config.json
@@ -0,0 +1,76 @@
+{
+ "version": "0.1.0",
+ "model_type": "qwen2",
+ "quantization": "q4f32_1",
+ "model_config": {
+ "hidden_act": "silu",
+ "hidden_size": 5120,
+ "intermediate_size": 27648,
+ "num_attention_heads": 40,
+ "num_hidden_layers": 64,
+ "num_key_value_heads": 8,
+ "rms_norm_eps": 1e-05,
+ "rope_theta": 1000000.0,
+ "vocab_size": 152064,
+ "tie_word_embeddings": false,
+ "context_window_size": 131072,
+ "prefill_chunk_size": 8192,
+ "tensor_parallel_shards": 1,
+ "head_dim": 128,
+ "dtype": "float32",
+ "max_batch_size": 128
+ },
+ "vocab_size": 152064,
+ "context_window_size": 131072,
+ "sliding_window_size": -1,
+ "prefill_chunk_size": 8192,
+ "attention_sink_size": -1,
+ "tensor_parallel_shards": 1,
+ "pipeline_parallel_stages": 1,
+ "temperature": 1.0,
+ "presence_penalty": 0.0,
+ "frequency_penalty": 0.0,
+ "repetition_penalty": 1.0,
+ "top_p": 1.0,
+ "tokenizer_files": [
+ "tokenizer.json",
+ "tokenizer_config.json"
+ ],
+ "tokenizer_info": {
+ "token_postproc_method": "byte_level",
+ "prepend_space_in_encode": false,
+ "strip_space_in_decode": false
+ },
+ "conv_template": {
+ "name": "deepseek_v3",
+ "system_template": "<\uff5cbegin\u2581of\u2581sentence\uff5c>{system_message}",
+ "system_message": "You are a helpful assistant.",
+ "system_prefix_token_ids": null,
+ "add_role_after_system_message": true,
+ "roles": {
+ "user": "<\uff5cUser\uff5c>",
+ "assistant": "<\uff5cAssistant\uff5c>"
+ },
+ "role_templates": {
+ "user": "{user_message}",
+ "assistant": "{assistant_message}",
+ "tool": "{tool_message}"
+ },
+ "messages": [],
+ "seps": [
+ "",
+ "<\uff5cend\u2581of\u2581sentence\uff5c>"
+ ],
+ "role_content_sep": "",
+ "role_empty_sep": "",
+ "stop_str": [],
+ "stop_token_ids": [
+ 151643
+ ],
+ "function_string": "",
+ "use_function_calling": false
+ },
+ "pad_token_id": 0,
+ "bos_token_id": 151643,
+ "eos_token_id": 151643
+}
\ No newline at end of file
diff --git a/ndarray-cache-b16.json b/ndarray-cache-b16.json
new file mode 100644
index 0000000000000000000000000000000000000000..76f836f1ee1612aef90ef1638eb9fc640b61d16b
--- /dev/null
+++ b/ndarray-cache-b16.json
@@ -0,0 +1,9703 @@
+{
+ "metadata": {
+ "ParamSize": 709,
+ "ParamBytes": 20481200128.0,
+ "BitsPerParam": 5.000922334820072
+ },
+ "records": [
+ {
+ "dataPath": "params_shard_0.bin",
+ "format": "raw-shard",
+ "nbytes": 389283840,
+ "records": [
+ {
+ "name": "model.embed_tokens.q_weight",
+ "shape": [
+ 152064,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 389283840,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "a5d3556afbf5fa2be30ba135893b2676"
+ },
+ {
+ "dataPath": "params_shard_1.bin",
+ "format": "raw-shard",
+ "nbytes": 48660480,
+ "records": [
+ {
+ "name": "model.embed_tokens.q_scale",
+ "shape": [
+ 152064,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 48660480,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "bddafd118b35c61adfdc893d17305824"
+ },
+ {
+ "dataPath": "params_shard_2.bin",
+ "format": "raw-shard",
+ "nbytes": 20658176,
+ "records": [
+ {
+ "name": "model.layers.0.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 14336,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.0.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 14336
+ },
+ {
+ "name": "model.layers.0.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 2293760,
+ "byteOffset": 18364416
+ }
+ ],
+ "md5sum": "19b135a2eb2fc9e75d27e9bbbf8222be"
+ },
+ {
+ "dataPath": "params_shard_3.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.0.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "96d61b6c6ff7eed03c0ec4c06af07b51"
+ },
+ {
+ "dataPath": "params_shard_4.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.0.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "e102203a2283d305c21639d73e71d5ec"
+ },
+ {
+ "dataPath": "params_shard_5.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.0.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.0.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.0.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "137d40dd6f3737c2f568c96e734cfdf8"
+ },
+ {
+ "dataPath": "params_shard_6.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.0.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.0.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.0.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.1.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.1.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.1.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "9b66adfd9fc06e9a60ca90c405e3b17c"
+ },
+ {
+ "dataPath": "params_shard_7.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.1.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "2da0b79e411092e6d5f84cc34475b6ff"
+ },
+ {
+ "dataPath": "params_shard_8.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.1.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "d9e2025aab4b50028a62018aad13e522"
+ },
+ {
+ "dataPath": "params_shard_9.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.1.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.1.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.1.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "670e73698a4bcd95406832720b1107a1"
+ },
+ {
+ "dataPath": "params_shard_10.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.1.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.1.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.1.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.2.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.2.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.2.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "894bd9def86ba5351a39a0b86d426a83"
+ },
+ {
+ "dataPath": "params_shard_11.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.2.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "450d8eecd0b1c197901958fb8bb9ac83"
+ },
+ {
+ "dataPath": "params_shard_12.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.2.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "d025e698135c43d2ec55c1a519c31cb5"
+ },
+ {
+ "dataPath": "params_shard_13.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.2.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.2.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.2.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "1d05f468c62b8b67858466bb71fe0f16"
+ },
+ {
+ "dataPath": "params_shard_14.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.2.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.2.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.2.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.3.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.3.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.3.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "1824fac088ce6e4cb8a431e6f6824a64"
+ },
+ {
+ "dataPath": "params_shard_15.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.3.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "95be36fc27e2af5072f34ffdc88b50fd"
+ },
+ {
+ "dataPath": "params_shard_16.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.3.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "2c70805174ae2c441aa87f0c447ccfc7"
+ },
+ {
+ "dataPath": "params_shard_17.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.3.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.3.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.3.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "9a6b806376439ebc53754af16bc4af01"
+ },
+ {
+ "dataPath": "params_shard_18.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.3.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.3.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.3.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.4.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.4.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.4.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "78ec449cbff1bb0c519719a128cadf13"
+ },
+ {
+ "dataPath": "params_shard_19.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.4.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "63ba4206daf94c714bad8c134b87f2c1"
+ },
+ {
+ "dataPath": "params_shard_20.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.4.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "cce4f63aba4b501535bb50c941ad0256"
+ },
+ {
+ "dataPath": "params_shard_21.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.4.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.4.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.4.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "5a1b8cb3489a5d22ede126946bfbc1ad"
+ },
+ {
+ "dataPath": "params_shard_22.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.4.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.4.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.4.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.5.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.5.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.5.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "0fb98aa8df1d6ccb1b371d01e6c9ea0d"
+ },
+ {
+ "dataPath": "params_shard_23.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.5.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "fc30e8c13cf738369279b67126432fd8"
+ },
+ {
+ "dataPath": "params_shard_24.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.5.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "a58e650b8d6fb216fb6ef26a7a17b454"
+ },
+ {
+ "dataPath": "params_shard_25.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.5.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.5.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.5.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "61d178956ae74f905644aa5b555e1cee"
+ },
+ {
+ "dataPath": "params_shard_26.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.5.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.5.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.5.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.6.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.6.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.6.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "ed4957794b3adf02335125f4f949210a"
+ },
+ {
+ "dataPath": "params_shard_27.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.6.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "4d008331d44d3491defce907cb4216a4"
+ },
+ {
+ "dataPath": "params_shard_28.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.6.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "a288322ad20835b49e60aabbe2d5f005"
+ },
+ {
+ "dataPath": "params_shard_29.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.6.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.6.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.6.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "2bb19542ece2f2f5d36322696040c13d"
+ },
+ {
+ "dataPath": "params_shard_30.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.6.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.6.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.6.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.7.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.7.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.7.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "6eef4376e35236e62e9c4ed19e61cccf"
+ },
+ {
+ "dataPath": "params_shard_31.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.7.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "020f73c90fed27f64f92a04c3ad7c604"
+ },
+ {
+ "dataPath": "params_shard_32.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.7.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "0537d151962b63b1a9155689f71ec607"
+ },
+ {
+ "dataPath": "params_shard_33.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.7.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.7.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.7.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "fcdeb5497cc9615e6d0408fe473d9ce0"
+ },
+ {
+ "dataPath": "params_shard_34.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.7.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.7.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.7.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.8.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.8.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.8.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "54d43f3df746cd1a724666239129a18d"
+ },
+ {
+ "dataPath": "params_shard_35.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.8.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "41790ff97c4fb2b3f66ded81d692a3ea"
+ },
+ {
+ "dataPath": "params_shard_36.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.8.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "3ad1843a21e24195895ff3e6e8db01f4"
+ },
+ {
+ "dataPath": "params_shard_37.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.8.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.8.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.8.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "f76b43fbfea3d75c090cdf9f105c62b8"
+ },
+ {
+ "dataPath": "params_shard_38.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.8.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.8.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.8.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.9.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.9.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.9.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "3cbd6ffa460215417908745c6b13ea25"
+ },
+ {
+ "dataPath": "params_shard_39.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.9.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "912c59fe92c4267ffddb20ce25919179"
+ },
+ {
+ "dataPath": "params_shard_40.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.9.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "9852b7516b561dbd7fb8865328aa9be0"
+ },
+ {
+ "dataPath": "params_shard_41.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.9.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.9.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.9.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "e3a8e18066f09a6eeaecbf0055fe02da"
+ },
+ {
+ "dataPath": "params_shard_42.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.9.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.9.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.9.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.10.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.10.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.10.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "5843c4ef81f00e967a891cf030f156f5"
+ },
+ {
+ "dataPath": "params_shard_43.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.10.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "cdc786bbc8ac85c5dbf516af6d985379"
+ },
+ {
+ "dataPath": "params_shard_44.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.10.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "15fdc367a5c861a466216ee604d108e4"
+ },
+ {
+ "dataPath": "params_shard_45.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.10.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.10.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.10.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "8eee545b4355ad5e23397ed46ff954b1"
+ },
+ {
+ "dataPath": "params_shard_46.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.10.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.10.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.10.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.11.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.11.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.11.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "7d7e4c354a8408e18bcb5376e015e6d2"
+ },
+ {
+ "dataPath": "params_shard_47.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.11.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "fbf236e88bc15238e5b8d85fccff18cd"
+ },
+ {
+ "dataPath": "params_shard_48.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.11.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "fc13cc1718c7cbd480765f0c68fe1bdb"
+ },
+ {
+ "dataPath": "params_shard_49.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.11.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.11.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.11.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "ca9da765e9c61456c3c99a03d2adab60"
+ },
+ {
+ "dataPath": "params_shard_50.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.11.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.11.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.11.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.12.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.12.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.12.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "40c2c199df2bafd7e5013a9d7f0b2768"
+ },
+ {
+ "dataPath": "params_shard_51.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.12.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "43ebd90127e550305d0fb5fd68d6c28a"
+ },
+ {
+ "dataPath": "params_shard_52.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.12.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "69d02941d620f906df4e74a4909e6144"
+ },
+ {
+ "dataPath": "params_shard_53.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.12.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.12.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.12.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "96e9da15f45b85eb89177ed947f38142"
+ },
+ {
+ "dataPath": "params_shard_54.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.12.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.12.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.12.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.13.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.13.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.13.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "7b93708d4243232f1dd6434eb87d79ef"
+ },
+ {
+ "dataPath": "params_shard_55.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.13.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "dedb15a35080aba3a55342e9066d9319"
+ },
+ {
+ "dataPath": "params_shard_56.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.13.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "264527d6572e190b42f5ff7a1d1ffd98"
+ },
+ {
+ "dataPath": "params_shard_57.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.13.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.13.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.13.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "5d58f5f4f467027a250ebede065c6d3c"
+ },
+ {
+ "dataPath": "params_shard_58.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.13.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.13.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.13.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.14.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.14.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.14.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "fad56ee36f05261e7d8164ce1dac2f5e"
+ },
+ {
+ "dataPath": "params_shard_59.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.14.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "ca82f259eaacbabb76218fff57afbbef"
+ },
+ {
+ "dataPath": "params_shard_60.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.14.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "bfd0013ccb55775edcca13c49e874992"
+ },
+ {
+ "dataPath": "params_shard_61.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.14.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.14.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.14.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "140e46d472a55960ef02fb13306c0cf3"
+ },
+ {
+ "dataPath": "params_shard_62.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.14.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.14.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.14.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.15.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.15.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.15.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "699802b56968d7c268fbde7cdd7b8880"
+ },
+ {
+ "dataPath": "params_shard_63.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.15.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "049015ddb63b7b9a7f939a6be8e276be"
+ },
+ {
+ "dataPath": "params_shard_64.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.15.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "a6eb79588ba89a69f8ee037e81857a37"
+ },
+ {
+ "dataPath": "params_shard_65.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.15.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.15.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.15.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "33dc46946da56d6401e201f47f5aaa4d"
+ },
+ {
+ "dataPath": "params_shard_66.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.15.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.15.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.15.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.16.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.16.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.16.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "e56cc62d757c3035b98b82a077a4fc7f"
+ },
+ {
+ "dataPath": "params_shard_67.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.16.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "9d951a658d29edac6d58b7abd2b1d303"
+ },
+ {
+ "dataPath": "params_shard_68.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.16.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "5368cdb100d69f3e39059a4c74b79a7a"
+ },
+ {
+ "dataPath": "params_shard_69.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.16.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.16.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.16.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "0f81a597c68d3787141411f38f14a510"
+ },
+ {
+ "dataPath": "params_shard_70.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.16.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.16.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.16.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.17.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.17.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.17.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "74730724666239da8d66fc69ee951bdc"
+ },
+ {
+ "dataPath": "params_shard_71.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.17.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "c9d556d84fff39b2157e42fb667e372c"
+ },
+ {
+ "dataPath": "params_shard_72.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.17.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "a536a22ea9095c94383e5f228acadd51"
+ },
+ {
+ "dataPath": "params_shard_73.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.17.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.17.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.17.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "8c064fd2dbc57c49c121988504bc9aa2"
+ },
+ {
+ "dataPath": "params_shard_74.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.17.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.17.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.17.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.18.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.18.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.18.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "a9c7581a7393c2c40a052933c45744b2"
+ },
+ {
+ "dataPath": "params_shard_75.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.18.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "c2d1a4e57274259f4bedabdd25508d53"
+ },
+ {
+ "dataPath": "params_shard_76.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.18.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "76ae742e6a343339da20c923db42cc7e"
+ },
+ {
+ "dataPath": "params_shard_77.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.18.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.18.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.18.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "dee16861587bba6f8652f9eedaa61c93"
+ },
+ {
+ "dataPath": "params_shard_78.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.18.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.18.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.18.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.19.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.19.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.19.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "55513331194fdc67f22b9bc479b85f0a"
+ },
+ {
+ "dataPath": "params_shard_79.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.19.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "ba873eb1b7f3b6a31328a7a9e3b950a3"
+ },
+ {
+ "dataPath": "params_shard_80.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.19.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "68a7bcdd600074debd8f22b7b34b0062"
+ },
+ {
+ "dataPath": "params_shard_81.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.19.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.19.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.19.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "218e66fb190d5f7334deed66da8811e2"
+ },
+ {
+ "dataPath": "params_shard_82.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.19.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.19.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.19.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.20.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.20.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.20.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "7ce627eca84d769b856f4b12d196c909"
+ },
+ {
+ "dataPath": "params_shard_83.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.20.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "bc7145d5904e1570d39ecf205d9afd89"
+ },
+ {
+ "dataPath": "params_shard_84.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.20.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "0a34b01b05830af72b0c568d47e836c4"
+ },
+ {
+ "dataPath": "params_shard_85.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.20.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.20.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.20.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "e3d5a64b41fbc416ef19e676d765ee4e"
+ },
+ {
+ "dataPath": "params_shard_86.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.20.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.20.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.20.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.21.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.21.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.21.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "8735d172684d7c48263cdcda7fba79fd"
+ },
+ {
+ "dataPath": "params_shard_87.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.21.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "86eda476773b957e344a409f375541f7"
+ },
+ {
+ "dataPath": "params_shard_88.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.21.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "1c7c1c5f1120b75049946cd39e1597e9"
+ },
+ {
+ "dataPath": "params_shard_89.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.21.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.21.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.21.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "1edc28f3f3ef940cd1d9c9c59fa25f65"
+ },
+ {
+ "dataPath": "params_shard_90.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.21.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.21.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.21.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.22.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.22.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.22.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "168974eae400fab555641d1aa2ef5bd6"
+ },
+ {
+ "dataPath": "params_shard_91.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.22.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "a0fb3e421bd805b3891d2b1a01ca0628"
+ },
+ {
+ "dataPath": "params_shard_92.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.22.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "d19026ce054dba56d76d7ce23bb5f062"
+ },
+ {
+ "dataPath": "params_shard_93.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.22.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.22.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.22.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "96dbae919b4c1c31035cc128b1befab7"
+ },
+ {
+ "dataPath": "params_shard_94.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.22.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.22.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.22.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.23.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.23.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.23.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "7c9d064e9a59d59b3a9917d366b03171"
+ },
+ {
+ "dataPath": "params_shard_95.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.23.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "17ac8e3f3cb20725188ffa9202692f6b"
+ },
+ {
+ "dataPath": "params_shard_96.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.23.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "8c5645ad43bf5864a20bd160066f47d1"
+ },
+ {
+ "dataPath": "params_shard_97.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.23.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.23.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.23.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "684ba24a4d1df17f0b8a6d31a4cc592a"
+ },
+ {
+ "dataPath": "params_shard_98.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.23.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.23.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.23.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.24.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.24.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.24.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "ee6d4c1abd0e1e5c6da64c27f9fbb476"
+ },
+ {
+ "dataPath": "params_shard_99.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.24.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "01080c3099d51bbb061f878d693b1455"
+ },
+ {
+ "dataPath": "params_shard_100.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.24.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "22c4522d55d3ba75da4fe61289ea5a08"
+ },
+ {
+ "dataPath": "params_shard_101.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.24.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.24.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.24.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "1913e9b87cb7dd69097a2702e81f9b11"
+ },
+ {
+ "dataPath": "params_shard_102.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.24.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.24.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.24.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.25.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.25.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.25.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "7025e9831d82de8c8a2ce645793821dd"
+ },
+ {
+ "dataPath": "params_shard_103.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.25.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "de9b75531929690e894bb1bdfb2ef97c"
+ },
+ {
+ "dataPath": "params_shard_104.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.25.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "8dca9a4901b30a6714a667990f7837d7"
+ },
+ {
+ "dataPath": "params_shard_105.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.25.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.25.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.25.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "9e50ffaeb882f1077db4eec3891a6113"
+ },
+ {
+ "dataPath": "params_shard_106.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.25.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.25.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.25.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.26.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.26.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.26.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "705da59b51915b542edafa8003c4700a"
+ },
+ {
+ "dataPath": "params_shard_107.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.26.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "06bab1fd4acda03e0e7a0087e94062cb"
+ },
+ {
+ "dataPath": "params_shard_108.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.26.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "4571b2586d5a793d09de3a9d5979b63a"
+ },
+ {
+ "dataPath": "params_shard_109.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.26.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.26.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.26.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "f3068f56cec0b3d716a60c180e84485b"
+ },
+ {
+ "dataPath": "params_shard_110.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.26.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.26.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.26.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.27.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.27.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.27.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "cb33d0b6528d47f65e7d0be4b6f79cfc"
+ },
+ {
+ "dataPath": "params_shard_111.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.27.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "5dc6b14108e49e4de9b758e7c58defb7"
+ },
+ {
+ "dataPath": "params_shard_112.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.27.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "ab4d214ebc3a59b454543a84b45841cd"
+ },
+ {
+ "dataPath": "params_shard_113.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.27.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.27.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.27.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "8ef0085c4f981a806092de6349e09afe"
+ },
+ {
+ "dataPath": "params_shard_114.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.27.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.27.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.27.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.28.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.28.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.28.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "55d6d2b27510aba58ce528e5ad31bf37"
+ },
+ {
+ "dataPath": "params_shard_115.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.28.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "1d82218603869d6d45991a0fce328ec3"
+ },
+ {
+ "dataPath": "params_shard_116.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.28.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "b4c7025553f3e53d015fd87153e9e62f"
+ },
+ {
+ "dataPath": "params_shard_117.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.28.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.28.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.28.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "3ba369687c5c8c4481066f3dac2cd08b"
+ },
+ {
+ "dataPath": "params_shard_118.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.28.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.28.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.28.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.29.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.29.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.29.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "948df02988a0d19a7f54986651829048"
+ },
+ {
+ "dataPath": "params_shard_119.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.29.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "f93a58cb9c20f7d021390116f05ae9cd"
+ },
+ {
+ "dataPath": "params_shard_120.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.29.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "a01e4cea537f55d5a27b200d2f74e7a6"
+ },
+ {
+ "dataPath": "params_shard_121.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.29.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.29.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.29.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "2e6852e453456f8be5d35bcf5246c1ea"
+ },
+ {
+ "dataPath": "params_shard_122.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.29.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.29.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.29.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.30.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.30.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.30.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "6f7f3f3ba57a09d69ea385c358755dcf"
+ },
+ {
+ "dataPath": "params_shard_123.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.30.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "c3cce73c0044e27aa85e30c0ed0a235f"
+ },
+ {
+ "dataPath": "params_shard_124.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.30.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "f63eac081500f2adf4bbf8b76bbf4c10"
+ },
+ {
+ "dataPath": "params_shard_125.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.30.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.30.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.30.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "ee0b78cd4742e3a14ec654ddebb0c8cd"
+ },
+ {
+ "dataPath": "params_shard_126.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.30.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.30.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.30.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.31.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.31.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.31.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "a7d808207e9992255f5c3e9e3eb5e7fa"
+ },
+ {
+ "dataPath": "params_shard_127.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.31.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "897e9088b50e7df2dcfaf535755a7df6"
+ },
+ {
+ "dataPath": "params_shard_128.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.31.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "4133fbeaddc366f4eb53a5f9f958c59c"
+ },
+ {
+ "dataPath": "params_shard_129.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.31.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.31.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.31.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "a693790bf96fcb6a443b118188b2fab8"
+ },
+ {
+ "dataPath": "params_shard_130.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.31.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.31.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.31.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.32.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.32.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.32.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "f1897ee6dc2bbffd32762a9573967ef2"
+ },
+ {
+ "dataPath": "params_shard_131.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.32.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "e41ad6a243695ab694829e42a5aaa0da"
+ },
+ {
+ "dataPath": "params_shard_132.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.32.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "44a01da91b46dfac179afb3875a00bfb"
+ },
+ {
+ "dataPath": "params_shard_133.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.32.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.32.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.32.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "d9e05b0db2fe692bf577150972ca1b46"
+ },
+ {
+ "dataPath": "params_shard_134.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.32.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.32.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.32.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.33.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.33.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.33.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "d691d31a6b8b3f56fea92fd35d7257ab"
+ },
+ {
+ "dataPath": "params_shard_135.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.33.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "fd114b52335d726e693ba042cf18d760"
+ },
+ {
+ "dataPath": "params_shard_136.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.33.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "35a3a39d22cbca791eefadc02850fb54"
+ },
+ {
+ "dataPath": "params_shard_137.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.33.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.33.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.33.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "c9603929fccd321415feecb7a3d39aff"
+ },
+ {
+ "dataPath": "params_shard_138.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.33.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.33.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.33.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.34.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.34.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.34.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "dc53aaf9e0dc6f0aa533e6378f19a2f7"
+ },
+ {
+ "dataPath": "params_shard_139.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.34.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "962ac5b9fadb98a80d8ac08e585eabbd"
+ },
+ {
+ "dataPath": "params_shard_140.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.34.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "76c991101adb7674927a925091a2b782"
+ },
+ {
+ "dataPath": "params_shard_141.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.34.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.34.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.34.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "2bac3d9eff1f2b4640222ed88eb556d6"
+ },
+ {
+ "dataPath": "params_shard_142.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.34.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.34.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.34.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.35.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.35.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.35.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "e9104e8e4d223f898eaa527e237fa814"
+ },
+ {
+ "dataPath": "params_shard_143.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.35.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "825327b0c3fe5b22a2a089945a2b13be"
+ },
+ {
+ "dataPath": "params_shard_144.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.35.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "eb914ffa9e97d8fc380abeb7571f25ff"
+ },
+ {
+ "dataPath": "params_shard_145.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.35.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.35.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.35.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "62a7d34aa6bcb699d5ff34dde670b252"
+ },
+ {
+ "dataPath": "params_shard_146.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.35.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.35.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.35.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.36.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.36.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.36.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "5e2e1d5ee46ab6e7b1d01a935cc434b1"
+ },
+ {
+ "dataPath": "params_shard_147.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.36.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "ccc6c7f43bb43d3c11598e2ad335bab3"
+ },
+ {
+ "dataPath": "params_shard_148.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.36.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "2c039f2f46558c83945571a5d8906733"
+ },
+ {
+ "dataPath": "params_shard_149.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.36.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.36.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.36.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "94667f75873c81ba0ea41ebf3996061c"
+ },
+ {
+ "dataPath": "params_shard_150.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.36.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.36.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.36.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.37.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.37.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.37.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "fcce211afc88cf0bfec729e3cf43bf5a"
+ },
+ {
+ "dataPath": "params_shard_151.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.37.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "d93b539242e2e35021792a9c7a9eb421"
+ },
+ {
+ "dataPath": "params_shard_152.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.37.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "8cc334c3d0fd4e8081953f17af91e9b2"
+ },
+ {
+ "dataPath": "params_shard_153.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.37.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.37.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.37.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "aeeae62fc71cd93870a8ebfef2c3651a"
+ },
+ {
+ "dataPath": "params_shard_154.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.37.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.37.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.37.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.38.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.38.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.38.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "82dbc785f53946f30ab25a9312771c08"
+ },
+ {
+ "dataPath": "params_shard_155.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.38.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "661dc4c8725b5cf23d91fcac3a79770a"
+ },
+ {
+ "dataPath": "params_shard_156.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.38.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "e7613be59ad90a50b58d4573950e1425"
+ },
+ {
+ "dataPath": "params_shard_157.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.38.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.38.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.38.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "b3fc63d69813f37d0409d1caa968a3a2"
+ },
+ {
+ "dataPath": "params_shard_158.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.38.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.38.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.38.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.39.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.39.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.39.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "aef64a9487d469b087fa749b17f51fe1"
+ },
+ {
+ "dataPath": "params_shard_159.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.39.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "1ae02bddb160db37712c6ea66c6a2804"
+ },
+ {
+ "dataPath": "params_shard_160.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.39.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "1e05eae54a6746dffd004b79fd229d54"
+ },
+ {
+ "dataPath": "params_shard_161.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.39.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.39.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.39.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "0550c1fffee045b3aba22666f4d4f065"
+ },
+ {
+ "dataPath": "params_shard_162.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.39.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.39.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.39.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.40.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.40.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.40.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "24f5ead4840e936bbee0625244a8a1cd"
+ },
+ {
+ "dataPath": "params_shard_163.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.40.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "902bf1082271f405dd765d01a6e371df"
+ },
+ {
+ "dataPath": "params_shard_164.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.40.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "74d570aa041b6b192f01b1d746bbbde0"
+ },
+ {
+ "dataPath": "params_shard_165.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.40.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.40.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.40.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "4b5532357829abe108014d35ffdda2a3"
+ },
+ {
+ "dataPath": "params_shard_166.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.40.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.40.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.40.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.41.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.41.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.41.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "790b440fadda515e72e7468812640bf2"
+ },
+ {
+ "dataPath": "params_shard_167.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.41.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "e6b52f1acec96b951a6c1fbad03f3836"
+ },
+ {
+ "dataPath": "params_shard_168.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.41.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "9f6826986ab773642c95ae0727a238a1"
+ },
+ {
+ "dataPath": "params_shard_169.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.41.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.41.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.41.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "72918479845cabd9ffa18596933997d3"
+ },
+ {
+ "dataPath": "params_shard_170.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.41.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.41.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.41.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.42.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.42.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.42.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "d3871774ecc0334832ed730a3b803a92"
+ },
+ {
+ "dataPath": "params_shard_171.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.42.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "5ac7b7b56162e160cc7fbed895453641"
+ },
+ {
+ "dataPath": "params_shard_172.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.42.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "df4aa0c2c90330291d867080848087f1"
+ },
+ {
+ "dataPath": "params_shard_173.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.42.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.42.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.42.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "843c606092d20d006e237743e1b739dd"
+ },
+ {
+ "dataPath": "params_shard_174.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.42.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.42.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.42.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.43.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.43.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.43.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "4118d86c539f100ca839c4a74e4ea4e7"
+ },
+ {
+ "dataPath": "params_shard_175.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.43.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "451e73739a5ed60e01b7d5b553b32feb"
+ },
+ {
+ "dataPath": "params_shard_176.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.43.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "f9462c6abbcd009163cbf6374cf2a6ce"
+ },
+ {
+ "dataPath": "params_shard_177.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.43.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.43.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.43.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "16ee877a871f5623078c6995f5bf292e"
+ },
+ {
+ "dataPath": "params_shard_178.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.43.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.43.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.43.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.44.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.44.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.44.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "81ee6ea436c74e926e878fe748c5b879"
+ },
+ {
+ "dataPath": "params_shard_179.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.44.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "677d4dd18121d6c1384942cd5d0d673f"
+ },
+ {
+ "dataPath": "params_shard_180.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.44.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "6e33e4f3fdb5ccf53d52f2fdf9a5e78f"
+ },
+ {
+ "dataPath": "params_shard_181.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.44.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.44.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.44.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "614c99c51f2c784bd2d9384a17b64f99"
+ },
+ {
+ "dataPath": "params_shard_182.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.44.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.44.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.44.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.45.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.45.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.45.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "2d52e0fff04b1a2cf7d0d9c1e9557c59"
+ },
+ {
+ "dataPath": "params_shard_183.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.45.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "8bd4d30299375dde2c9f29e55043c949"
+ },
+ {
+ "dataPath": "params_shard_184.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.45.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "fac4acc8f18ecfa2a6e34cf89fcb499b"
+ },
+ {
+ "dataPath": "params_shard_185.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.45.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.45.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.45.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "3fc58a97f6b5c1684d04182538e6cc4a"
+ },
+ {
+ "dataPath": "params_shard_186.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.45.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.45.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.45.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.46.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.46.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.46.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "e8e12302324a85c6cbb293998057080c"
+ },
+ {
+ "dataPath": "params_shard_187.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.46.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "34cfd38623478dfcc1c6094e1fb859d2"
+ },
+ {
+ "dataPath": "params_shard_188.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.46.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "62e122e98cd6bfdc8885ff6bddff1b0d"
+ },
+ {
+ "dataPath": "params_shard_189.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.46.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.46.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.46.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "edb68a54c9a80e48400abfdd44a3b901"
+ },
+ {
+ "dataPath": "params_shard_190.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.46.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.46.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.46.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.47.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.47.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.47.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "7be5bff882acdfe8c31bfea11c85b728"
+ },
+ {
+ "dataPath": "params_shard_191.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.47.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "e7a561097d43b054dd924aecbb7e343e"
+ },
+ {
+ "dataPath": "params_shard_192.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.47.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "210a9080788a15dd27871702d584d9ae"
+ },
+ {
+ "dataPath": "params_shard_193.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.47.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.47.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.47.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "bf2e6a4447b8ec22d517bc6a2c98935e"
+ },
+ {
+ "dataPath": "params_shard_194.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.47.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.47.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.47.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.48.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.48.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.48.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "91e87c91000cb343cf97335234778e89"
+ },
+ {
+ "dataPath": "params_shard_195.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.48.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "47ff16ca99b30631b19038815b30df1a"
+ },
+ {
+ "dataPath": "params_shard_196.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.48.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "38a9f63418bf283f40bc53cf7f52c677"
+ },
+ {
+ "dataPath": "params_shard_197.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.48.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.48.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.48.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "2bf46302659f98a9c4e73603b0d6cb3c"
+ },
+ {
+ "dataPath": "params_shard_198.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.48.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.48.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.48.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.49.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.49.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.49.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "e487cb58f97f0a467e6eb97524a28330"
+ },
+ {
+ "dataPath": "params_shard_199.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.49.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "af3633b85dc2252e33357ee3a142afc0"
+ },
+ {
+ "dataPath": "params_shard_200.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.49.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "c323236c7d5ad90d938ec35d7380fb05"
+ },
+ {
+ "dataPath": "params_shard_201.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.49.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.49.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.49.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "409f66d2c1eeb2b949360d040778e702"
+ },
+ {
+ "dataPath": "params_shard_202.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.49.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.49.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.49.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.50.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.50.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.50.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "fc1311fadb535c9c3fedca2a6890738a"
+ },
+ {
+ "dataPath": "params_shard_203.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.50.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "eac2ed57c9f5358dcc0d21b1c9efd8ce"
+ },
+ {
+ "dataPath": "params_shard_204.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.50.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "29b3edf73bc7cc03db7d2dc8ea51dba4"
+ },
+ {
+ "dataPath": "params_shard_205.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.50.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.50.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.50.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "da791060584b4716257f7375f4590ade"
+ },
+ {
+ "dataPath": "params_shard_206.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.50.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.50.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.50.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.51.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.51.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.51.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "3a4071691b01dbd696bd14ef8238c705"
+ },
+ {
+ "dataPath": "params_shard_207.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.51.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "68f5c10d8b1c5957fd340a285f48596a"
+ },
+ {
+ "dataPath": "params_shard_208.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.51.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "cdacb7674985f29c7ca6531013533397"
+ },
+ {
+ "dataPath": "params_shard_209.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.51.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.51.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.51.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "d7551478b67f2887da11d67e1b20458f"
+ },
+ {
+ "dataPath": "params_shard_210.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.51.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.51.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.51.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.52.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.52.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.52.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "54f7bc560548972b35f9dde8dd422cbb"
+ },
+ {
+ "dataPath": "params_shard_211.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.52.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "ae9ea3d6e6c71851067d17709d1bae70"
+ },
+ {
+ "dataPath": "params_shard_212.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.52.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "f55b48e6466d6c36d75c6131a081d90b"
+ },
+ {
+ "dataPath": "params_shard_213.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.52.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.52.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.52.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "cc538747c1184efbee56864cadc86e89"
+ },
+ {
+ "dataPath": "params_shard_214.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.52.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.52.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.52.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.53.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.53.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.53.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "c4eda8ac90b7eb8d82ba1102f7b60d4b"
+ },
+ {
+ "dataPath": "params_shard_215.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.53.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "86692eabd67ea856a536849544c63548"
+ },
+ {
+ "dataPath": "params_shard_216.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.53.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "34f7c76b2b978a3aef45b9002e859811"
+ },
+ {
+ "dataPath": "params_shard_217.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.53.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.53.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.53.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "44af0c7745184eee20b6ed83bb5b8a07"
+ },
+ {
+ "dataPath": "params_shard_218.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.53.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.53.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.53.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.54.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.54.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.54.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "af57982b4f1688b3ade911288382fdc1"
+ },
+ {
+ "dataPath": "params_shard_219.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.54.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "3b8f14132a2e28a95810e0afcdc3abc7"
+ },
+ {
+ "dataPath": "params_shard_220.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.54.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "24c2c4fab7e84045e0e74d5a3b417424"
+ },
+ {
+ "dataPath": "params_shard_221.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.54.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.54.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.54.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "95098a6acf673ecc3aeec1caa4cae215"
+ },
+ {
+ "dataPath": "params_shard_222.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.54.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.54.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.54.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.55.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.55.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.55.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "30fcd62f7301c9e64511e835dc76244c"
+ },
+ {
+ "dataPath": "params_shard_223.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.55.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "f57b06c96b3972c5c856d7749bc7dcc7"
+ },
+ {
+ "dataPath": "params_shard_224.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.55.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "16a9a10c4a39e534f43fbf65eb85a630"
+ },
+ {
+ "dataPath": "params_shard_225.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.55.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.55.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.55.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "544d25b93d84f058f17c7ce4f2ef7800"
+ },
+ {
+ "dataPath": "params_shard_226.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.55.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.55.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.55.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.56.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.56.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.56.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "2d98ff2a2723ad0bfbe072ae977f904d"
+ },
+ {
+ "dataPath": "params_shard_227.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.56.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "945b5232a36c056e0db5f14fb594f440"
+ },
+ {
+ "dataPath": "params_shard_228.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.56.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "f9889a8f3f5efa3134a4ea619e6685f0"
+ },
+ {
+ "dataPath": "params_shard_229.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.56.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.56.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.56.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "549eaaea20964eff92cf341f352cdadc"
+ },
+ {
+ "dataPath": "params_shard_230.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.56.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.56.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.56.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.57.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.57.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.57.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "3d18a3f5b7e0b20cfa76eb0324876a92"
+ },
+ {
+ "dataPath": "params_shard_231.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.57.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "269eb10ca8b5772ce5968d5ed029581a"
+ },
+ {
+ "dataPath": "params_shard_232.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.57.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "e2e52dca6d1ad243420fe6a6d8699674"
+ },
+ {
+ "dataPath": "params_shard_233.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.57.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.57.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.57.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "323ac3fcc94fc1934281230094c03901"
+ },
+ {
+ "dataPath": "params_shard_234.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.57.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.57.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.57.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.58.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.58.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.58.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "2f5cfeb4aabde62f0e4b53f731c8791c"
+ },
+ {
+ "dataPath": "params_shard_235.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.58.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "4168839b89b60ab8c8ad6c3d346ccc19"
+ },
+ {
+ "dataPath": "params_shard_236.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.58.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "e821edec5a7a89a983d06f63f32bc728"
+ },
+ {
+ "dataPath": "params_shard_237.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.58.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.58.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.58.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "cc15b783ccafe63a3228ae0602699852"
+ },
+ {
+ "dataPath": "params_shard_238.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.58.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.58.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.58.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.59.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.59.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.59.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "85a4c7747da90ca4a44916239bbf8434"
+ },
+ {
+ "dataPath": "params_shard_239.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.59.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "dda52034a4ea687ec109ae909734ca2d"
+ },
+ {
+ "dataPath": "params_shard_240.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.59.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "21ed06aed4398c4f1c92eadbf896e416"
+ },
+ {
+ "dataPath": "params_shard_241.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.59.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.59.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.59.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "4b444b1fbcd358fc60acdc117674cfc9"
+ },
+ {
+ "dataPath": "params_shard_242.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.59.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.59.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.59.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.60.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.60.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.60.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "fcefca8c351dfad6e373916cb69216b8"
+ },
+ {
+ "dataPath": "params_shard_243.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.60.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "00a0751370f3a8ce196ff1082b052455"
+ },
+ {
+ "dataPath": "params_shard_244.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.60.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "659600488165359cbdf8c3d1609ca439"
+ },
+ {
+ "dataPath": "params_shard_245.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.60.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.60.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.60.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "10a2ce38adf3324cf4bf46db38cee732"
+ },
+ {
+ "dataPath": "params_shard_246.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.60.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.60.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.60.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.61.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.61.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.61.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "3499d5386f61358d3bc4a6e2721f7c7f"
+ },
+ {
+ "dataPath": "params_shard_247.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.61.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "746fb385b3863da326ff76b8c23f44ee"
+ },
+ {
+ "dataPath": "params_shard_248.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.61.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "10b7036f961653e8110430c4e781fb72"
+ },
+ {
+ "dataPath": "params_shard_249.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.61.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.61.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.61.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "5636ed4aa6a3d2f59940f33911258b43"
+ },
+ {
+ "dataPath": "params_shard_250.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.61.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.61.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.61.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.62.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.62.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.62.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "58c577d390e62c3fd306fdfc8efa2b1b"
+ },
+ {
+ "dataPath": "params_shard_251.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.62.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "d9237342ed10fb225dea406295cd192d"
+ },
+ {
+ "dataPath": "params_shard_252.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.62.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "c251fec419e1720f311df06e60cf1877"
+ },
+ {
+ "dataPath": "params_shard_253.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.62.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.62.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.62.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "9f4bf2c1fcdf7514c83293bc9e1a6c1f"
+ },
+ {
+ "dataPath": "params_shard_254.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.62.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.62.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.62.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.63.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.63.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.63.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "e516d3cb8ba315555ad5d2eb418e8f68"
+ },
+ {
+ "dataPath": "params_shard_255.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.63.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "7a53f632cd0ab8b2ec1b0bb402683706"
+ },
+ {
+ "dataPath": "params_shard_256.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.63.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "8f32df5c5ce254ff05013edd5a52fe5d"
+ },
+ {
+ "dataPath": "params_shard_257.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.63.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.63.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.63.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "9a2777c1a378b3f9fcd4a7594d72e8dc"
+ },
+ {
+ "dataPath": "params_shard_258.bin",
+ "format": "raw-shard",
+ "nbytes": 389283840,
+ "records": [
+ {
+ "name": "lm_head.q_weight",
+ "shape": [
+ 152064,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 389283840,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "5621516379304600cc71159de28b8bc3"
+ },
+ {
+ "dataPath": "params_shard_259.bin",
+ "format": "raw-shard",
+ "nbytes": 48660480,
+ "records": [
+ {
+ "name": "lm_head.q_scale",
+ "shape": [
+ 152064,
+ 160
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 48660480,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "d9ecc5cc7681d72b16e032a7b83849b2"
+ },
+ {
+ "dataPath": "params_shard_260.bin",
+ "format": "raw-shard",
+ "nbytes": 8878080,
+ "records": [
+ {
+ "name": "model.layers.63.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.63.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.63.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.norm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "bfloat16",
+ "format": "raw",
+ "nbytes": 10240,
+ "byteOffset": 8867840
+ }
+ ],
+ "md5sum": "05481db171508742fb07f2572d1a3e13"
+ }
+ ]
+}
\ No newline at end of file
diff --git a/ndarray-cache.json b/ndarray-cache.json
new file mode 100644
index 0000000000000000000000000000000000000000..80e330463b13c1718cd1ea85862c86a07e8b1b77
--- /dev/null
+++ b/ndarray-cache.json
@@ -0,0 +1,9703 @@
+{
+ "metadata": {
+ "ParamSize": 709,
+ "ParamBytes": 20481200128.0,
+ "BitsPerParam": 5.000922334820072
+ },
+ "records": [
+ {
+ "dataPath": "params_shard_0.bin",
+ "format": "raw-shard",
+ "nbytes": 389283840,
+ "records": [
+ {
+ "name": "model.embed_tokens.q_weight",
+ "shape": [
+ 152064,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 389283840,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "a5d3556afbf5fa2be30ba135893b2676"
+ },
+ {
+ "dataPath": "params_shard_1.bin",
+ "format": "raw-shard",
+ "nbytes": 48660480,
+ "records": [
+ {
+ "name": "model.embed_tokens.q_scale",
+ "shape": [
+ 152064,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 48660480,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "bddafd118b35c61adfdc893d17305824"
+ },
+ {
+ "dataPath": "params_shard_2.bin",
+ "format": "raw-shard",
+ "nbytes": 20658176,
+ "records": [
+ {
+ "name": "model.layers.0.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 14336,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.0.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 14336
+ },
+ {
+ "name": "model.layers.0.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 2293760,
+ "byteOffset": 18364416
+ }
+ ],
+ "md5sum": "19b135a2eb2fc9e75d27e9bbbf8222be"
+ },
+ {
+ "dataPath": "params_shard_3.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.0.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "96d61b6c6ff7eed03c0ec4c06af07b51"
+ },
+ {
+ "dataPath": "params_shard_4.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.0.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "e102203a2283d305c21639d73e71d5ec"
+ },
+ {
+ "dataPath": "params_shard_5.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.0.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.0.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.0.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "137d40dd6f3737c2f568c96e734cfdf8"
+ },
+ {
+ "dataPath": "params_shard_6.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.0.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.0.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.0.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.1.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.1.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.1.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "9b66adfd9fc06e9a60ca90c405e3b17c"
+ },
+ {
+ "dataPath": "params_shard_7.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.1.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "2da0b79e411092e6d5f84cc34475b6ff"
+ },
+ {
+ "dataPath": "params_shard_8.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.1.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "d9e2025aab4b50028a62018aad13e522"
+ },
+ {
+ "dataPath": "params_shard_9.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.1.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.1.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.1.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "670e73698a4bcd95406832720b1107a1"
+ },
+ {
+ "dataPath": "params_shard_10.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.1.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.1.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.1.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.2.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.2.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.2.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "894bd9def86ba5351a39a0b86d426a83"
+ },
+ {
+ "dataPath": "params_shard_11.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.2.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "450d8eecd0b1c197901958fb8bb9ac83"
+ },
+ {
+ "dataPath": "params_shard_12.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.2.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "d025e698135c43d2ec55c1a519c31cb5"
+ },
+ {
+ "dataPath": "params_shard_13.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.2.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.2.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.2.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "1d05f468c62b8b67858466bb71fe0f16"
+ },
+ {
+ "dataPath": "params_shard_14.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.2.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.2.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.2.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.3.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.3.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.3.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "1824fac088ce6e4cb8a431e6f6824a64"
+ },
+ {
+ "dataPath": "params_shard_15.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.3.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "95be36fc27e2af5072f34ffdc88b50fd"
+ },
+ {
+ "dataPath": "params_shard_16.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.3.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "2c70805174ae2c441aa87f0c447ccfc7"
+ },
+ {
+ "dataPath": "params_shard_17.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.3.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.3.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.3.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "9a6b806376439ebc53754af16bc4af01"
+ },
+ {
+ "dataPath": "params_shard_18.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.3.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.3.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.3.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.4.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.4.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.4.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "78ec449cbff1bb0c519719a128cadf13"
+ },
+ {
+ "dataPath": "params_shard_19.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.4.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "63ba4206daf94c714bad8c134b87f2c1"
+ },
+ {
+ "dataPath": "params_shard_20.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.4.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "cce4f63aba4b501535bb50c941ad0256"
+ },
+ {
+ "dataPath": "params_shard_21.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.4.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.4.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.4.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "5a1b8cb3489a5d22ede126946bfbc1ad"
+ },
+ {
+ "dataPath": "params_shard_22.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.4.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.4.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.4.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.5.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.5.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.5.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "0fb98aa8df1d6ccb1b371d01e6c9ea0d"
+ },
+ {
+ "dataPath": "params_shard_23.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.5.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "fc30e8c13cf738369279b67126432fd8"
+ },
+ {
+ "dataPath": "params_shard_24.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.5.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "a58e650b8d6fb216fb6ef26a7a17b454"
+ },
+ {
+ "dataPath": "params_shard_25.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.5.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.5.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.5.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "61d178956ae74f905644aa5b555e1cee"
+ },
+ {
+ "dataPath": "params_shard_26.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.5.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.5.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.5.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.6.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.6.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.6.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "ed4957794b3adf02335125f4f949210a"
+ },
+ {
+ "dataPath": "params_shard_27.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.6.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "4d008331d44d3491defce907cb4216a4"
+ },
+ {
+ "dataPath": "params_shard_28.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.6.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "a288322ad20835b49e60aabbe2d5f005"
+ },
+ {
+ "dataPath": "params_shard_29.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.6.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.6.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.6.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "2bb19542ece2f2f5d36322696040c13d"
+ },
+ {
+ "dataPath": "params_shard_30.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.6.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.6.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.6.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.7.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.7.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.7.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "6eef4376e35236e62e9c4ed19e61cccf"
+ },
+ {
+ "dataPath": "params_shard_31.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.7.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "020f73c90fed27f64f92a04c3ad7c604"
+ },
+ {
+ "dataPath": "params_shard_32.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.7.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "0537d151962b63b1a9155689f71ec607"
+ },
+ {
+ "dataPath": "params_shard_33.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.7.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.7.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.7.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "fcdeb5497cc9615e6d0408fe473d9ce0"
+ },
+ {
+ "dataPath": "params_shard_34.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.7.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.7.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.7.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.8.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.8.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.8.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "54d43f3df746cd1a724666239129a18d"
+ },
+ {
+ "dataPath": "params_shard_35.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.8.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "41790ff97c4fb2b3f66ded81d692a3ea"
+ },
+ {
+ "dataPath": "params_shard_36.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.8.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "3ad1843a21e24195895ff3e6e8db01f4"
+ },
+ {
+ "dataPath": "params_shard_37.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.8.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.8.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.8.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "f76b43fbfea3d75c090cdf9f105c62b8"
+ },
+ {
+ "dataPath": "params_shard_38.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.8.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.8.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.8.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.9.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.9.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.9.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "3cbd6ffa460215417908745c6b13ea25"
+ },
+ {
+ "dataPath": "params_shard_39.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.9.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "912c59fe92c4267ffddb20ce25919179"
+ },
+ {
+ "dataPath": "params_shard_40.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.9.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "9852b7516b561dbd7fb8865328aa9be0"
+ },
+ {
+ "dataPath": "params_shard_41.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.9.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.9.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.9.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "e3a8e18066f09a6eeaecbf0055fe02da"
+ },
+ {
+ "dataPath": "params_shard_42.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.9.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.9.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.9.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.10.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.10.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.10.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "5843c4ef81f00e967a891cf030f156f5"
+ },
+ {
+ "dataPath": "params_shard_43.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.10.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "cdc786bbc8ac85c5dbf516af6d985379"
+ },
+ {
+ "dataPath": "params_shard_44.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.10.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "15fdc367a5c861a466216ee604d108e4"
+ },
+ {
+ "dataPath": "params_shard_45.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.10.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.10.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.10.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "8eee545b4355ad5e23397ed46ff954b1"
+ },
+ {
+ "dataPath": "params_shard_46.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.10.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.10.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.10.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.11.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.11.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.11.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "7d7e4c354a8408e18bcb5376e015e6d2"
+ },
+ {
+ "dataPath": "params_shard_47.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.11.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "fbf236e88bc15238e5b8d85fccff18cd"
+ },
+ {
+ "dataPath": "params_shard_48.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.11.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "fc13cc1718c7cbd480765f0c68fe1bdb"
+ },
+ {
+ "dataPath": "params_shard_49.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.11.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.11.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.11.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "ca9da765e9c61456c3c99a03d2adab60"
+ },
+ {
+ "dataPath": "params_shard_50.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.11.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.11.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.11.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.12.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.12.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.12.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "40c2c199df2bafd7e5013a9d7f0b2768"
+ },
+ {
+ "dataPath": "params_shard_51.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.12.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "43ebd90127e550305d0fb5fd68d6c28a"
+ },
+ {
+ "dataPath": "params_shard_52.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.12.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "69d02941d620f906df4e74a4909e6144"
+ },
+ {
+ "dataPath": "params_shard_53.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.12.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.12.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.12.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "96e9da15f45b85eb89177ed947f38142"
+ },
+ {
+ "dataPath": "params_shard_54.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.12.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.12.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.12.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.13.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.13.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.13.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "7b93708d4243232f1dd6434eb87d79ef"
+ },
+ {
+ "dataPath": "params_shard_55.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.13.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "dedb15a35080aba3a55342e9066d9319"
+ },
+ {
+ "dataPath": "params_shard_56.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.13.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "264527d6572e190b42f5ff7a1d1ffd98"
+ },
+ {
+ "dataPath": "params_shard_57.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.13.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.13.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.13.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "5d58f5f4f467027a250ebede065c6d3c"
+ },
+ {
+ "dataPath": "params_shard_58.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.13.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.13.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.13.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.14.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.14.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.14.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "fad56ee36f05261e7d8164ce1dac2f5e"
+ },
+ {
+ "dataPath": "params_shard_59.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.14.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "ca82f259eaacbabb76218fff57afbbef"
+ },
+ {
+ "dataPath": "params_shard_60.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.14.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "bfd0013ccb55775edcca13c49e874992"
+ },
+ {
+ "dataPath": "params_shard_61.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.14.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.14.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.14.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "140e46d472a55960ef02fb13306c0cf3"
+ },
+ {
+ "dataPath": "params_shard_62.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.14.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.14.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.14.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.15.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.15.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.15.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "699802b56968d7c268fbde7cdd7b8880"
+ },
+ {
+ "dataPath": "params_shard_63.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.15.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "049015ddb63b7b9a7f939a6be8e276be"
+ },
+ {
+ "dataPath": "params_shard_64.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.15.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "a6eb79588ba89a69f8ee037e81857a37"
+ },
+ {
+ "dataPath": "params_shard_65.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.15.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.15.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.15.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "33dc46946da56d6401e201f47f5aaa4d"
+ },
+ {
+ "dataPath": "params_shard_66.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.15.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.15.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.15.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.16.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.16.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.16.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "e56cc62d757c3035b98b82a077a4fc7f"
+ },
+ {
+ "dataPath": "params_shard_67.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.16.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "9d951a658d29edac6d58b7abd2b1d303"
+ },
+ {
+ "dataPath": "params_shard_68.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.16.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "5368cdb100d69f3e39059a4c74b79a7a"
+ },
+ {
+ "dataPath": "params_shard_69.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.16.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.16.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.16.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "0f81a597c68d3787141411f38f14a510"
+ },
+ {
+ "dataPath": "params_shard_70.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.16.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.16.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.16.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.17.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.17.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.17.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "74730724666239da8d66fc69ee951bdc"
+ },
+ {
+ "dataPath": "params_shard_71.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.17.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "c9d556d84fff39b2157e42fb667e372c"
+ },
+ {
+ "dataPath": "params_shard_72.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.17.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "a536a22ea9095c94383e5f228acadd51"
+ },
+ {
+ "dataPath": "params_shard_73.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.17.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.17.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.17.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "8c064fd2dbc57c49c121988504bc9aa2"
+ },
+ {
+ "dataPath": "params_shard_74.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.17.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.17.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.17.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.18.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.18.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.18.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "a9c7581a7393c2c40a052933c45744b2"
+ },
+ {
+ "dataPath": "params_shard_75.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.18.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "c2d1a4e57274259f4bedabdd25508d53"
+ },
+ {
+ "dataPath": "params_shard_76.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.18.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "76ae742e6a343339da20c923db42cc7e"
+ },
+ {
+ "dataPath": "params_shard_77.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.18.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.18.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.18.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "dee16861587bba6f8652f9eedaa61c93"
+ },
+ {
+ "dataPath": "params_shard_78.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.18.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.18.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.18.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.19.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.19.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.19.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "55513331194fdc67f22b9bc479b85f0a"
+ },
+ {
+ "dataPath": "params_shard_79.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.19.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "ba873eb1b7f3b6a31328a7a9e3b950a3"
+ },
+ {
+ "dataPath": "params_shard_80.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.19.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "68a7bcdd600074debd8f22b7b34b0062"
+ },
+ {
+ "dataPath": "params_shard_81.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.19.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.19.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.19.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "218e66fb190d5f7334deed66da8811e2"
+ },
+ {
+ "dataPath": "params_shard_82.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.19.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.19.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.19.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.20.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.20.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.20.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "7ce627eca84d769b856f4b12d196c909"
+ },
+ {
+ "dataPath": "params_shard_83.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.20.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "bc7145d5904e1570d39ecf205d9afd89"
+ },
+ {
+ "dataPath": "params_shard_84.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.20.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "0a34b01b05830af72b0c568d47e836c4"
+ },
+ {
+ "dataPath": "params_shard_85.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.20.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.20.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.20.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "e3d5a64b41fbc416ef19e676d765ee4e"
+ },
+ {
+ "dataPath": "params_shard_86.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.20.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.20.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.20.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.21.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.21.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.21.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "8735d172684d7c48263cdcda7fba79fd"
+ },
+ {
+ "dataPath": "params_shard_87.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.21.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "86eda476773b957e344a409f375541f7"
+ },
+ {
+ "dataPath": "params_shard_88.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.21.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "1c7c1c5f1120b75049946cd39e1597e9"
+ },
+ {
+ "dataPath": "params_shard_89.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.21.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.21.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.21.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "1edc28f3f3ef940cd1d9c9c59fa25f65"
+ },
+ {
+ "dataPath": "params_shard_90.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.21.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.21.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.21.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.22.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.22.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.22.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "168974eae400fab555641d1aa2ef5bd6"
+ },
+ {
+ "dataPath": "params_shard_91.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.22.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "a0fb3e421bd805b3891d2b1a01ca0628"
+ },
+ {
+ "dataPath": "params_shard_92.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.22.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "d19026ce054dba56d76d7ce23bb5f062"
+ },
+ {
+ "dataPath": "params_shard_93.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.22.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.22.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.22.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "96dbae919b4c1c31035cc128b1befab7"
+ },
+ {
+ "dataPath": "params_shard_94.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.22.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.22.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.22.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.23.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.23.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.23.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "7c9d064e9a59d59b3a9917d366b03171"
+ },
+ {
+ "dataPath": "params_shard_95.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.23.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "17ac8e3f3cb20725188ffa9202692f6b"
+ },
+ {
+ "dataPath": "params_shard_96.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.23.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "8c5645ad43bf5864a20bd160066f47d1"
+ },
+ {
+ "dataPath": "params_shard_97.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.23.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.23.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.23.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "684ba24a4d1df17f0b8a6d31a4cc592a"
+ },
+ {
+ "dataPath": "params_shard_98.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.23.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.23.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.23.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.24.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.24.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.24.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "ee6d4c1abd0e1e5c6da64c27f9fbb476"
+ },
+ {
+ "dataPath": "params_shard_99.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.24.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "01080c3099d51bbb061f878d693b1455"
+ },
+ {
+ "dataPath": "params_shard_100.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.24.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "22c4522d55d3ba75da4fe61289ea5a08"
+ },
+ {
+ "dataPath": "params_shard_101.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.24.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.24.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.24.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "1913e9b87cb7dd69097a2702e81f9b11"
+ },
+ {
+ "dataPath": "params_shard_102.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.24.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.24.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.24.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.25.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.25.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.25.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "7025e9831d82de8c8a2ce645793821dd"
+ },
+ {
+ "dataPath": "params_shard_103.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.25.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "de9b75531929690e894bb1bdfb2ef97c"
+ },
+ {
+ "dataPath": "params_shard_104.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.25.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "8dca9a4901b30a6714a667990f7837d7"
+ },
+ {
+ "dataPath": "params_shard_105.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.25.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.25.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.25.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "9e50ffaeb882f1077db4eec3891a6113"
+ },
+ {
+ "dataPath": "params_shard_106.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.25.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.25.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.25.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.26.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.26.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.26.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "705da59b51915b542edafa8003c4700a"
+ },
+ {
+ "dataPath": "params_shard_107.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.26.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "06bab1fd4acda03e0e7a0087e94062cb"
+ },
+ {
+ "dataPath": "params_shard_108.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.26.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "4571b2586d5a793d09de3a9d5979b63a"
+ },
+ {
+ "dataPath": "params_shard_109.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.26.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.26.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.26.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "f3068f56cec0b3d716a60c180e84485b"
+ },
+ {
+ "dataPath": "params_shard_110.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.26.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.26.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.26.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.27.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.27.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.27.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "cb33d0b6528d47f65e7d0be4b6f79cfc"
+ },
+ {
+ "dataPath": "params_shard_111.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.27.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "5dc6b14108e49e4de9b758e7c58defb7"
+ },
+ {
+ "dataPath": "params_shard_112.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.27.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "ab4d214ebc3a59b454543a84b45841cd"
+ },
+ {
+ "dataPath": "params_shard_113.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.27.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.27.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.27.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "8ef0085c4f981a806092de6349e09afe"
+ },
+ {
+ "dataPath": "params_shard_114.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.27.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.27.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.27.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.28.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.28.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.28.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "55d6d2b27510aba58ce528e5ad31bf37"
+ },
+ {
+ "dataPath": "params_shard_115.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.28.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "1d82218603869d6d45991a0fce328ec3"
+ },
+ {
+ "dataPath": "params_shard_116.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.28.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "b4c7025553f3e53d015fd87153e9e62f"
+ },
+ {
+ "dataPath": "params_shard_117.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.28.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.28.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.28.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "3ba369687c5c8c4481066f3dac2cd08b"
+ },
+ {
+ "dataPath": "params_shard_118.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.28.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.28.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.28.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.29.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.29.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.29.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "948df02988a0d19a7f54986651829048"
+ },
+ {
+ "dataPath": "params_shard_119.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.29.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "f93a58cb9c20f7d021390116f05ae9cd"
+ },
+ {
+ "dataPath": "params_shard_120.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.29.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "a01e4cea537f55d5a27b200d2f74e7a6"
+ },
+ {
+ "dataPath": "params_shard_121.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.29.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.29.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.29.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "2e6852e453456f8be5d35bcf5246c1ea"
+ },
+ {
+ "dataPath": "params_shard_122.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.29.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.29.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.29.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.30.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.30.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.30.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "6f7f3f3ba57a09d69ea385c358755dcf"
+ },
+ {
+ "dataPath": "params_shard_123.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.30.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "c3cce73c0044e27aa85e30c0ed0a235f"
+ },
+ {
+ "dataPath": "params_shard_124.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.30.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "f63eac081500f2adf4bbf8b76bbf4c10"
+ },
+ {
+ "dataPath": "params_shard_125.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.30.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.30.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.30.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "ee0b78cd4742e3a14ec654ddebb0c8cd"
+ },
+ {
+ "dataPath": "params_shard_126.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.30.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.30.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.30.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.31.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.31.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.31.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "a7d808207e9992255f5c3e9e3eb5e7fa"
+ },
+ {
+ "dataPath": "params_shard_127.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.31.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "897e9088b50e7df2dcfaf535755a7df6"
+ },
+ {
+ "dataPath": "params_shard_128.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.31.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "4133fbeaddc366f4eb53a5f9f958c59c"
+ },
+ {
+ "dataPath": "params_shard_129.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.31.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.31.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.31.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "a693790bf96fcb6a443b118188b2fab8"
+ },
+ {
+ "dataPath": "params_shard_130.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.31.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.31.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.31.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.32.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.32.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.32.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "f1897ee6dc2bbffd32762a9573967ef2"
+ },
+ {
+ "dataPath": "params_shard_131.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.32.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "e41ad6a243695ab694829e42a5aaa0da"
+ },
+ {
+ "dataPath": "params_shard_132.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.32.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "44a01da91b46dfac179afb3875a00bfb"
+ },
+ {
+ "dataPath": "params_shard_133.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.32.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.32.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.32.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "d9e05b0db2fe692bf577150972ca1b46"
+ },
+ {
+ "dataPath": "params_shard_134.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.32.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.32.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.32.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.33.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.33.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.33.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "d691d31a6b8b3f56fea92fd35d7257ab"
+ },
+ {
+ "dataPath": "params_shard_135.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.33.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "fd114b52335d726e693ba042cf18d760"
+ },
+ {
+ "dataPath": "params_shard_136.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.33.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "35a3a39d22cbca791eefadc02850fb54"
+ },
+ {
+ "dataPath": "params_shard_137.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.33.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.33.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.33.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "c9603929fccd321415feecb7a3d39aff"
+ },
+ {
+ "dataPath": "params_shard_138.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.33.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.33.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.33.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.34.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.34.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.34.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "dc53aaf9e0dc6f0aa533e6378f19a2f7"
+ },
+ {
+ "dataPath": "params_shard_139.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.34.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "962ac5b9fadb98a80d8ac08e585eabbd"
+ },
+ {
+ "dataPath": "params_shard_140.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.34.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "76c991101adb7674927a925091a2b782"
+ },
+ {
+ "dataPath": "params_shard_141.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.34.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.34.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.34.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "2bac3d9eff1f2b4640222ed88eb556d6"
+ },
+ {
+ "dataPath": "params_shard_142.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.34.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.34.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.34.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.35.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.35.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.35.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "e9104e8e4d223f898eaa527e237fa814"
+ },
+ {
+ "dataPath": "params_shard_143.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.35.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "825327b0c3fe5b22a2a089945a2b13be"
+ },
+ {
+ "dataPath": "params_shard_144.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.35.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "eb914ffa9e97d8fc380abeb7571f25ff"
+ },
+ {
+ "dataPath": "params_shard_145.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.35.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.35.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.35.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "62a7d34aa6bcb699d5ff34dde670b252"
+ },
+ {
+ "dataPath": "params_shard_146.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.35.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.35.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.35.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.36.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.36.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.36.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "5e2e1d5ee46ab6e7b1d01a935cc434b1"
+ },
+ {
+ "dataPath": "params_shard_147.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.36.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "ccc6c7f43bb43d3c11598e2ad335bab3"
+ },
+ {
+ "dataPath": "params_shard_148.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.36.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "2c039f2f46558c83945571a5d8906733"
+ },
+ {
+ "dataPath": "params_shard_149.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.36.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.36.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.36.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "94667f75873c81ba0ea41ebf3996061c"
+ },
+ {
+ "dataPath": "params_shard_150.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.36.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.36.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.36.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.37.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.37.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.37.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "fcce211afc88cf0bfec729e3cf43bf5a"
+ },
+ {
+ "dataPath": "params_shard_151.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.37.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "d93b539242e2e35021792a9c7a9eb421"
+ },
+ {
+ "dataPath": "params_shard_152.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.37.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "8cc334c3d0fd4e8081953f17af91e9b2"
+ },
+ {
+ "dataPath": "params_shard_153.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.37.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.37.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.37.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "aeeae62fc71cd93870a8ebfef2c3651a"
+ },
+ {
+ "dataPath": "params_shard_154.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.37.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.37.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.37.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.38.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.38.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.38.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "82dbc785f53946f30ab25a9312771c08"
+ },
+ {
+ "dataPath": "params_shard_155.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.38.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "661dc4c8725b5cf23d91fcac3a79770a"
+ },
+ {
+ "dataPath": "params_shard_156.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.38.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "e7613be59ad90a50b58d4573950e1425"
+ },
+ {
+ "dataPath": "params_shard_157.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.38.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.38.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.38.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "b3fc63d69813f37d0409d1caa968a3a2"
+ },
+ {
+ "dataPath": "params_shard_158.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.38.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.38.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.38.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.39.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.39.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.39.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "aef64a9487d469b087fa749b17f51fe1"
+ },
+ {
+ "dataPath": "params_shard_159.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.39.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "1ae02bddb160db37712c6ea66c6a2804"
+ },
+ {
+ "dataPath": "params_shard_160.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.39.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "1e05eae54a6746dffd004b79fd229d54"
+ },
+ {
+ "dataPath": "params_shard_161.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.39.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.39.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.39.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "0550c1fffee045b3aba22666f4d4f065"
+ },
+ {
+ "dataPath": "params_shard_162.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.39.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.39.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.39.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.40.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.40.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.40.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "24f5ead4840e936bbee0625244a8a1cd"
+ },
+ {
+ "dataPath": "params_shard_163.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.40.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "902bf1082271f405dd765d01a6e371df"
+ },
+ {
+ "dataPath": "params_shard_164.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.40.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "74d570aa041b6b192f01b1d746bbbde0"
+ },
+ {
+ "dataPath": "params_shard_165.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.40.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.40.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.40.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "4b5532357829abe108014d35ffdda2a3"
+ },
+ {
+ "dataPath": "params_shard_166.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.40.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.40.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.40.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.41.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.41.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.41.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "790b440fadda515e72e7468812640bf2"
+ },
+ {
+ "dataPath": "params_shard_167.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.41.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "e6b52f1acec96b951a6c1fbad03f3836"
+ },
+ {
+ "dataPath": "params_shard_168.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.41.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "9f6826986ab773642c95ae0727a238a1"
+ },
+ {
+ "dataPath": "params_shard_169.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.41.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.41.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.41.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "72918479845cabd9ffa18596933997d3"
+ },
+ {
+ "dataPath": "params_shard_170.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.41.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.41.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.41.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.42.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.42.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.42.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "d3871774ecc0334832ed730a3b803a92"
+ },
+ {
+ "dataPath": "params_shard_171.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.42.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "5ac7b7b56162e160cc7fbed895453641"
+ },
+ {
+ "dataPath": "params_shard_172.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.42.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "df4aa0c2c90330291d867080848087f1"
+ },
+ {
+ "dataPath": "params_shard_173.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.42.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.42.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.42.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "843c606092d20d006e237743e1b739dd"
+ },
+ {
+ "dataPath": "params_shard_174.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.42.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.42.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.42.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.43.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.43.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.43.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "4118d86c539f100ca839c4a74e4ea4e7"
+ },
+ {
+ "dataPath": "params_shard_175.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.43.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "451e73739a5ed60e01b7d5b553b32feb"
+ },
+ {
+ "dataPath": "params_shard_176.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.43.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "f9462c6abbcd009163cbf6374cf2a6ce"
+ },
+ {
+ "dataPath": "params_shard_177.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.43.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.43.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.43.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "16ee877a871f5623078c6995f5bf292e"
+ },
+ {
+ "dataPath": "params_shard_178.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.43.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.43.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.43.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.44.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.44.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.44.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "81ee6ea436c74e926e878fe748c5b879"
+ },
+ {
+ "dataPath": "params_shard_179.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.44.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "677d4dd18121d6c1384942cd5d0d673f"
+ },
+ {
+ "dataPath": "params_shard_180.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.44.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "6e33e4f3fdb5ccf53d52f2fdf9a5e78f"
+ },
+ {
+ "dataPath": "params_shard_181.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.44.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.44.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.44.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "614c99c51f2c784bd2d9384a17b64f99"
+ },
+ {
+ "dataPath": "params_shard_182.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.44.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.44.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.44.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.45.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.45.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.45.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "2d52e0fff04b1a2cf7d0d9c1e9557c59"
+ },
+ {
+ "dataPath": "params_shard_183.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.45.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "8bd4d30299375dde2c9f29e55043c949"
+ },
+ {
+ "dataPath": "params_shard_184.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.45.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "fac4acc8f18ecfa2a6e34cf89fcb499b"
+ },
+ {
+ "dataPath": "params_shard_185.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.45.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.45.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.45.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "3fc58a97f6b5c1684d04182538e6cc4a"
+ },
+ {
+ "dataPath": "params_shard_186.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.45.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.45.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.45.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.46.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.46.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.46.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "e8e12302324a85c6cbb293998057080c"
+ },
+ {
+ "dataPath": "params_shard_187.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.46.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "34cfd38623478dfcc1c6094e1fb859d2"
+ },
+ {
+ "dataPath": "params_shard_188.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.46.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "62e122e98cd6bfdc8885ff6bddff1b0d"
+ },
+ {
+ "dataPath": "params_shard_189.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.46.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.46.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.46.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "edb68a54c9a80e48400abfdd44a3b901"
+ },
+ {
+ "dataPath": "params_shard_190.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.46.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.46.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.46.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.47.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.47.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.47.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "7be5bff882acdfe8c31bfea11c85b728"
+ },
+ {
+ "dataPath": "params_shard_191.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.47.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "e7a561097d43b054dd924aecbb7e343e"
+ },
+ {
+ "dataPath": "params_shard_192.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.47.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "210a9080788a15dd27871702d584d9ae"
+ },
+ {
+ "dataPath": "params_shard_193.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.47.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.47.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.47.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "bf2e6a4447b8ec22d517bc6a2c98935e"
+ },
+ {
+ "dataPath": "params_shard_194.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.47.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.47.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.47.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.48.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.48.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.48.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "91e87c91000cb343cf97335234778e89"
+ },
+ {
+ "dataPath": "params_shard_195.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.48.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "47ff16ca99b30631b19038815b30df1a"
+ },
+ {
+ "dataPath": "params_shard_196.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.48.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "38a9f63418bf283f40bc53cf7f52c677"
+ },
+ {
+ "dataPath": "params_shard_197.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.48.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.48.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.48.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "2bf46302659f98a9c4e73603b0d6cb3c"
+ },
+ {
+ "dataPath": "params_shard_198.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.48.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.48.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.48.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.49.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.49.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.49.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "e487cb58f97f0a467e6eb97524a28330"
+ },
+ {
+ "dataPath": "params_shard_199.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.49.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "af3633b85dc2252e33357ee3a142afc0"
+ },
+ {
+ "dataPath": "params_shard_200.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.49.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "c323236c7d5ad90d938ec35d7380fb05"
+ },
+ {
+ "dataPath": "params_shard_201.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.49.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.49.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.49.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "409f66d2c1eeb2b949360d040778e702"
+ },
+ {
+ "dataPath": "params_shard_202.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.49.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.49.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.49.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.50.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.50.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.50.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "fc1311fadb535c9c3fedca2a6890738a"
+ },
+ {
+ "dataPath": "params_shard_203.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.50.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "eac2ed57c9f5358dcc0d21b1c9efd8ce"
+ },
+ {
+ "dataPath": "params_shard_204.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.50.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "29b3edf73bc7cc03db7d2dc8ea51dba4"
+ },
+ {
+ "dataPath": "params_shard_205.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.50.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.50.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.50.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "da791060584b4716257f7375f4590ade"
+ },
+ {
+ "dataPath": "params_shard_206.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.50.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.50.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.50.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.51.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.51.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.51.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "3a4071691b01dbd696bd14ef8238c705"
+ },
+ {
+ "dataPath": "params_shard_207.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.51.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "68f5c10d8b1c5957fd340a285f48596a"
+ },
+ {
+ "dataPath": "params_shard_208.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.51.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "cdacb7674985f29c7ca6531013533397"
+ },
+ {
+ "dataPath": "params_shard_209.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.51.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.51.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.51.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "d7551478b67f2887da11d67e1b20458f"
+ },
+ {
+ "dataPath": "params_shard_210.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.51.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.51.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.51.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.52.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.52.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.52.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "54f7bc560548972b35f9dde8dd422cbb"
+ },
+ {
+ "dataPath": "params_shard_211.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.52.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "ae9ea3d6e6c71851067d17709d1bae70"
+ },
+ {
+ "dataPath": "params_shard_212.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.52.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "f55b48e6466d6c36d75c6131a081d90b"
+ },
+ {
+ "dataPath": "params_shard_213.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.52.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.52.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.52.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "cc538747c1184efbee56864cadc86e89"
+ },
+ {
+ "dataPath": "params_shard_214.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.52.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.52.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.52.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.53.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.53.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.53.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "c4eda8ac90b7eb8d82ba1102f7b60d4b"
+ },
+ {
+ "dataPath": "params_shard_215.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.53.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "86692eabd67ea856a536849544c63548"
+ },
+ {
+ "dataPath": "params_shard_216.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.53.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "34f7c76b2b978a3aef45b9002e859811"
+ },
+ {
+ "dataPath": "params_shard_217.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.53.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.53.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.53.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "44af0c7745184eee20b6ed83bb5b8a07"
+ },
+ {
+ "dataPath": "params_shard_218.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.53.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.53.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.53.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.54.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.54.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.54.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "af57982b4f1688b3ade911288382fdc1"
+ },
+ {
+ "dataPath": "params_shard_219.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.54.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "3b8f14132a2e28a95810e0afcdc3abc7"
+ },
+ {
+ "dataPath": "params_shard_220.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.54.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "24c2c4fab7e84045e0e74d5a3b417424"
+ },
+ {
+ "dataPath": "params_shard_221.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.54.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.54.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.54.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "95098a6acf673ecc3aeec1caa4cae215"
+ },
+ {
+ "dataPath": "params_shard_222.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.54.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.54.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.54.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.55.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.55.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.55.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "30fcd62f7301c9e64511e835dc76244c"
+ },
+ {
+ "dataPath": "params_shard_223.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.55.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "f57b06c96b3972c5c856d7749bc7dcc7"
+ },
+ {
+ "dataPath": "params_shard_224.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.55.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "16a9a10c4a39e534f43fbf65eb85a630"
+ },
+ {
+ "dataPath": "params_shard_225.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.55.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.55.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.55.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "544d25b93d84f058f17c7ce4f2ef7800"
+ },
+ {
+ "dataPath": "params_shard_226.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.55.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.55.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.55.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.56.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.56.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.56.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "2d98ff2a2723ad0bfbe072ae977f904d"
+ },
+ {
+ "dataPath": "params_shard_227.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.56.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "945b5232a36c056e0db5f14fb594f440"
+ },
+ {
+ "dataPath": "params_shard_228.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.56.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "f9889a8f3f5efa3134a4ea619e6685f0"
+ },
+ {
+ "dataPath": "params_shard_229.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.56.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.56.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.56.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "549eaaea20964eff92cf341f352cdadc"
+ },
+ {
+ "dataPath": "params_shard_230.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.56.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.56.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.56.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.57.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.57.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.57.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "3d18a3f5b7e0b20cfa76eb0324876a92"
+ },
+ {
+ "dataPath": "params_shard_231.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.57.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "269eb10ca8b5772ce5968d5ed029581a"
+ },
+ {
+ "dataPath": "params_shard_232.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.57.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "e2e52dca6d1ad243420fe6a6d8699674"
+ },
+ {
+ "dataPath": "params_shard_233.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.57.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.57.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.57.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "323ac3fcc94fc1934281230094c03901"
+ },
+ {
+ "dataPath": "params_shard_234.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.57.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.57.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.57.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.58.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.58.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.58.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "2f5cfeb4aabde62f0e4b53f731c8791c"
+ },
+ {
+ "dataPath": "params_shard_235.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.58.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "4168839b89b60ab8c8ad6c3d346ccc19"
+ },
+ {
+ "dataPath": "params_shard_236.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.58.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "e821edec5a7a89a983d06f63f32bc728"
+ },
+ {
+ "dataPath": "params_shard_237.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.58.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.58.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.58.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "cc15b783ccafe63a3228ae0602699852"
+ },
+ {
+ "dataPath": "params_shard_238.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.58.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.58.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.58.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.59.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.59.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.59.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "85a4c7747da90ca4a44916239bbf8434"
+ },
+ {
+ "dataPath": "params_shard_239.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.59.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "dda52034a4ea687ec109ae909734ca2d"
+ },
+ {
+ "dataPath": "params_shard_240.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.59.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "21ed06aed4398c4f1c92eadbf896e416"
+ },
+ {
+ "dataPath": "params_shard_241.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.59.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.59.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.59.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "4b444b1fbcd358fc60acdc117674cfc9"
+ },
+ {
+ "dataPath": "params_shard_242.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.59.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.59.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.59.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.60.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.60.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.60.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "fcefca8c351dfad6e373916cb69216b8"
+ },
+ {
+ "dataPath": "params_shard_243.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.60.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "00a0751370f3a8ce196ff1082b052455"
+ },
+ {
+ "dataPath": "params_shard_244.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.60.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "659600488165359cbdf8c3d1609ca439"
+ },
+ {
+ "dataPath": "params_shard_245.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.60.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.60.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.60.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "10a2ce38adf3324cf4bf46db38cee732"
+ },
+ {
+ "dataPath": "params_shard_246.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.60.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.60.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.60.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.61.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.61.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.61.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "3499d5386f61358d3bc4a6e2721f7c7f"
+ },
+ {
+ "dataPath": "params_shard_247.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.61.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "746fb385b3863da326ff76b8c23f44ee"
+ },
+ {
+ "dataPath": "params_shard_248.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.61.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "10b7036f961653e8110430c4e781fb72"
+ },
+ {
+ "dataPath": "params_shard_249.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.61.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.61.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.61.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "5636ed4aa6a3d2f59940f33911258b43"
+ },
+ {
+ "dataPath": "params_shard_250.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.61.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.61.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.61.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.62.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.62.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.62.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "58c577d390e62c3fd306fdfc8efa2b1b"
+ },
+ {
+ "dataPath": "params_shard_251.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.62.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "d9237342ed10fb225dea406295cd192d"
+ },
+ {
+ "dataPath": "params_shard_252.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.62.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "c251fec419e1720f311df06e60cf1877"
+ },
+ {
+ "dataPath": "params_shard_253.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.62.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.62.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.62.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "9f4bf2c1fcdf7514c83293bc9e1a6c1f"
+ },
+ {
+ "dataPath": "params_shard_254.bin",
+ "format": "raw-shard",
+ "nbytes": 29526016,
+ "records": [
+ {
+ "name": "model.layers.62.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.62.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.62.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.layers.63.self_attn.c_attn.bias",
+ "shape": [
+ 7168
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 14336,
+ "byteOffset": 8867840
+ },
+ {
+ "name": "model.layers.63.self_attn.c_attn.q_weight",
+ "shape": [
+ 7168,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 18350080,
+ "byteOffset": 8882176
+ },
+ {
+ "name": "model.layers.63.self_attn.c_attn.q_scale",
+ "shape": [
+ 7168,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 2293760,
+ "byteOffset": 27232256
+ }
+ ],
+ "md5sum": "e516d3cb8ba315555ad5d2eb418e8f68"
+ },
+ {
+ "dataPath": "params_shard_255.bin",
+ "format": "raw-shard",
+ "nbytes": 141557760,
+ "records": [
+ {
+ "name": "model.layers.63.mlp.gate_up_proj.q_weight",
+ "shape": [
+ 55296,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 141557760,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "7a53f632cd0ab8b2ec1b0bb402683706"
+ },
+ {
+ "dataPath": "params_shard_256.bin",
+ "format": "raw-shard",
+ "nbytes": 70778880,
+ "records": [
+ {
+ "name": "model.layers.63.mlp.down_proj.q_weight",
+ "shape": [
+ 5120,
+ 3456
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 70778880,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "8f32df5c5ce254ff05013edd5a52fe5d"
+ },
+ {
+ "dataPath": "params_shard_257.bin",
+ "format": "raw-shard",
+ "nbytes": 32440320,
+ "records": [
+ {
+ "name": "model.layers.63.self_attn.o_proj.q_weight",
+ "shape": [
+ 5120,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 13107200,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.63.self_attn.o_proj.q_scale",
+ "shape": [
+ 5120,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 1638400,
+ "byteOffset": 13107200
+ },
+ {
+ "name": "model.layers.63.mlp.gate_up_proj.q_scale",
+ "shape": [
+ 55296,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 17694720,
+ "byteOffset": 14745600
+ }
+ ],
+ "md5sum": "9a2777c1a378b3f9fcd4a7594d72e8dc"
+ },
+ {
+ "dataPath": "params_shard_258.bin",
+ "format": "raw-shard",
+ "nbytes": 389283840,
+ "records": [
+ {
+ "name": "lm_head.q_weight",
+ "shape": [
+ 152064,
+ 640
+ ],
+ "dtype": "uint32",
+ "format": "f32-to-bf16",
+ "nbytes": 389283840,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "5621516379304600cc71159de28b8bc3"
+ },
+ {
+ "dataPath": "params_shard_259.bin",
+ "format": "raw-shard",
+ "nbytes": 48660480,
+ "records": [
+ {
+ "name": "lm_head.q_scale",
+ "shape": [
+ 152064,
+ 160
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 48660480,
+ "byteOffset": 0
+ }
+ ],
+ "md5sum": "d9ecc5cc7681d72b16e032a7b83849b2"
+ },
+ {
+ "dataPath": "params_shard_260.bin",
+ "format": "raw-shard",
+ "nbytes": 8878080,
+ "records": [
+ {
+ "name": "model.layers.63.mlp.down_proj.q_scale",
+ "shape": [
+ 5120,
+ 864
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 8847360,
+ "byteOffset": 0
+ },
+ {
+ "name": "model.layers.63.input_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8847360
+ },
+ {
+ "name": "model.layers.63.post_attention_layernorm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8857600
+ },
+ {
+ "name": "model.norm.weight",
+ "shape": [
+ 5120
+ ],
+ "dtype": "float32",
+ "format": "f32-to-bf16",
+ "nbytes": 10240,
+ "byteOffset": 8867840
+ }
+ ],
+ "md5sum": "05481db171508742fb07f2572d1a3e13"
+ }
+ ]
+}
\ No newline at end of file
diff --git a/params_shard_0.bin b/params_shard_0.bin
new file mode 100644
index 0000000000000000000000000000000000000000..9d5485dd5b82c99efe5fac4433da6fef95ed4a51
--- /dev/null
+++ b/params_shard_0.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8890bddb63179f3b8a81d2359ff1a3f0ca3d8cf78364f187733a6862f55089db
+size 389283840
diff --git a/params_shard_1.bin b/params_shard_1.bin
new file mode 100644
index 0000000000000000000000000000000000000000..9d1b03f91a9e9699a5ecb617b68b9572bc79bc16
--- /dev/null
+++ b/params_shard_1.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77f5af13a359edb7041f0b3bf6448abd31905111b8e59145561d3ad7ae208f69
+size 48660480
diff --git a/params_shard_10.bin b/params_shard_10.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b83e3828154b6a7eb2ce25acd9ad5645d7681a11
--- /dev/null
+++ b/params_shard_10.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d853a44177d18fa79c2761c1f7385359c9e2d8bf079c1f7588da70eaef8322b3
+size 29526016
diff --git a/params_shard_100.bin b/params_shard_100.bin
new file mode 100644
index 0000000000000000000000000000000000000000..80b713bf461ca2cbb773d03f7d9ef07fff840cf3
--- /dev/null
+++ b/params_shard_100.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb0b65984bbb3ce76bae90a07f64579df96cb446794713c4b07e1752a0697ce9
+size 70778880
diff --git a/params_shard_101.bin b/params_shard_101.bin
new file mode 100644
index 0000000000000000000000000000000000000000..2e72c1b3d14e16552a25ed39470d764162ccc75c
--- /dev/null
+++ b/params_shard_101.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fff42a72fa1f9e7cdd23d67ca87838c09d12423c6161af86db99119536071321
+size 32440320
diff --git a/params_shard_102.bin b/params_shard_102.bin
new file mode 100644
index 0000000000000000000000000000000000000000..9b914a9a0883139823ef89ff07cc09acb373f0b0
--- /dev/null
+++ b/params_shard_102.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d90f1bb201f1fdcedeb34c9094d698adfa5aa7bb2901df150f51556d1dcb537c
+size 29526016
diff --git a/params_shard_103.bin b/params_shard_103.bin
new file mode 100644
index 0000000000000000000000000000000000000000..66955bfcef0bbe0b375d5bde6d86dce37e8e11df
--- /dev/null
+++ b/params_shard_103.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0949f479fa46923d0ef6167f6b8e13d7035dbdbb85b8b81dcac790a085ae05df
+size 141557760
diff --git a/params_shard_104.bin b/params_shard_104.bin
new file mode 100644
index 0000000000000000000000000000000000000000..eee10f7443819913fcece1380b5df4fbcabfbc01
--- /dev/null
+++ b/params_shard_104.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d9d441a0e1fc9958dc3bca17571b7efc6db9998c315a5a2088d80022432bf79
+size 70778880
diff --git a/params_shard_105.bin b/params_shard_105.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c7d99679043959e5ac391344fdb577d6ef170abc
--- /dev/null
+++ b/params_shard_105.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45e17dc18ac1c0da2a8a0e1fd81edd486719e86dfeb20be034091bf5deaa3c10
+size 32440320
diff --git a/params_shard_106.bin b/params_shard_106.bin
new file mode 100644
index 0000000000000000000000000000000000000000..7dee110311009dbf7f792362dff631285eb15f04
--- /dev/null
+++ b/params_shard_106.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e7b1f2a97a2ac7c287be43e2603a41c670739a6bc25ebfa9b38ea7b16fabe4f
+size 29526016
diff --git a/params_shard_107.bin b/params_shard_107.bin
new file mode 100644
index 0000000000000000000000000000000000000000..a66629a73a08ce5555b6b59e26be64fedb1001c2
--- /dev/null
+++ b/params_shard_107.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af3e5f0ff419f05425c9745474786a948744a9847f0a5008329e6a857aacc431
+size 141557760
diff --git a/params_shard_108.bin b/params_shard_108.bin
new file mode 100644
index 0000000000000000000000000000000000000000..1ccec45bcaea8ba64932b7f72a3b056b207e4f88
--- /dev/null
+++ b/params_shard_108.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f05689c9d98e99ecdcb853bef32576bd9add2505d042946789baa712523b69f5
+size 70778880
diff --git a/params_shard_109.bin b/params_shard_109.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d678dfd8c5df91cf35be31e68202624b7034783c
--- /dev/null
+++ b/params_shard_109.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee301ed81d57143b6e8eab52fbc20a908db6006f1fcb500e221d962387d0f895
+size 32440320
diff --git a/params_shard_11.bin b/params_shard_11.bin
new file mode 100644
index 0000000000000000000000000000000000000000..84faa8453112ad88801935087cf72954ca7bd50f
--- /dev/null
+++ b/params_shard_11.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bff955505a869752fa31f49d15e8254be930cedd42cb85021532bf4e6a5e6a8b
+size 141557760
diff --git a/params_shard_110.bin b/params_shard_110.bin
new file mode 100644
index 0000000000000000000000000000000000000000..472d10492d85dbf2b3a35ddd437dac8a5546bc4b
--- /dev/null
+++ b/params_shard_110.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:184eaaf2df59c6173d143fee912836aaac262a6998f3babc1486a58c91288332
+size 29526016
diff --git a/params_shard_111.bin b/params_shard_111.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c93131f0e9534cd0ec47f0901b41a1b7f1aa69d0
--- /dev/null
+++ b/params_shard_111.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68d971ad94463dc28bd6173815069c24bb73d52769a63ad5ae4c03bc7090bb9b
+size 141557760
diff --git a/params_shard_112.bin b/params_shard_112.bin
new file mode 100644
index 0000000000000000000000000000000000000000..49d0d78d1962c506f0fd2dbcf4125e0212663028
--- /dev/null
+++ b/params_shard_112.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01daa226fac8f6d7a63952e2d06cae5fd4e2be5ecfe6354543aea55850baf63a
+size 70778880
diff --git a/params_shard_113.bin b/params_shard_113.bin
new file mode 100644
index 0000000000000000000000000000000000000000..7d3e145fd641b9ce54ea391558201335ce05b987
--- /dev/null
+++ b/params_shard_113.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c2143bacc56ebe9fcfcf7ae840134a7f260aed74f2a3443110c1dd97a0268e2
+size 32440320
diff --git a/params_shard_114.bin b/params_shard_114.bin
new file mode 100644
index 0000000000000000000000000000000000000000..03d3beea5260f2b74cecb8b4f628776916656920
--- /dev/null
+++ b/params_shard_114.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5305384520eb4264f4fb8ae63291904f03985ce64c3a5fec2674585a9525e96
+size 29526016
diff --git a/params_shard_115.bin b/params_shard_115.bin
new file mode 100644
index 0000000000000000000000000000000000000000..8fc46868b6c45be4655887b27121b3c7336f55de
--- /dev/null
+++ b/params_shard_115.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a52822596f9f6f8243b311aa39387cb88e3adf9009dc6adcdc838cb94d39f57
+size 141557760
diff --git a/params_shard_116.bin b/params_shard_116.bin
new file mode 100644
index 0000000000000000000000000000000000000000..25f5ca495aedbd09f091dcafc55b6cfdf65c6fd7
--- /dev/null
+++ b/params_shard_116.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92295349d2d73e4e447db0320ca65aacd1dc1fd8afd0da6b49b4892f3a2d015e
+size 70778880
diff --git a/params_shard_117.bin b/params_shard_117.bin
new file mode 100644
index 0000000000000000000000000000000000000000..cfa8519d01a960f250a7dbed9a7ec27de30f2f1c
--- /dev/null
+++ b/params_shard_117.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3293e7c8ce03e6f985666a051e938e22fa91dcaf95bb11c3f13d78fccf83afc8
+size 32440320
diff --git a/params_shard_118.bin b/params_shard_118.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e8711a42e0ac008edb2a5187b1dd23725e2cf7c3
--- /dev/null
+++ b/params_shard_118.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61f81b34020e247d41edc61c1ef2dcdf8daf7461270f148fe9155762733ce465
+size 29526016
diff --git a/params_shard_119.bin b/params_shard_119.bin
new file mode 100644
index 0000000000000000000000000000000000000000..705518fb245d6518da3ba6bc379be75dee10bb35
--- /dev/null
+++ b/params_shard_119.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98d0ba209f8527727f94fd84324543e1da59ea013b8017a4c8d91253fc119074
+size 141557760
diff --git a/params_shard_12.bin b/params_shard_12.bin
new file mode 100644
index 0000000000000000000000000000000000000000..1e59980285e0453a68f0acef7142996cc662c03f
--- /dev/null
+++ b/params_shard_12.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee479a3bb68d8dd2e730e111fd7927d31a525521950cbce7f1b00dbed59498ba
+size 70778880
diff --git a/params_shard_120.bin b/params_shard_120.bin
new file mode 100644
index 0000000000000000000000000000000000000000..86bbbb7b8ecdfcd740e91bf219439096aad60473
--- /dev/null
+++ b/params_shard_120.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23d1faf54f9a3d171a9c61f0595dda6c05c524e529079e33fa535eb282733f21
+size 70778880
diff --git a/params_shard_121.bin b/params_shard_121.bin
new file mode 100644
index 0000000000000000000000000000000000000000..801f6f09baa375516b8f65f9adafcc51700f971a
--- /dev/null
+++ b/params_shard_121.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52cea6e8627ffc0c610cef600b111cabdf77164235e69f43be08aaf77073ceaa
+size 32440320
diff --git a/params_shard_122.bin b/params_shard_122.bin
new file mode 100644
index 0000000000000000000000000000000000000000..980d3815126c7d3d514746ce053e52b1ed66dcaf
--- /dev/null
+++ b/params_shard_122.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91ffa1cdb5843ead2af5c4daf4a3c8a6a5a4a969aeefe4f2c706e6d333f7308e
+size 29526016
diff --git a/params_shard_123.bin b/params_shard_123.bin
new file mode 100644
index 0000000000000000000000000000000000000000..9555926aea832b8b998b7820905e3efa2dd10339
--- /dev/null
+++ b/params_shard_123.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:608d1a09ae4018c0056cb1da145a2748b812410e1c94e05e876ca0af251e2987
+size 141557760
diff --git a/params_shard_124.bin b/params_shard_124.bin
new file mode 100644
index 0000000000000000000000000000000000000000..2b8b7ed685602eab9aa90dd7e79d4727350e05da
--- /dev/null
+++ b/params_shard_124.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9415caf1f15b1e41eaacc32785c01899211241d479a8a7c9ebb245ba2a8b8606
+size 70778880
diff --git a/params_shard_125.bin b/params_shard_125.bin
new file mode 100644
index 0000000000000000000000000000000000000000..2852a1e029deae2ab9b8cbe4e0d451b65ddcc7c3
--- /dev/null
+++ b/params_shard_125.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fab03a2bf9135317b50c6a75c336c210e7e0ecde5e448b4d90c18f119d7ddaa4
+size 32440320
diff --git a/params_shard_126.bin b/params_shard_126.bin
new file mode 100644
index 0000000000000000000000000000000000000000..acb093617f68903278fb9b81930ff60b59424bb2
--- /dev/null
+++ b/params_shard_126.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:181ac695f6a0ae656599ab0c29e8937afb115c70aca3ced1a1607100a3919167
+size 29526016
diff --git a/params_shard_127.bin b/params_shard_127.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e6bc73517fbeee771e6720b9c538d9d7c7c8eb28
--- /dev/null
+++ b/params_shard_127.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48a4b5e70275f59d8ef972da10f9695a4cacb5a440cc66da598eb77ab0aa3f9a
+size 141557760
diff --git a/params_shard_128.bin b/params_shard_128.bin
new file mode 100644
index 0000000000000000000000000000000000000000..43fae404c72707aac863987ec35b1035ece99a61
--- /dev/null
+++ b/params_shard_128.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a6a95e3173a5ddbb0aab36e1a5b7f632c8a6350f6a5cd92ce0e712abe55715a
+size 70778880
diff --git a/params_shard_129.bin b/params_shard_129.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e81aa5994bca28a347c8ce318c5ea947c9e483c9
--- /dev/null
+++ b/params_shard_129.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75b8694a82957fd100ebf201df899001c70f2a8b0c394428114f7d40e743e87b
+size 32440320
diff --git a/params_shard_13.bin b/params_shard_13.bin
new file mode 100644
index 0000000000000000000000000000000000000000..73c4eb942abf406708a3b7360b29dc22f1e31352
--- /dev/null
+++ b/params_shard_13.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81a3cbbbfe3833d819fcf8f389e2bf46cab78fa2ead8334add71e4c099e4710d
+size 32440320
diff --git a/params_shard_130.bin b/params_shard_130.bin
new file mode 100644
index 0000000000000000000000000000000000000000..13320ab31f58436f3e4c63ca7f7622c53968c64b
--- /dev/null
+++ b/params_shard_130.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43cb7df756294388520b53281298ed4ce116001bde19541ff8929caaaa441020
+size 29526016
diff --git a/params_shard_131.bin b/params_shard_131.bin
new file mode 100644
index 0000000000000000000000000000000000000000..3768871a84f9d12ae95d3aebb949ee4cfeb0c2dd
--- /dev/null
+++ b/params_shard_131.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b55137f0f18551a834b85e23dcd64d354a9e7a88357825da6d8011453f183df
+size 141557760
diff --git a/params_shard_132.bin b/params_shard_132.bin
new file mode 100644
index 0000000000000000000000000000000000000000..2fb72156636dc182a15595ca655b0f9f1be8dcf0
--- /dev/null
+++ b/params_shard_132.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bb3fdc24879f8c48e43a622abd40ea9ae2c1f00b33bce83cd5e144c0d21317c
+size 70778880
diff --git a/params_shard_133.bin b/params_shard_133.bin
new file mode 100644
index 0000000000000000000000000000000000000000..85f09fa506dbe2d40bc9e09f22014bccc6bd8580
--- /dev/null
+++ b/params_shard_133.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:060c9f1f107c498d759b0112f90d59c26e64a07c060e5bb208f4128bd1e9adac
+size 32440320
diff --git a/params_shard_134.bin b/params_shard_134.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e32804cbf88cc35c3903debea9f1acd59b601688
--- /dev/null
+++ b/params_shard_134.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b03fec197d01954f8ad6f0d2dcbf7a2fa23b471283bd7d3b64fe6cddccf6e0c
+size 29526016
diff --git a/params_shard_135.bin b/params_shard_135.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e443515576db39e3e7aeaa3002f286d88539b239
--- /dev/null
+++ b/params_shard_135.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48ee5bbef047f97d3104a48d42e6052123e2404bc34327a3aa4332725c7e8e8e
+size 141557760
diff --git a/params_shard_136.bin b/params_shard_136.bin
new file mode 100644
index 0000000000000000000000000000000000000000..2e91edd1dd9e98b6919476bb8085a95f7ea930cd
--- /dev/null
+++ b/params_shard_136.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41a2494cc064ab59dd6f9737a60d1f4947a7f6ff0f0eac142d8994ee7487dcec
+size 70778880
diff --git a/params_shard_137.bin b/params_shard_137.bin
new file mode 100644
index 0000000000000000000000000000000000000000..59422b829c4b08a8825b182ff64944c737b1602a
--- /dev/null
+++ b/params_shard_137.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02777507f440dfb4398f138a3744ff7e7b43817439a23d158caf70bf8b211dd4
+size 32440320
diff --git a/params_shard_138.bin b/params_shard_138.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c4c191b574512451cc1f5539d19c164a1395e817
--- /dev/null
+++ b/params_shard_138.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bc3087ac8baba6bad94ed82e091b4d8d7608d18f69c616955dc1e8b68d19cb1
+size 29526016
diff --git a/params_shard_139.bin b/params_shard_139.bin
new file mode 100644
index 0000000000000000000000000000000000000000..03c451ff5180ec1431c3cedf86369b092d665368
--- /dev/null
+++ b/params_shard_139.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29001e7656e56f34ab80b5880f2223f11ccc0d2c61295beab3e13f466a66c582
+size 141557760
diff --git a/params_shard_14.bin b/params_shard_14.bin
new file mode 100644
index 0000000000000000000000000000000000000000..42ebfcfe285dfe9ff67e2f4ff82588876a0f43f6
--- /dev/null
+++ b/params_shard_14.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0c3e8164cb1c4525c277c6e9ef432944c0a644cb6315d219bdb3a48fd7552b2
+size 29526016
diff --git a/params_shard_140.bin b/params_shard_140.bin
new file mode 100644
index 0000000000000000000000000000000000000000..47e6dfa25ba949c8f35e6e252c88e5e4bfdba1cb
--- /dev/null
+++ b/params_shard_140.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a7adcf2f7aef770f353374199d10c340d8801c657226ea2b5827e7107e7bcaf
+size 70778880
diff --git a/params_shard_141.bin b/params_shard_141.bin
new file mode 100644
index 0000000000000000000000000000000000000000..7ef3d8cda9f6aa39873574b2755539f16612a65c
--- /dev/null
+++ b/params_shard_141.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a40699e3184b0effd7cb2a89012761e62915da9db37400656781b0b0331def2f
+size 32440320
diff --git a/params_shard_142.bin b/params_shard_142.bin
new file mode 100644
index 0000000000000000000000000000000000000000..2e768a9bfc57da7db8c46c82001b19319e3e4c5e
--- /dev/null
+++ b/params_shard_142.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4639f11d2bf346aee51bb2441a6dbf75d4680fedfc738dc7cbc2e9401cc6b49
+size 29526016
diff --git a/params_shard_143.bin b/params_shard_143.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b93f0f3ce5e59a3e62291ee352263a672eeb3fa0
--- /dev/null
+++ b/params_shard_143.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e4222b7e43d200c8e869eed8ab34322796ff96ab6d1797c079fd9950c3eff75
+size 141557760
diff --git a/params_shard_144.bin b/params_shard_144.bin
new file mode 100644
index 0000000000000000000000000000000000000000..8d1a39abdbea9a0958645986bbe00e3b8b703e55
--- /dev/null
+++ b/params_shard_144.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc89ccaa656aab530998fcd4c142748a62210ec9b511903486473fc5a6a3b774
+size 70778880
diff --git a/params_shard_145.bin b/params_shard_145.bin
new file mode 100644
index 0000000000000000000000000000000000000000..6d02b41406046739634a4b8cd18bd11bbdea8bff
--- /dev/null
+++ b/params_shard_145.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eca6ecc50b7ef9d4e7f815834e97b6e61a7c0327dca1fa5f81e79298c40f822f
+size 32440320
diff --git a/params_shard_146.bin b/params_shard_146.bin
new file mode 100644
index 0000000000000000000000000000000000000000..ba5fbb2cab91a6b5d02691c2d2259ad149d8080f
--- /dev/null
+++ b/params_shard_146.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ebc330d6514537b68cd804b223a5d90ca62cc75462df736594f5eb181821d62
+size 29526016
diff --git a/params_shard_147.bin b/params_shard_147.bin
new file mode 100644
index 0000000000000000000000000000000000000000..318b4d12eb4150afcec8a5b1119b6315e0c01885
--- /dev/null
+++ b/params_shard_147.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48d73295efadd9ddc142d4418f7dfd043872eb7871dd9008f7a1fc43943dd2aa
+size 141557760
diff --git a/params_shard_148.bin b/params_shard_148.bin
new file mode 100644
index 0000000000000000000000000000000000000000..98b84612eca3873998af23546166f645568cbd5b
--- /dev/null
+++ b/params_shard_148.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a9e7c5657a3d8f5eba25a561e05b0782ad905b75a4b5702fe3e7937b9b3c6c4
+size 70778880
diff --git a/params_shard_149.bin b/params_shard_149.bin
new file mode 100644
index 0000000000000000000000000000000000000000..f46826df6b7c524432481c087998d7c3a3dcca83
--- /dev/null
+++ b/params_shard_149.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6d739f302b367ae54249bca3b135b4c7366637cb32eaa1d2750256e353b091b
+size 32440320
diff --git a/params_shard_15.bin b/params_shard_15.bin
new file mode 100644
index 0000000000000000000000000000000000000000..7b31cf7d5c4d0b768f57850b0cde331ae010db34
--- /dev/null
+++ b/params_shard_15.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0299061ecbf8a995068aecaf35cde648fc2046b60c3e6f85b8e80ffbbb33b699
+size 141557760
diff --git a/params_shard_150.bin b/params_shard_150.bin
new file mode 100644
index 0000000000000000000000000000000000000000..534ecb9f911f11c7ca2c3f8753b6d4465a7d37a3
--- /dev/null
+++ b/params_shard_150.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:058dc63768c7990ca2d31c375f3a3be505a2df0db092f0388a7c98f9a402d6e7
+size 29526016
diff --git a/params_shard_151.bin b/params_shard_151.bin
new file mode 100644
index 0000000000000000000000000000000000000000..5b783e7de545205bbc05e6bdcb8a87864f87ab9d
--- /dev/null
+++ b/params_shard_151.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea40b1945005518ef4fe6ba57eea33c212692dc2ff1cc8cc9e070f86f1a2429c
+size 141557760
diff --git a/params_shard_152.bin b/params_shard_152.bin
new file mode 100644
index 0000000000000000000000000000000000000000..886940a43a82301db7dd9b46bd04d7d5d23812a2
--- /dev/null
+++ b/params_shard_152.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c19f19d565c43fbb81daaab89bf4e746d4ca82f0ca7055ee3ec9ec5dedc5c36
+size 70778880
diff --git a/params_shard_153.bin b/params_shard_153.bin
new file mode 100644
index 0000000000000000000000000000000000000000..99a1a6c83f3510ab51d2b224ea1a14e7eff60db2
--- /dev/null
+++ b/params_shard_153.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47b29925f9ea026f9def0e391b0bd744299487b7e13cea472406122045e15654
+size 32440320
diff --git a/params_shard_154.bin b/params_shard_154.bin
new file mode 100644
index 0000000000000000000000000000000000000000..9989af883f44115637eab91b30c9d18fa118832b
--- /dev/null
+++ b/params_shard_154.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7892dc1c944bcdf4c249ec64bd0b94e47bf0aca9b934c54d4cd36e693f6dff47
+size 29526016
diff --git a/params_shard_155.bin b/params_shard_155.bin
new file mode 100644
index 0000000000000000000000000000000000000000..95ac5ec3aece5f22897fa89ab3c36a1e23c8a80b
--- /dev/null
+++ b/params_shard_155.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b7a4385d2e49ba3c3a90e5284715ca00907e6ec45191b3052f196f337946ae4
+size 141557760
diff --git a/params_shard_156.bin b/params_shard_156.bin
new file mode 100644
index 0000000000000000000000000000000000000000..871cd3f0848ecf3cb587263fef460b44fd729941
--- /dev/null
+++ b/params_shard_156.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87327f7851395480229ad15150a28bb0c224e105e14e0b6b3a869bd1779bcaf7
+size 70778880
diff --git a/params_shard_157.bin b/params_shard_157.bin
new file mode 100644
index 0000000000000000000000000000000000000000..edfa320e81310a7ecca3194493c7cdeea9bf1aed
--- /dev/null
+++ b/params_shard_157.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9f52e5db1d22342d2784ddf28ff0f0c79aab6596f39621ac4714b4724de9819
+size 32440320
diff --git a/params_shard_158.bin b/params_shard_158.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4cbca62af08d5710a03f5b916cd3bf4695598198
--- /dev/null
+++ b/params_shard_158.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0e252b5313be7d24ca32c034203ce95f9999710b7cedef8d78f49b95bb4dd51
+size 29526016
diff --git a/params_shard_159.bin b/params_shard_159.bin
new file mode 100644
index 0000000000000000000000000000000000000000..7e0dee6d71916229bfd35cfceb28d512718f78e4
--- /dev/null
+++ b/params_shard_159.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cff8ab00ec974e0c84ff6eb313105f07c9b2b75b916a9758071856b090f23342
+size 141557760
diff --git a/params_shard_16.bin b/params_shard_16.bin
new file mode 100644
index 0000000000000000000000000000000000000000..aa29cb8ffefc828c62a5b347a62002d3abd944c7
--- /dev/null
+++ b/params_shard_16.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:481fee7151bbeecd64055b28062998279092c8d4eb0405338b6790c434e6aa0b
+size 70778880
diff --git a/params_shard_160.bin b/params_shard_160.bin
new file mode 100644
index 0000000000000000000000000000000000000000..407a6c1acb5d23ef548aa8493e891ac75cb3e647
--- /dev/null
+++ b/params_shard_160.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68c5afb06eedea50935809fa0f13008859aa3a726dd179142fa0eaef6ab41127
+size 70778880
diff --git a/params_shard_161.bin b/params_shard_161.bin
new file mode 100644
index 0000000000000000000000000000000000000000..8efc73e2c27342f41b3b2f621ad5355387f024aa
--- /dev/null
+++ b/params_shard_161.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5988f604e96c509501c2107a8dc8ed23b6a831cc60da34f22f83576a2c6c4aff
+size 32440320
diff --git a/params_shard_162.bin b/params_shard_162.bin
new file mode 100644
index 0000000000000000000000000000000000000000..54405c3baffd92ebcbc363f849a85d154ce6fe94
--- /dev/null
+++ b/params_shard_162.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae278f6c7731dce8b050a7ea24eccb30754684ec5a45af4add0afa1ee2b46082
+size 29526016
diff --git a/params_shard_163.bin b/params_shard_163.bin
new file mode 100644
index 0000000000000000000000000000000000000000..578618e25e72e767487e28fc6c265b3875972688
--- /dev/null
+++ b/params_shard_163.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e40a61d832b54ed1cc5efb549885e778bb3a00d01488608b4cda7c0471c1dab
+size 141557760
diff --git a/params_shard_164.bin b/params_shard_164.bin
new file mode 100644
index 0000000000000000000000000000000000000000..7bb8828034017fbc2640894709da943a115d3b55
--- /dev/null
+++ b/params_shard_164.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12e0eef112b0dcb37186859ac30c1aea1204a0c8e29654779f6191d6c79629e6
+size 70778880
diff --git a/params_shard_165.bin b/params_shard_165.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c24099a00f599339c3277ef1bae1c494706777e2
--- /dev/null
+++ b/params_shard_165.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:145c1a5e255df6ec79e902d1a1cf8269d28326256a977ab647b1ffe408c2a5e9
+size 32440320
diff --git a/params_shard_166.bin b/params_shard_166.bin
new file mode 100644
index 0000000000000000000000000000000000000000..31d3cf4fe05634d301c93333547199656d9d79fc
--- /dev/null
+++ b/params_shard_166.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfe841a3bc344b4c3088229e23726f6951dadc83242d62aecf6d9dd1b37f0c2a
+size 29526016
diff --git a/params_shard_167.bin b/params_shard_167.bin
new file mode 100644
index 0000000000000000000000000000000000000000..856d9ee6917ed39f7a19dac770303c3998bb1f13
--- /dev/null
+++ b/params_shard_167.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1e7c264b0e577a311de05a2fb3213c423a8f12f44f1bb0d01242688f5b3f154
+size 141557760
diff --git a/params_shard_168.bin b/params_shard_168.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c7b7b9c3deb325c67b5f71e51c0e8e0971e94776
--- /dev/null
+++ b/params_shard_168.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35a9660cade3eec8ef21db4d8a5460ae6a79be9631dd6418becceb6c3ea67e8b
+size 70778880
diff --git a/params_shard_169.bin b/params_shard_169.bin
new file mode 100644
index 0000000000000000000000000000000000000000..204fc478a4cb5c31904879332342be85447b0735
--- /dev/null
+++ b/params_shard_169.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d20267e5b24ba32b2087552bbaa86b181a5f6b748653f6f1f8131da33aa654a5
+size 32440320
diff --git a/params_shard_17.bin b/params_shard_17.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4d8abb2c2902021bfd7f91e4cffe1a39dd64e9be
--- /dev/null
+++ b/params_shard_17.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:284cbe53490798468546eb71b338f4968d23afa0b0f118c68f4369731bb88fb6
+size 32440320
diff --git a/params_shard_170.bin b/params_shard_170.bin
new file mode 100644
index 0000000000000000000000000000000000000000..1211f8d565ebbdb135490d7acbe59ea93d424fcf
--- /dev/null
+++ b/params_shard_170.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ce72179fa85c74030674b6641f94e728d51f4b4af9ab1d71645aff2e36e2c4a
+size 29526016
diff --git a/params_shard_171.bin b/params_shard_171.bin
new file mode 100644
index 0000000000000000000000000000000000000000..7fde12daffd220c66905b3ed2f3704dde0428b10
--- /dev/null
+++ b/params_shard_171.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83685acb5653c3248b40c585e4b2d21eed0e26c7d4aeb9b5b1f2bc26b6f704e5
+size 141557760
diff --git a/params_shard_172.bin b/params_shard_172.bin
new file mode 100644
index 0000000000000000000000000000000000000000..440f070076e1a33ddac1f649333507e7dbf0826a
--- /dev/null
+++ b/params_shard_172.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8506e24802c06f17d8c652c2ec4f4102268ef5c66b140e74c0d8f1ed5818ad3
+size 70778880
diff --git a/params_shard_173.bin b/params_shard_173.bin
new file mode 100644
index 0000000000000000000000000000000000000000..a6103b4772679c257a4681e63c78588d87264839
--- /dev/null
+++ b/params_shard_173.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79adf95619928ad262194fe4a6d04be4072ac80e17929f06f3fb3e6132dad64b
+size 32440320
diff --git a/params_shard_174.bin b/params_shard_174.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4216032fca47366020d292e036f0ccbae68f938d
--- /dev/null
+++ b/params_shard_174.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fe72e4bb31f73d74a57bedd60246966e47728c240e1f1115759c58e858e93d2
+size 29526016
diff --git a/params_shard_175.bin b/params_shard_175.bin
new file mode 100644
index 0000000000000000000000000000000000000000..513eed91ef1edd0a4dd1b913dd2818a8c5fe3df5
--- /dev/null
+++ b/params_shard_175.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f4a6dc061426bd983014e6b2feec199384887d079c6e86345c84d0acdb90414
+size 141557760
diff --git a/params_shard_176.bin b/params_shard_176.bin
new file mode 100644
index 0000000000000000000000000000000000000000..3302224a5d1d65c32ecdd30a97cd62016be88e6a
--- /dev/null
+++ b/params_shard_176.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f805ee6b65d314782d158f0fa1ce20c9c3319ff6b717e5ddc31039a3057c5c4
+size 70778880
diff --git a/params_shard_177.bin b/params_shard_177.bin
new file mode 100644
index 0000000000000000000000000000000000000000..7da47ec6b4868872106b037a4c5bf95bedaa26dd
--- /dev/null
+++ b/params_shard_177.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dacb2a0b56c7cce7e073d699d20371b5eb848be4d5c0c61a690285245a977970
+size 32440320
diff --git a/params_shard_178.bin b/params_shard_178.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4bc32c1713914173d9f79e8992e5a29a2c63127a
--- /dev/null
+++ b/params_shard_178.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ebcc699bf4b7669cbfe8a022f3d6669801ecc0208c07cb86a1765f810b43740
+size 29526016
diff --git a/params_shard_179.bin b/params_shard_179.bin
new file mode 100644
index 0000000000000000000000000000000000000000..1b9ce96c7596d307c349900d184e031ef82c0861
--- /dev/null
+++ b/params_shard_179.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbc7f096f50cd430ef1ae7433f9ce5b1eb764e83aebcdb79aace676247fa0ae7
+size 141557760
diff --git a/params_shard_18.bin b/params_shard_18.bin
new file mode 100644
index 0000000000000000000000000000000000000000..03346e43eca48deaafca453247ca0e54b9b945f1
--- /dev/null
+++ b/params_shard_18.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6523569ef09661991a7df46e842a06011e6b90cb526313ca57d88d54a719dc8d
+size 29526016
diff --git a/params_shard_180.bin b/params_shard_180.bin
new file mode 100644
index 0000000000000000000000000000000000000000..49e9b31b733147c45c22b3740e0be0abbf3f5a70
--- /dev/null
+++ b/params_shard_180.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15cd6322371a7d53fa680a961cb5440754b4df9ecb9b89b26c1a727ccddbc241
+size 70778880
diff --git a/params_shard_181.bin b/params_shard_181.bin
new file mode 100644
index 0000000000000000000000000000000000000000..3ab8473b48d628f1d203f31a4a90e614574b07fa
--- /dev/null
+++ b/params_shard_181.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53df1e4fad0252b53ef4af224798fb5bf8f83c8c301c6bc1a696b679dea77784
+size 32440320
diff --git a/params_shard_182.bin b/params_shard_182.bin
new file mode 100644
index 0000000000000000000000000000000000000000..f385b708e4bb96f848510be1158bb2f92b25fc28
--- /dev/null
+++ b/params_shard_182.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f4a1e89a0a21284c3c78566d6fe30a4b3e82f43407d2810b83f4269ce0ff61b
+size 29526016
diff --git a/params_shard_183.bin b/params_shard_183.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b501281ae8ce2c80a3378374db1a802437c20b54
--- /dev/null
+++ b/params_shard_183.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e727a6db2eb844b5136c19e1bee44812a340f695179ca2262459e390726272e
+size 141557760
diff --git a/params_shard_184.bin b/params_shard_184.bin
new file mode 100644
index 0000000000000000000000000000000000000000..aa7647571dabc7ec76d1cb0b6ef4abcb94c41383
--- /dev/null
+++ b/params_shard_184.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f025a3a6a82f0bef4c86fd70cf89f1beed6a6bb6724315ccd5eaff19df7ebb4a
+size 70778880
diff --git a/params_shard_185.bin b/params_shard_185.bin
new file mode 100644
index 0000000000000000000000000000000000000000..223c66acea93012d61e672d1ae531287e3c22be2
--- /dev/null
+++ b/params_shard_185.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5d7fea4d0c14fe1d140fd7b97587e9738a3e6547f1799b1c6d386c8b7db010c
+size 32440320
diff --git a/params_shard_186.bin b/params_shard_186.bin
new file mode 100644
index 0000000000000000000000000000000000000000..8d933b64b4553ccdc66e9a716032f879e5ed75f7
--- /dev/null
+++ b/params_shard_186.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9fa2032e5ae0e0fa3312254a2ff132f941b409b523a1b60711c0d07d412ca2b
+size 29526016
diff --git a/params_shard_187.bin b/params_shard_187.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d9211b7e8c91b33f58117c97a38b381caad6059d
--- /dev/null
+++ b/params_shard_187.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:906b66bd46e4c09d9d83494b51fa49393b5fa9729f288ed849ad0770c199209c
+size 141557760
diff --git a/params_shard_188.bin b/params_shard_188.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4bd292116c3258fface70bdc2bd95f58059ef8d4
--- /dev/null
+++ b/params_shard_188.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d108c17719721f07e5fa008d7f65d1ea773e3901c14d0e1b0d98a535ac8fe921
+size 70778880
diff --git a/params_shard_189.bin b/params_shard_189.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c9f27278b98211cc25a5f1e2742241206cb5f163
--- /dev/null
+++ b/params_shard_189.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df1f06b751f68b2773345670b5383669a0bcd5bf4242be0983ef8388be3669a0
+size 32440320
diff --git a/params_shard_19.bin b/params_shard_19.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b01167523e851531c378b4e9200f46e82860b0b2
--- /dev/null
+++ b/params_shard_19.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fffe478813d212a8456bb6a3ab4a89bb108b5876e4fb368d767feecf67721fd
+size 141557760
diff --git a/params_shard_190.bin b/params_shard_190.bin
new file mode 100644
index 0000000000000000000000000000000000000000..af57214260ee8fb12a4dc87f5b97051eb3347403
--- /dev/null
+++ b/params_shard_190.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68ce27ad41f19b5ab3abefdef3bb5758cf48b4e74ee81598d919caebb026f6d5
+size 29526016
diff --git a/params_shard_191.bin b/params_shard_191.bin
new file mode 100644
index 0000000000000000000000000000000000000000..82a44b803df8cd0d687c5eb97c6af50b9ee9c1d6
--- /dev/null
+++ b/params_shard_191.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e398f7cd407c5aea548f68b834930cf0beccad5561010bc8d0391ff4fbe7188a
+size 141557760
diff --git a/params_shard_192.bin b/params_shard_192.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e889bce430e27f6e56e248fea9079083b796adf5
--- /dev/null
+++ b/params_shard_192.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e314b89d9df55f7f43e3abd075732a25c54f66ec5e32e0f33b2214c14e3aa12
+size 70778880
diff --git a/params_shard_193.bin b/params_shard_193.bin
new file mode 100644
index 0000000000000000000000000000000000000000..44bfb55e6d1b6e0bb37099f03d26854b01c261ed
--- /dev/null
+++ b/params_shard_193.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d0738851d69e57be47d8999981aa9bf13c55cf691c8fa6f0c9098741fc90add
+size 32440320
diff --git a/params_shard_194.bin b/params_shard_194.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b8a0b14e41d09acd089f6d00c55f82bf0b7b2dab
--- /dev/null
+++ b/params_shard_194.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8a91f975372fcb6af6edfc22dd02763ba156c1162e307ba95210e4a11651f15
+size 29526016
diff --git a/params_shard_195.bin b/params_shard_195.bin
new file mode 100644
index 0000000000000000000000000000000000000000..62ad7830b9199c94df3c24092caff9b0bfdffdfa
--- /dev/null
+++ b/params_shard_195.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8303214f42bbf8be6ec8f913f2fa5ee433e816e7afdaab5c754f25622e468b08
+size 141557760
diff --git a/params_shard_196.bin b/params_shard_196.bin
new file mode 100644
index 0000000000000000000000000000000000000000..9b109ba7edd2b49c6a0ec08350344c2e90ee99b4
--- /dev/null
+++ b/params_shard_196.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03cc837b4f0e9914bc16ae9b69ebde0cd7a39d2d94abdc2524f24e49c894e1d4
+size 70778880
diff --git a/params_shard_197.bin b/params_shard_197.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b98a71ef86c8d1cf4bc109b3e40b7eada3edbc43
--- /dev/null
+++ b/params_shard_197.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfee603e9e5a47471353d2b2191a866a2a6684e32a7a0f7c04ef5dc0831e0b19
+size 32440320
diff --git a/params_shard_198.bin b/params_shard_198.bin
new file mode 100644
index 0000000000000000000000000000000000000000..aefae6e3d0b4a04e39a0f5f0cd7200d022161a38
--- /dev/null
+++ b/params_shard_198.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60467dc0bf80e502c3d6acc32d693032cc243dfd4da86bf6bbea11b63e5967d7
+size 29526016
diff --git a/params_shard_199.bin b/params_shard_199.bin
new file mode 100644
index 0000000000000000000000000000000000000000..cf7b3316bb1922ecb2338b3e5b3d3c7095f46d42
--- /dev/null
+++ b/params_shard_199.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15cdd54b864d55490082305d0cf705eeef87fc25173e9c77c5c5a4f7cbf30a08
+size 141557760
diff --git a/params_shard_2.bin b/params_shard_2.bin
new file mode 100644
index 0000000000000000000000000000000000000000..03fabd06524c7e72d312594e1ee74d8fd5211bc4
--- /dev/null
+++ b/params_shard_2.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc52452d50897079c2459f5c1ae2711d75826f3f0575df7f361cd15f8baa97ac
+size 20658176
diff --git a/params_shard_20.bin b/params_shard_20.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b376d8c3f561410400e320e2f14ddb7aca3a05da
--- /dev/null
+++ b/params_shard_20.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b466e8f2cc5b302ed1a2b5ac109bcf40e0a5c4b9614c3dac94c4062f9464a26b
+size 70778880
diff --git a/params_shard_200.bin b/params_shard_200.bin
new file mode 100644
index 0000000000000000000000000000000000000000..24c4cf52828b30a39fa8548c35f22cf12cd5c412
--- /dev/null
+++ b/params_shard_200.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51ab99a5bf4133fd69d89dbc008d085d71c6f9a9f5e54c7654c090245f1f804e
+size 70778880
diff --git a/params_shard_201.bin b/params_shard_201.bin
new file mode 100644
index 0000000000000000000000000000000000000000..27e7a933a424e75810dbfdb205a90675ba1308b6
--- /dev/null
+++ b/params_shard_201.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24492ad4fa6f2bc5c995e7f71db7d3878d22f678c80dd784c761276dae4a96d5
+size 32440320
diff --git a/params_shard_202.bin b/params_shard_202.bin
new file mode 100644
index 0000000000000000000000000000000000000000..bd80fc2980958ba1ff3dc526eccdc7467a721e46
--- /dev/null
+++ b/params_shard_202.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06895ba4a1db41d16929edcaba5b2ed84a08e99a907e49e31aa750921e2146d2
+size 29526016
diff --git a/params_shard_203.bin b/params_shard_203.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b7011d2dc6273a9771afe5c7974a5e0244f3c90e
--- /dev/null
+++ b/params_shard_203.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5a5cd445b0e9e37ea7b4bd23dcf9a38f4faca79cd552a7897eb8b8a82356c60
+size 141557760
diff --git a/params_shard_204.bin b/params_shard_204.bin
new file mode 100644
index 0000000000000000000000000000000000000000..17c09ef270fb739683ee0cacafdace0e3c315abd
--- /dev/null
+++ b/params_shard_204.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2dac5e72f816d3fe873a10b1d1c978660c8a070154fcf4d4085c16ff22107dff
+size 70778880
diff --git a/params_shard_205.bin b/params_shard_205.bin
new file mode 100644
index 0000000000000000000000000000000000000000..ef07db1343d81c65f69db05e2eefc1447aba46d0
--- /dev/null
+++ b/params_shard_205.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f30720ef4e59030a776bbbfc7a98f655270be8a10f74063fa5d970cd5a966b8
+size 32440320
diff --git a/params_shard_206.bin b/params_shard_206.bin
new file mode 100644
index 0000000000000000000000000000000000000000..2a2424944e698a980a49fde50e9312084f363c48
--- /dev/null
+++ b/params_shard_206.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5177e8f2b97a7a3dcf45f959f3738f85f7a3b86f9486c388c87e037ad89c00c9
+size 29526016
diff --git a/params_shard_207.bin b/params_shard_207.bin
new file mode 100644
index 0000000000000000000000000000000000000000..53595a4363589681cf4be12de1d0d04a7522bd6e
--- /dev/null
+++ b/params_shard_207.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79a4a6b1ad09b86014055796569b6dfd9335ff74f5a5250f350ba8cf38ced74e
+size 141557760
diff --git a/params_shard_208.bin b/params_shard_208.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e931cef2c65d6b3544b62f46c4bbce288e703c11
--- /dev/null
+++ b/params_shard_208.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8dfe3d5cd62e3dd274c8b4f7b70e440eb3829692cfb3216fedddceb9f15822a2
+size 70778880
diff --git a/params_shard_209.bin b/params_shard_209.bin
new file mode 100644
index 0000000000000000000000000000000000000000..1f99bd2734a10c017efcec11172337c4fc649ebf
--- /dev/null
+++ b/params_shard_209.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:877590216c938a7e9404a87a898a7ae0f0504892d407f90e1c2a1e946134abea
+size 32440320
diff --git a/params_shard_21.bin b/params_shard_21.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d5c93ee2dc72145068f5f617e06c95ddcc88dc31
--- /dev/null
+++ b/params_shard_21.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fb513904b2f998812f735e9b5adf4115e3d3e0c4ac0b1d963e25087ec5b8cc2
+size 32440320
diff --git a/params_shard_210.bin b/params_shard_210.bin
new file mode 100644
index 0000000000000000000000000000000000000000..7540fe6d5a9811571bb08c3ceb74890698c4ea39
--- /dev/null
+++ b/params_shard_210.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2385d618a3d8a635442d41f9343f4233d473821c9f2d4b62ffae6038a78e5ca
+size 29526016
diff --git a/params_shard_211.bin b/params_shard_211.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e40860332921cc852b9579b4a8f260a3826ec8a3
--- /dev/null
+++ b/params_shard_211.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a78e315ec2b8743c69cb02bd104e4cc5ac1c1d3619d0ad763dcb758bc6c4fc7f
+size 141557760
diff --git a/params_shard_212.bin b/params_shard_212.bin
new file mode 100644
index 0000000000000000000000000000000000000000..dbdcb5aac4e7608db902635c1720137cd6923c7a
--- /dev/null
+++ b/params_shard_212.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c31f626f84dd3fe747ebb05b2db768d4e0add14b2610d3b1068e004766e7b7f
+size 70778880
diff --git a/params_shard_213.bin b/params_shard_213.bin
new file mode 100644
index 0000000000000000000000000000000000000000..f94868f0b302d4e2fbf8bd079f63b9322a469dc6
--- /dev/null
+++ b/params_shard_213.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1fc3ae8aa2d78e2dca349b209ddc76964b522b0c2cf46b6225d6f48e4146b88
+size 32440320
diff --git a/params_shard_214.bin b/params_shard_214.bin
new file mode 100644
index 0000000000000000000000000000000000000000..3d81eedbcbdeda9d75b0d2ca61920b814bb84c2f
--- /dev/null
+++ b/params_shard_214.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0400bea5e7054bf3dd0365da2629e4ce28202e4b48b4b1ef4d7e731104471de8
+size 29526016
diff --git a/params_shard_215.bin b/params_shard_215.bin
new file mode 100644
index 0000000000000000000000000000000000000000..81241fd9184e5505791b5cc86e87855624c9395e
--- /dev/null
+++ b/params_shard_215.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39f88f6971d0f83babd9be8da3d2a3c0c47e4a2c84e38f1f45acc8174067e65d
+size 141557760
diff --git a/params_shard_216.bin b/params_shard_216.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4a9a8d052bf114cf0d6975583bd461236e661f22
--- /dev/null
+++ b/params_shard_216.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edd87c4379dabaf442d012c9c31df174bd447cd856d03537afcbe775ee8a0e80
+size 70778880
diff --git a/params_shard_217.bin b/params_shard_217.bin
new file mode 100644
index 0000000000000000000000000000000000000000..a9571365f1628fc4b08a601a62e09f9d4a27cea4
--- /dev/null
+++ b/params_shard_217.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9174bd28edfdf5585e3d6b8f485bf87727be94c9431d8b153b6def56652e694c
+size 32440320
diff --git a/params_shard_218.bin b/params_shard_218.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d4d07b5c3a36c968206828979f34da983d8ea98f
--- /dev/null
+++ b/params_shard_218.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f683e51f12fe4b09ab3de6a3d99a46b00c66bae69eca602ccf0b508afcca031
+size 29526016
diff --git a/params_shard_219.bin b/params_shard_219.bin
new file mode 100644
index 0000000000000000000000000000000000000000..186228f66221b86b81a396aa9eecf11dfac50935
--- /dev/null
+++ b/params_shard_219.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdbb59d6debbaebc9c4b84c32bac61e08a8aff558b5a826b81928911d5c605f2
+size 141557760
diff --git a/params_shard_22.bin b/params_shard_22.bin
new file mode 100644
index 0000000000000000000000000000000000000000..2f7bd47821e7076cd0a530e30ec70ca5f986f3cc
--- /dev/null
+++ b/params_shard_22.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:424b50f9a3c5501f08d981ddb1a00922e6c0e1b16fb2d3853cfafde60b8e39d2
+size 29526016
diff --git a/params_shard_220.bin b/params_shard_220.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b3d107d5b79e7bb54fbc1fe747c678c733a087a0
--- /dev/null
+++ b/params_shard_220.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0088cb7b527f007b50e65d5097125a0d34793a4984981a60152cf847d8f25316
+size 70778880
diff --git a/params_shard_221.bin b/params_shard_221.bin
new file mode 100644
index 0000000000000000000000000000000000000000..1c53504229bab49fcde8d7f1d2b08b80badf26c4
--- /dev/null
+++ b/params_shard_221.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05a726fce1822d34aa4e02da896262a52bab276fa2a46c5458fb45826140ce41
+size 32440320
diff --git a/params_shard_222.bin b/params_shard_222.bin
new file mode 100644
index 0000000000000000000000000000000000000000..9f5a5b87753b2063670be62f89bf5300fff11cef
--- /dev/null
+++ b/params_shard_222.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f2f7223906fd2a8a89eadbbeb64a0fda5b5cee30889e93cee255aa2a0975034
+size 29526016
diff --git a/params_shard_223.bin b/params_shard_223.bin
new file mode 100644
index 0000000000000000000000000000000000000000..cff913080f09be36d68152f29356c658fc1151c2
--- /dev/null
+++ b/params_shard_223.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bbba4f86f61683b4d3240818e63e18c0acfc3646cc57ec01f0e6599caea2414
+size 141557760
diff --git a/params_shard_224.bin b/params_shard_224.bin
new file mode 100644
index 0000000000000000000000000000000000000000..dc14456b7fcd851f908f5f2cf4fc546ca917718b
--- /dev/null
+++ b/params_shard_224.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01b1836260c75c14bf83d581daecaa41b1854f0e90c1ad9d7ccfd32c47e41251
+size 70778880
diff --git a/params_shard_225.bin b/params_shard_225.bin
new file mode 100644
index 0000000000000000000000000000000000000000..907d149fff585e2d05852d18b6c6650e1efced6c
--- /dev/null
+++ b/params_shard_225.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:387dfd75796b4d1ef494e700124a9e4a00a1df07d7263ace9d34a3f5ffdcbe13
+size 32440320
diff --git a/params_shard_226.bin b/params_shard_226.bin
new file mode 100644
index 0000000000000000000000000000000000000000..76f8af3fbaba409ad1762fb6266c391cce18c37b
--- /dev/null
+++ b/params_shard_226.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd8d7e9204e1d2a6cb7c58901f8d4ca0bdddb6cdb32364ee3f88088faa0cfeb0
+size 29526016
diff --git a/params_shard_227.bin b/params_shard_227.bin
new file mode 100644
index 0000000000000000000000000000000000000000..0b824d402a53af1224995e683d001622a839916a
--- /dev/null
+++ b/params_shard_227.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7b6d0dfe83e63cf4a447279f65839bacb7f9f357cb3a7b80c4859e2e31a496f
+size 141557760
diff --git a/params_shard_228.bin b/params_shard_228.bin
new file mode 100644
index 0000000000000000000000000000000000000000..a8978d5498ccd2586bf3962aa914557484d9bfac
--- /dev/null
+++ b/params_shard_228.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4732ea599c02238879cb43e396c23ff3cdcdedf973696cb49b2b792aaa863675
+size 70778880
diff --git a/params_shard_229.bin b/params_shard_229.bin
new file mode 100644
index 0000000000000000000000000000000000000000..24824775649ccc6e13d44c5632b1f5a42a826a77
--- /dev/null
+++ b/params_shard_229.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92f482f0a571dd92494dd0fa5476e3084ae4da00c613bbb8999e20ca6c69cf1c
+size 32440320
diff --git a/params_shard_23.bin b/params_shard_23.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c27d3e1601f753571cf82f8d836b502e2dbfcaf3
--- /dev/null
+++ b/params_shard_23.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80fc5917b24f773a19e002f5192cf574d2ed8efb5a76498461a8c4d14823acbe
+size 141557760
diff --git a/params_shard_230.bin b/params_shard_230.bin
new file mode 100644
index 0000000000000000000000000000000000000000..1f20acceade7b77c4d901d041ec93ae1c2a8c93d
--- /dev/null
+++ b/params_shard_230.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66f43ff2efee5aa6f9dd8c667f746cf3687092ae22caa8a2f4720a3087a7b6e1
+size 29526016
diff --git a/params_shard_231.bin b/params_shard_231.bin
new file mode 100644
index 0000000000000000000000000000000000000000..2442cc67c29d36a5180b20b63dbb03b3dcf6308b
--- /dev/null
+++ b/params_shard_231.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77e872838ab18ecd30924f6350de73912cfa2593b740f187a5facfff75247cd0
+size 141557760
diff --git a/params_shard_232.bin b/params_shard_232.bin
new file mode 100644
index 0000000000000000000000000000000000000000..addfa0826b79e6f250aea433c38f1786a3851396
--- /dev/null
+++ b/params_shard_232.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f12174b1f2202188fe19ab08c2095c607daf1215f4629c2441d7c836131b05
+size 70778880
diff --git a/params_shard_233.bin b/params_shard_233.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c1df0bab1cddfe2fc10d3fc165531aed15c04f18
--- /dev/null
+++ b/params_shard_233.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e54887c68ac3ca9952eb18378bd2ace3a09aea2eb184674d3a5fec38c567433f
+size 32440320
diff --git a/params_shard_234.bin b/params_shard_234.bin
new file mode 100644
index 0000000000000000000000000000000000000000..0df1d051ea2c2e9421df005d22ebed1285a5f472
--- /dev/null
+++ b/params_shard_234.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80395d0557a5904775356e4f4ec1142908acba461d58a2e6b36069aec2c9b663
+size 29526016
diff --git a/params_shard_235.bin b/params_shard_235.bin
new file mode 100644
index 0000000000000000000000000000000000000000..1102cedd46e2a890c689e531bf590897b3366ce0
--- /dev/null
+++ b/params_shard_235.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07da709b0b394877418fe2c89ffd7261443673a6274a4f389c7cac9b6e96da6d
+size 141557760
diff --git a/params_shard_236.bin b/params_shard_236.bin
new file mode 100644
index 0000000000000000000000000000000000000000..89aada29d738dd0011737947ccb7dee5743a6581
--- /dev/null
+++ b/params_shard_236.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f685bc2fa366e5415a7d7338b9eaf943571b7f790350b49d8fa6614c998d45ba
+size 70778880
diff --git a/params_shard_237.bin b/params_shard_237.bin
new file mode 100644
index 0000000000000000000000000000000000000000..db44530c7527ef8dd9b6b94472a9818b8ef23e79
--- /dev/null
+++ b/params_shard_237.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d04352c9a1cbd1f3a891b4405d3d938b0ef3244528c102bb6cda64388f34b01
+size 32440320
diff --git a/params_shard_238.bin b/params_shard_238.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e95dda48873a5dd2de5141d71bf503b9caeecdfa
--- /dev/null
+++ b/params_shard_238.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa53284542e91836e5ba8f7b8cb1288e1129db6b545857b15ff066af79856fe9
+size 29526016
diff --git a/params_shard_239.bin b/params_shard_239.bin
new file mode 100644
index 0000000000000000000000000000000000000000..62a94d977787af6efeea6f34cf8a7eb6c8a3fce7
--- /dev/null
+++ b/params_shard_239.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:223483d74dd8753af4038ed9ae36da10b5abea4039304779083641a9cabc54ad
+size 141557760
diff --git a/params_shard_24.bin b/params_shard_24.bin
new file mode 100644
index 0000000000000000000000000000000000000000..f1a85b4a3ae35fb8e2a17230c202d83641bfb492
--- /dev/null
+++ b/params_shard_24.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca04f536e1e82645740bd4e007120a4f177a86b1a886500603378b4fa0fc7663
+size 70778880
diff --git a/params_shard_240.bin b/params_shard_240.bin
new file mode 100644
index 0000000000000000000000000000000000000000..be014cea7d554bcccf50b10a79a8c4387a87359e
--- /dev/null
+++ b/params_shard_240.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e98623484e3c4c356d247eed0177e7a9315ec7026139eb1f7c39ef2b69e541ec
+size 70778880
diff --git a/params_shard_241.bin b/params_shard_241.bin
new file mode 100644
index 0000000000000000000000000000000000000000..039103ba0eee4240be664e198c7e0bb906c1485e
--- /dev/null
+++ b/params_shard_241.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d624ba9e7962ab060a6ae2ca10123e0aa9d873b088b691c25395e6aede5c4928
+size 32440320
diff --git a/params_shard_242.bin b/params_shard_242.bin
new file mode 100644
index 0000000000000000000000000000000000000000..219c6327265c44e689eb1352d0d5c9a074a0497e
--- /dev/null
+++ b/params_shard_242.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd8aa4b40d4ebad9a212a0543f46ce745a4cb14ec8b0b6fcdf2772164d9ffe13
+size 29526016
diff --git a/params_shard_243.bin b/params_shard_243.bin
new file mode 100644
index 0000000000000000000000000000000000000000..330c9bd24c8c6726e1043b87a224b12366d4518b
--- /dev/null
+++ b/params_shard_243.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:283474824a62ecff81196df9f351b995a83478e902d8eba7a683c4ab70f5dfe5
+size 141557760
diff --git a/params_shard_244.bin b/params_shard_244.bin
new file mode 100644
index 0000000000000000000000000000000000000000..7f0a857262cea0ed8d2fde804aee4b90d1f9e0d0
--- /dev/null
+++ b/params_shard_244.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68bc5fd0b06b71ab7beaf1668b9a2731a220faad84be5b70e58b64cdf7bde3ff
+size 70778880
diff --git a/params_shard_245.bin b/params_shard_245.bin
new file mode 100644
index 0000000000000000000000000000000000000000..bbe0217917e470d76d5371ad1edbccf0d66d34d9
--- /dev/null
+++ b/params_shard_245.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:046c3c7320f3bdee4431eac9beabd5d0cbd3e392f77ca5b81f7edc37a30a289b
+size 32440320
diff --git a/params_shard_246.bin b/params_shard_246.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c320460dec3345a920b2fe51d098b5f4c5011e9e
--- /dev/null
+++ b/params_shard_246.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7b3544c000ad3498b31e292c879aadd1be414397fd20ebac4294a150084c656
+size 29526016
diff --git a/params_shard_247.bin b/params_shard_247.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e73266ae96fdda91839e7a127a0152fc44b4b7d7
--- /dev/null
+++ b/params_shard_247.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57b5abf0450456749988af95bb60dcea7a5dda7112a4bcb994f08adf8bb82bdc
+size 141557760
diff --git a/params_shard_248.bin b/params_shard_248.bin
new file mode 100644
index 0000000000000000000000000000000000000000..5178fbe78dd4af20df2de0c6ba717ded822ba72d
--- /dev/null
+++ b/params_shard_248.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4f976d6c45a91950076bcec0e92c6ce793a80692c20c78784b771dae7fac1ea
+size 70778880
diff --git a/params_shard_249.bin b/params_shard_249.bin
new file mode 100644
index 0000000000000000000000000000000000000000..a152d6406fde2c3806271a2cdc2b745d3db9f4f0
--- /dev/null
+++ b/params_shard_249.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b9dee50fca73471d5643b61bfa7007e5416038b3b680d15299e8b60397558d9
+size 32440320
diff --git a/params_shard_25.bin b/params_shard_25.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e59886ff1a3350cf49c997044ed24fed1400c65b
--- /dev/null
+++ b/params_shard_25.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63be9cc5699a1fc3e29ef33dfd1faa7b51173d4d5e2c1a3c26a5b42b76496373
+size 32440320
diff --git a/params_shard_250.bin b/params_shard_250.bin
new file mode 100644
index 0000000000000000000000000000000000000000..21dd326d8047e74f9da125c43ccd942fc4a56a09
--- /dev/null
+++ b/params_shard_250.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9a123a64f060c38a7e8d0968a0893b3f8f13dfec358a2ff9bc776aa0352a3cc
+size 29526016
diff --git a/params_shard_251.bin b/params_shard_251.bin
new file mode 100644
index 0000000000000000000000000000000000000000..311248ba352b23738fafc5c8e78f15c298ba4b41
--- /dev/null
+++ b/params_shard_251.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9939e11c9f53a5dec968c1237ad04dbe27bbeb6a3ffdd26942fa685e7f0cbea7
+size 141557760
diff --git a/params_shard_252.bin b/params_shard_252.bin
new file mode 100644
index 0000000000000000000000000000000000000000..9713a93833bffb62c790e9a73e85420080fbc90f
--- /dev/null
+++ b/params_shard_252.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d3618a4884096e701ca386cd53bebd1aec3b7228eac6e91f9ffb735892f6bc0
+size 70778880
diff --git a/params_shard_253.bin b/params_shard_253.bin
new file mode 100644
index 0000000000000000000000000000000000000000..712dea1013baf849e947c76ca97f53bdec464ee9
--- /dev/null
+++ b/params_shard_253.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf0808066e4e1b90090c0b0fb3627632f5e3b9205fe4b89f14cc7597bfe8c13f
+size 32440320
diff --git a/params_shard_254.bin b/params_shard_254.bin
new file mode 100644
index 0000000000000000000000000000000000000000..38b1964c87c001ad70196fe7e4a09e0d2a44f2cf
--- /dev/null
+++ b/params_shard_254.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e209f25852cb544d0ab8106573692f9a816f240876e10a3700bf085a0c30c47e
+size 29526016
diff --git a/params_shard_255.bin b/params_shard_255.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d59a58adeefc2a2fda1c6941ebab0c8db937adf8
--- /dev/null
+++ b/params_shard_255.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5dd34c9d0ca25d63991c3000e1b1fb11d196b18c9f35c36c74db795023801968
+size 141557760
diff --git a/params_shard_256.bin b/params_shard_256.bin
new file mode 100644
index 0000000000000000000000000000000000000000..16bff29cda3767b6fbfff07a1985c665af224f70
--- /dev/null
+++ b/params_shard_256.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0cc21c192ab4be42e7c34b30276bf82a4cf3cff9a7c5d0145f2540e1134e318
+size 70778880
diff --git a/params_shard_257.bin b/params_shard_257.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d84e60e49d72e9f9457d2291c1f699ada213e343
--- /dev/null
+++ b/params_shard_257.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6d4c969877e885d40f07690ffded6a598185cacbd3cc9e600207dfe735f1652
+size 32440320
diff --git a/params_shard_258.bin b/params_shard_258.bin
new file mode 100644
index 0000000000000000000000000000000000000000..6bf503e774fc7e28cee2624789d8491d0ee3ecb0
--- /dev/null
+++ b/params_shard_258.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e4a2f16983a66d12226896f65623dc66ec12914fc4b85959c533ea2287db069
+size 389283840
diff --git a/params_shard_259.bin b/params_shard_259.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e289fddc1e04bac2cca4a48b88e3dc5fe3a334b5
--- /dev/null
+++ b/params_shard_259.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8baeb6e0d5a30ac3fb3929add4f34f72856b9f5a022f3bdbb4c7e959797e496
+size 48660480
diff --git a/params_shard_26.bin b/params_shard_26.bin
new file mode 100644
index 0000000000000000000000000000000000000000..085d1a8aaded512b9bc7f321e844fbd119bfb3a9
--- /dev/null
+++ b/params_shard_26.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7676d55a2b989f85a08088ad5245274086077d72332351a2ce1da044ef36d005
+size 29526016
diff --git a/params_shard_260.bin b/params_shard_260.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e90adad1fb94e69234f0f5e760a6e5b1cfc2f801
--- /dev/null
+++ b/params_shard_260.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ddbbbf3ef302c081645a7fc2b969dddc571a7e4696f3949a77c939928de8ac5
+size 8878080
diff --git a/params_shard_27.bin b/params_shard_27.bin
new file mode 100644
index 0000000000000000000000000000000000000000..56200e3a0407b0f0b81368d05055852a063b5f4b
--- /dev/null
+++ b/params_shard_27.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93758957019f3cc8645b3d589eff3ef972fe3f6f91f8b3fc48f5375a820ef64e
+size 141557760
diff --git a/params_shard_28.bin b/params_shard_28.bin
new file mode 100644
index 0000000000000000000000000000000000000000..947ffb1dd560ec637ae4b4ad59c6fa8090c20cec
--- /dev/null
+++ b/params_shard_28.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec9539f8735709cb04c866cb45c844b3f0109f5103f2a38566d7512d21e41aa4
+size 70778880
diff --git a/params_shard_29.bin b/params_shard_29.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c929f17a7d37e1b4274043b1c331ce3e8bfdba9a
--- /dev/null
+++ b/params_shard_29.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e8b0e0e6cae7298b0197e585500e57828ead6e422195faef7d776b5436fbbc6
+size 32440320
diff --git a/params_shard_3.bin b/params_shard_3.bin
new file mode 100644
index 0000000000000000000000000000000000000000..2cd7abbd34e284ac87beae138323f6960276f5aa
--- /dev/null
+++ b/params_shard_3.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c01e1538412e270fc6bf60ec421bd292eb7bce454ba793ef3bbbf818fe8ec835
+size 141557760
diff --git a/params_shard_30.bin b/params_shard_30.bin
new file mode 100644
index 0000000000000000000000000000000000000000..889b2edba14c6ee390db60e5953b7eb29308a475
--- /dev/null
+++ b/params_shard_30.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfa26b62a893228db93a3a72dfbad6979ef8338e7d3e55f765441c5d3f9b4973
+size 29526016
diff --git a/params_shard_31.bin b/params_shard_31.bin
new file mode 100644
index 0000000000000000000000000000000000000000..a503388288d88c372722282b2c08528f43120db4
--- /dev/null
+++ b/params_shard_31.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58294048029331468f70e4b7c0cf194daedc949a02c43063115f7dcbd0bf35d9
+size 141557760
diff --git a/params_shard_32.bin b/params_shard_32.bin
new file mode 100644
index 0000000000000000000000000000000000000000..a6b1af362a17d6234ecb32f85bae78be8e0fa95a
--- /dev/null
+++ b/params_shard_32.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9db709a0025abf5bff064945ef77df37c97d1f87a38a4e76c6da4f6085c2fd5
+size 70778880
diff --git a/params_shard_33.bin b/params_shard_33.bin
new file mode 100644
index 0000000000000000000000000000000000000000..f6065c41b5128c593b53bef34c030fdb04378103
--- /dev/null
+++ b/params_shard_33.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f34c3cc8ab06a378c2ea448c002d0434de4376a9d2528eac53d6fb8460e20b4b
+size 32440320
diff --git a/params_shard_34.bin b/params_shard_34.bin
new file mode 100644
index 0000000000000000000000000000000000000000..43a834052026c17a3049ee53af4457609c53bbc5
--- /dev/null
+++ b/params_shard_34.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d71f2c47221a529631a4722d0f3471306255e8fd8efaf9ea43fb5851c14d7e19
+size 29526016
diff --git a/params_shard_35.bin b/params_shard_35.bin
new file mode 100644
index 0000000000000000000000000000000000000000..f49788b651394efd85b6cdc32338471b48f1d5c9
--- /dev/null
+++ b/params_shard_35.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4be7499532023e010c498b31b552a59dbb0b494dad38ccfa6685ffb26d22c148
+size 141557760
diff --git a/params_shard_36.bin b/params_shard_36.bin
new file mode 100644
index 0000000000000000000000000000000000000000..77ca091caa4050c695ad4e7b7cf500f20744f1c3
--- /dev/null
+++ b/params_shard_36.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12422e37f48ea9592f329726146fd1a5323b5d5ff5714241d196a027926a9d45
+size 70778880
diff --git a/params_shard_37.bin b/params_shard_37.bin
new file mode 100644
index 0000000000000000000000000000000000000000..a24771b39ea201b8a927fcf8d0afe98ba8ee001f
--- /dev/null
+++ b/params_shard_37.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef3d8990fa4fbfd1c57ef5274188332099844bde30a8e16b358a6fa72916cbe9
+size 32440320
diff --git a/params_shard_38.bin b/params_shard_38.bin
new file mode 100644
index 0000000000000000000000000000000000000000..5ffbca1b2f8d2a0930170185a9306f241e82fa8d
--- /dev/null
+++ b/params_shard_38.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d3cbeedad6a41e3809925443aa157e45741cec1e7d241c6c95ffdae1c5bd95d
+size 29526016
diff --git a/params_shard_39.bin b/params_shard_39.bin
new file mode 100644
index 0000000000000000000000000000000000000000..a2860629b8b423ebbcaebe67f049b207526bef74
--- /dev/null
+++ b/params_shard_39.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f0f765c83df634458a607edabafac81d8c384cf395b9094fb74455ab499b668
+size 141557760
diff --git a/params_shard_4.bin b/params_shard_4.bin
new file mode 100644
index 0000000000000000000000000000000000000000..5b4f89a7161df55fe767f6eee26663c2990052f3
--- /dev/null
+++ b/params_shard_4.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:064a661595feffbd7f6cf7c4422e3bde93d9569a8f95ff49a7f512fedd984e08
+size 70778880
diff --git a/params_shard_40.bin b/params_shard_40.bin
new file mode 100644
index 0000000000000000000000000000000000000000..94864e83783b6b9440907e440e3bab433af5a917
--- /dev/null
+++ b/params_shard_40.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dff64415179a92d893f4450caa78ca5effb05d80ad5745c65ec2d7563807efcc
+size 70778880
diff --git a/params_shard_41.bin b/params_shard_41.bin
new file mode 100644
index 0000000000000000000000000000000000000000..82620b0379634964131793d95cb322d2dd39c8c0
--- /dev/null
+++ b/params_shard_41.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50e61452487dfd0111a3bebed25a7a34e7d724ea53d6bad5260eb3dcb78397fa
+size 32440320
diff --git a/params_shard_42.bin b/params_shard_42.bin
new file mode 100644
index 0000000000000000000000000000000000000000..42e664a86e9ba067dbefb1167c2ffaab0028e15a
--- /dev/null
+++ b/params_shard_42.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b2e693d3f0e480b404ac6f08f9c460acd6b3ba891fc3dff09289329d168ba17
+size 29526016
diff --git a/params_shard_43.bin b/params_shard_43.bin
new file mode 100644
index 0000000000000000000000000000000000000000..5ec2260a6a2daa882b507e3111a552c76d969981
--- /dev/null
+++ b/params_shard_43.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ec0f1b6e40cdce67d82b3b53d9d262b014e0c78252789f6119395fb76febaee
+size 141557760
diff --git a/params_shard_44.bin b/params_shard_44.bin
new file mode 100644
index 0000000000000000000000000000000000000000..a9565535471e00ee11bea04a1afb9c6595affc8e
--- /dev/null
+++ b/params_shard_44.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5aac9ebbe31cd5cb50bf00ec02d909303ffb69423f8b7d88ebb0a510f4eaf5d6
+size 70778880
diff --git a/params_shard_45.bin b/params_shard_45.bin
new file mode 100644
index 0000000000000000000000000000000000000000..3665f42b37e63b4414647f8224ab728bef582aa8
--- /dev/null
+++ b/params_shard_45.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1eb23c0e0d1a57de6d31561d9790677d819731b2b173bd03c9caa4e6b26b280e
+size 32440320
diff --git a/params_shard_46.bin b/params_shard_46.bin
new file mode 100644
index 0000000000000000000000000000000000000000..56900505800f611e12356c369348822a9cbe16e9
--- /dev/null
+++ b/params_shard_46.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f92ce857014deb943c3c0f440835e994b5158ba6f14edb9f68dcb00cc3bc6dee
+size 29526016
diff --git a/params_shard_47.bin b/params_shard_47.bin
new file mode 100644
index 0000000000000000000000000000000000000000..7b8254f6e2a7e943cd5126ebb69382b307053b10
--- /dev/null
+++ b/params_shard_47.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1569db3cbe123dd620a2c203e665c2141e0a2d97e549695a2734543c4bab2b0b
+size 141557760
diff --git a/params_shard_48.bin b/params_shard_48.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b5e3ee44a9fa4db90b8ebc3b90ff752e8f07f8fa
--- /dev/null
+++ b/params_shard_48.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8aab74cecd0bb41bbaa1f154f9077e80952f5b7600e8d6543f71bf499ddbeb0c
+size 70778880
diff --git a/params_shard_49.bin b/params_shard_49.bin
new file mode 100644
index 0000000000000000000000000000000000000000..358f08aac26b8d1561fa596a45a82784ae2e4b82
--- /dev/null
+++ b/params_shard_49.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c930f85d84e986c80af1120961db1334d2e497f19607bbe27158902256138906
+size 32440320
diff --git a/params_shard_5.bin b/params_shard_5.bin
new file mode 100644
index 0000000000000000000000000000000000000000..6cbc7614ff32b3ca2e0a55eb6eea50a4bfcba38e
--- /dev/null
+++ b/params_shard_5.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75a0bb589580f317a96853420e665489f0b93a4fc528aa86ba99c167f789b200
+size 32440320
diff --git a/params_shard_50.bin b/params_shard_50.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b55754410a93136d50c71fc46e2f45f76e920209
--- /dev/null
+++ b/params_shard_50.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11c24151ce34a0f49c3fc9acb15fd77258c6acc4d8d066e69900952a6dd4aa5f
+size 29526016
diff --git a/params_shard_51.bin b/params_shard_51.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b9f196af8c9e4279aefdd408dc488ada584e39fd
--- /dev/null
+++ b/params_shard_51.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:732afcddd19e04eafa7f79a44d68281f662c64d4fc9f4f1be427915df1ce68d0
+size 141557760
diff --git a/params_shard_52.bin b/params_shard_52.bin
new file mode 100644
index 0000000000000000000000000000000000000000..81d7605de832198cf80fd0327d5ad6e958db32f7
--- /dev/null
+++ b/params_shard_52.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a89ad1d3edfc0eda1c78fc154c10a8f76542b9c2cf0213c35b1879201289ccd5
+size 70778880
diff --git a/params_shard_53.bin b/params_shard_53.bin
new file mode 100644
index 0000000000000000000000000000000000000000..9c67749639c1f2e1b2d57075b23560302bae1acf
--- /dev/null
+++ b/params_shard_53.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c634b84162e4ee60257dd60f5929849a6b09034197d2295695abcd90be3637a
+size 32440320
diff --git a/params_shard_54.bin b/params_shard_54.bin
new file mode 100644
index 0000000000000000000000000000000000000000..2da7db84ac05c9e8220a3db3269e53ec220614e2
--- /dev/null
+++ b/params_shard_54.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f9154afa129bd719fe92d724b96705aed5c11ead6bbc5bd6808a46b21fe5627
+size 29526016
diff --git a/params_shard_55.bin b/params_shard_55.bin
new file mode 100644
index 0000000000000000000000000000000000000000..91f9d1a0ec5b16eb9e29fddf26698210a17a9641
--- /dev/null
+++ b/params_shard_55.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76ed309f551ef21e3fa5a6c9b0310690d2bcac7a08af4db849b8cb10f50faf8e
+size 141557760
diff --git a/params_shard_56.bin b/params_shard_56.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4f6509350959794b57feedda9de02ba53d5e4266
--- /dev/null
+++ b/params_shard_56.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cce9b258842baf67f7f816f95daa4716048e97eac7008ae415418480eb2c2717
+size 70778880
diff --git a/params_shard_57.bin b/params_shard_57.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b841d16c7561974dc44ffc75ccb5b1d20de46721
--- /dev/null
+++ b/params_shard_57.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:994fac9968cb85267984a082617038699d6875c18f1874ce2b1f4152c9246ded
+size 32440320
diff --git a/params_shard_58.bin b/params_shard_58.bin
new file mode 100644
index 0000000000000000000000000000000000000000..739104f358b59df90c2cd6dda9d2de040d465c17
--- /dev/null
+++ b/params_shard_58.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b36027a066e4d10b0f6960039680d80204a3ee2f343e4c06b3b1ad88f21274f1
+size 29526016
diff --git a/params_shard_59.bin b/params_shard_59.bin
new file mode 100644
index 0000000000000000000000000000000000000000..5d654354a87735dfa58145e9c2a0e01547cf3053
--- /dev/null
+++ b/params_shard_59.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad917522df4ccc27182c6f914de3016195b4f24a56152149d88780255d42a1f6
+size 141557760
diff --git a/params_shard_6.bin b/params_shard_6.bin
new file mode 100644
index 0000000000000000000000000000000000000000..116727d936ebfedfe78719e57a6ef5ed3179bcf6
--- /dev/null
+++ b/params_shard_6.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62eb25e5888ce6b05e51f299d6b5893c916f06819afb4826f31f4b933a34304a
+size 29526016
diff --git a/params_shard_60.bin b/params_shard_60.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c88494b3ec5de77cf95dd3d44c64d6c9f9a09146
--- /dev/null
+++ b/params_shard_60.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26d42ad92ff468c74435130c4c21848ed681f8050bf0b5ef88f8033a22d72c8b
+size 70778880
diff --git a/params_shard_61.bin b/params_shard_61.bin
new file mode 100644
index 0000000000000000000000000000000000000000..ad340f1a48e54382b15081fe4c00e46a50e71f5f
--- /dev/null
+++ b/params_shard_61.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a78c3f18aa9a40d7f600902f4bc9af07cfc021ebaa16d44c665afe907c2d813
+size 32440320
diff --git a/params_shard_62.bin b/params_shard_62.bin
new file mode 100644
index 0000000000000000000000000000000000000000..819784937859af30e3fd0e85ddb2020ce997f982
--- /dev/null
+++ b/params_shard_62.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2826ceaa5e3afea7c85472d1714485fbfe27ddede4b4dcb279dff3c157ade4a
+size 29526016
diff --git a/params_shard_63.bin b/params_shard_63.bin
new file mode 100644
index 0000000000000000000000000000000000000000..8fc6160a807e0dd389f1b26621a6727c9fd53eef
--- /dev/null
+++ b/params_shard_63.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62a6d732bbfde798c28f5d3dad56c05f762983c9e2284e084266eb96df52b066
+size 141557760
diff --git a/params_shard_64.bin b/params_shard_64.bin
new file mode 100644
index 0000000000000000000000000000000000000000..1d67af1fb050fb1fdaf01fb38704323529020d7b
--- /dev/null
+++ b/params_shard_64.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30be6c90d618f04c33edb2dae40ca73776f5386b82cf750b3fd3a026f2422940
+size 70778880
diff --git a/params_shard_65.bin b/params_shard_65.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d386572658cec93f99ad1ccec4d1edbd264914b0
--- /dev/null
+++ b/params_shard_65.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b954c17871c1f465ec946abfb7f4e2b8320c420031b79d721767d69e099f8db0
+size 32440320
diff --git a/params_shard_66.bin b/params_shard_66.bin
new file mode 100644
index 0000000000000000000000000000000000000000..54f09568bfe109341e6e165aeff7fd1fe8223049
--- /dev/null
+++ b/params_shard_66.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26283cdb610dcb93566e4389b5bb8218042e5cb0062ab71b9ea5527f976bbe66
+size 29526016
diff --git a/params_shard_67.bin b/params_shard_67.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b3efd2888ec945710e5ff51ecf2ec672435e0d74
--- /dev/null
+++ b/params_shard_67.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3de3138774ef88ef69d55033a3489464edc76d6068f3f6ad564812fe6b0509ee
+size 141557760
diff --git a/params_shard_68.bin b/params_shard_68.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c5ce716bcc121442657cd841f44fa77839aa42ec
--- /dev/null
+++ b/params_shard_68.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:694c20c7ae238dd88e03323f3a6d7defaf921047ceacc8a07b52a91eeffd7803
+size 70778880
diff --git a/params_shard_69.bin b/params_shard_69.bin
new file mode 100644
index 0000000000000000000000000000000000000000..9de95af0d963432e200950a5438069afb16fe655
--- /dev/null
+++ b/params_shard_69.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adaf282ddabe7ba3dabb7a17cc0a14c4e4782c6cbba715d459bcac5960f4afc6
+size 32440320
diff --git a/params_shard_7.bin b/params_shard_7.bin
new file mode 100644
index 0000000000000000000000000000000000000000..f2d955c3e44ad34d8d043e298886be69508b7f2b
--- /dev/null
+++ b/params_shard_7.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:268d9943af1048b4320633fd826192e9f858dfe0842433e0a872019198220d15
+size 141557760
diff --git a/params_shard_70.bin b/params_shard_70.bin
new file mode 100644
index 0000000000000000000000000000000000000000..833647236651fd0d30d3cbae2105cdcd3f4bd042
--- /dev/null
+++ b/params_shard_70.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b077a8f5ed0ebfed7c83a464f0eac7f695e150f78140c19e3b8f0cd252ffa6cc
+size 29526016
diff --git a/params_shard_71.bin b/params_shard_71.bin
new file mode 100644
index 0000000000000000000000000000000000000000..137e9c7388fe5440a8f863ec4e6055fe33831012
--- /dev/null
+++ b/params_shard_71.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2271c6efaf2eaac5093852c9c24ba91488582ffe404931f80fa31ef10896cf5f
+size 141557760
diff --git a/params_shard_72.bin b/params_shard_72.bin
new file mode 100644
index 0000000000000000000000000000000000000000..0bc93500fbfa11f2a7bd74b7966c45ccf6fe0408
--- /dev/null
+++ b/params_shard_72.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89b198c7875621667b2033748133e250f7a1c8e9d4c89895c3ab26ce96a55c84
+size 70778880
diff --git a/params_shard_73.bin b/params_shard_73.bin
new file mode 100644
index 0000000000000000000000000000000000000000..884a0d4852d341a353fe0d17c6a49fda05e4a4e7
--- /dev/null
+++ b/params_shard_73.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77b33e2202f81f36b6822832f50c6a0990e049988a4674be3fa7d538ccc48d45
+size 32440320
diff --git a/params_shard_74.bin b/params_shard_74.bin
new file mode 100644
index 0000000000000000000000000000000000000000..33f618529c9dd53f8cced775ed4be4a5ab923cff
--- /dev/null
+++ b/params_shard_74.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfcd8de436b21d661e6714a3a1f5018a29f4abb2086d74c5a14a46750af16bff
+size 29526016
diff --git a/params_shard_75.bin b/params_shard_75.bin
new file mode 100644
index 0000000000000000000000000000000000000000..0c0da31a9a79a06a6365c209ff84100b179fff5b
--- /dev/null
+++ b/params_shard_75.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19a0823b49923d751860cc0ba6c7cd4a4a9ddbe1a398a3466d77b33d4c8a4f95
+size 141557760
diff --git a/params_shard_76.bin b/params_shard_76.bin
new file mode 100644
index 0000000000000000000000000000000000000000..353be76cdcf38e566b80283b3cb2016065eec7ae
--- /dev/null
+++ b/params_shard_76.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebf2b91c71ad04ad1a4883a4b2d832e1f1124cc72b2cdc9109d66ee4631aa9ae
+size 70778880
diff --git a/params_shard_77.bin b/params_shard_77.bin
new file mode 100644
index 0000000000000000000000000000000000000000..3f235e3c77c6138ed1551f425718812e224032da
--- /dev/null
+++ b/params_shard_77.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:139e9008e85710bd0c3bbb2085b85a8e0434f8c387c498353c9eaab30172933d
+size 32440320
diff --git a/params_shard_78.bin b/params_shard_78.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c06c4017f673ddebc44a4d7da484c247727cd819
--- /dev/null
+++ b/params_shard_78.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f568d4255923e667577e8f950c5b6b8f649ed569c4a8d66f194b79a18d14fcdc
+size 29526016
diff --git a/params_shard_79.bin b/params_shard_79.bin
new file mode 100644
index 0000000000000000000000000000000000000000..95b05f5a0ffe5d37a38f65ab2d32da4bf34993bf
--- /dev/null
+++ b/params_shard_79.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f2c73885a78bc2b7c617cbcd9bc29a75d2ccf46277e25dbed777b46bda4e4e4
+size 141557760
diff --git a/params_shard_8.bin b/params_shard_8.bin
new file mode 100644
index 0000000000000000000000000000000000000000..080c72dbc3dc7211722039956ebdbdba6d5047f7
--- /dev/null
+++ b/params_shard_8.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06e10231559c664099fdfbb6e813cb6f6202a7baa6958d992672e9c0eba949c2
+size 70778880
diff --git a/params_shard_80.bin b/params_shard_80.bin
new file mode 100644
index 0000000000000000000000000000000000000000..9fb888199345dcad897f1a85457483827b4087b4
--- /dev/null
+++ b/params_shard_80.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab2ca73795346bad5baf1673798050f97b7a98d0fd6196a20e6358b9f40ca199
+size 70778880
diff --git a/params_shard_81.bin b/params_shard_81.bin
new file mode 100644
index 0000000000000000000000000000000000000000..2f12ef9bbed353c8efc586c5fff7a7aad75e8c1b
--- /dev/null
+++ b/params_shard_81.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74a0c821788464caaa992b5cf849e41395322289405d66e48fbbc630bc50c130
+size 32440320
diff --git a/params_shard_82.bin b/params_shard_82.bin
new file mode 100644
index 0000000000000000000000000000000000000000..17c8834cb1ceb1204e82f7a962e905fbf9082c01
--- /dev/null
+++ b/params_shard_82.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebc6018e3d9b9564848c2bf91c7925038b292970bf5fa1e358b923b763732c39
+size 29526016
diff --git a/params_shard_83.bin b/params_shard_83.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d98347e9e9ad4bd49b4d12bc8c716ec9feb656b8
--- /dev/null
+++ b/params_shard_83.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:993fb51d09b5d061f42e426eb237ea0f144b84dfad0613bfdacc1c91c5727585
+size 141557760
diff --git a/params_shard_84.bin b/params_shard_84.bin
new file mode 100644
index 0000000000000000000000000000000000000000..f989240ccd8d9f0263ffdf1b1e7a22050547425c
--- /dev/null
+++ b/params_shard_84.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b2e2098957cfeb694571d2d4284a168f44149d375a9d92a63a54ac04d8432cc
+size 70778880
diff --git a/params_shard_85.bin b/params_shard_85.bin
new file mode 100644
index 0000000000000000000000000000000000000000..cd4022604e96233bd00a5b863319ed5063166890
--- /dev/null
+++ b/params_shard_85.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8adbc2bcd2e2ae6f35b9fd9c079e97eef6eb35f7fa54501ace9617eeddf7e73f
+size 32440320
diff --git a/params_shard_86.bin b/params_shard_86.bin
new file mode 100644
index 0000000000000000000000000000000000000000..0340123b711d27877a446d7bda152639c63cd069
--- /dev/null
+++ b/params_shard_86.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:531766e5fdb638792fcc62f7753dcbda5dcc9e6f7d8bcc96898f2c1a95aa319a
+size 29526016
diff --git a/params_shard_87.bin b/params_shard_87.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b2fb4ef87e88c3b66f8803f722e1063cb8744317
--- /dev/null
+++ b/params_shard_87.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bc3b00025681fa6beffcbd58783a87476d70d64ddfccbaec983eb64291d20fc
+size 141557760
diff --git a/params_shard_88.bin b/params_shard_88.bin
new file mode 100644
index 0000000000000000000000000000000000000000..f43c240746b5dc23102309e437081f14b8d3e383
--- /dev/null
+++ b/params_shard_88.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18060bc999b7c2719fdd4a05add4466892b4c42b20b77b861a5d9ccc18d444b6
+size 70778880
diff --git a/params_shard_89.bin b/params_shard_89.bin
new file mode 100644
index 0000000000000000000000000000000000000000..1d0ed8d028d98d73fd97851f8a3ef6d6a574586d
--- /dev/null
+++ b/params_shard_89.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73a70aefebbab6c9ce7837f4bf13120f590e7fa40f510d154170773a9a4249a1
+size 32440320
diff --git a/params_shard_9.bin b/params_shard_9.bin
new file mode 100644
index 0000000000000000000000000000000000000000..de4c198bbe2d629c2639a1d4eb4b28e71c2db8ee
--- /dev/null
+++ b/params_shard_9.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3979d83235ceb66fd53f3d904cdac6b726b5033f46de17e0718972921c3edb5a
+size 32440320
diff --git a/params_shard_90.bin b/params_shard_90.bin
new file mode 100644
index 0000000000000000000000000000000000000000..917baa26db4e965881fdecdb94f8d6101ac213b7
--- /dev/null
+++ b/params_shard_90.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c1720d9706b3c854e751efebf3700f0c9ec5c04da71a6d81f4803081d57dc00
+size 29526016
diff --git a/params_shard_91.bin b/params_shard_91.bin
new file mode 100644
index 0000000000000000000000000000000000000000..5cf12daaf54437d3a0b93551c3fd77f960fc508d
--- /dev/null
+++ b/params_shard_91.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcc6f6f86476b75a2a6589cdb2eef41dc50f2ce2b2048fb34623c8a2eeb4697c
+size 141557760
diff --git a/params_shard_92.bin b/params_shard_92.bin
new file mode 100644
index 0000000000000000000000000000000000000000..66b0959bac011dec1944a8bd7f3f57bbb29813ff
--- /dev/null
+++ b/params_shard_92.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4e90f26e3bb8a7dba491c4e5b617408101921aedfadd927c1c02f732717876a
+size 70778880
diff --git a/params_shard_93.bin b/params_shard_93.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d688c557b6e61371a5191ff0329394d2f33fc53b
--- /dev/null
+++ b/params_shard_93.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fca9e7a4430e07f7c1e9f2378676b27f24f1b7e2eb5a964c3513741bd3c14c3
+size 32440320
diff --git a/params_shard_94.bin b/params_shard_94.bin
new file mode 100644
index 0000000000000000000000000000000000000000..7bc272c064c818e144c4c12c6308bfbd7535250d
--- /dev/null
+++ b/params_shard_94.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26324759971ca5667fd34c3f1399c4fbd7b72c0f6940ca516cf8f3ab0857c92b
+size 29526016
diff --git a/params_shard_95.bin b/params_shard_95.bin
new file mode 100644
index 0000000000000000000000000000000000000000..5e03759853f6a3e08b568a2269b0102094b43fe3
--- /dev/null
+++ b/params_shard_95.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b73613ece7a86948ebfe26c210e6d240fe882cd52478b9b3973656827f13419
+size 141557760
diff --git a/params_shard_96.bin b/params_shard_96.bin
new file mode 100644
index 0000000000000000000000000000000000000000..a335b344c44230ee30a0f2582c47913a7e5e0b98
--- /dev/null
+++ b/params_shard_96.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cc74e5db9f85ff246b9aeffc2536fbb6cf204aeb17c64ce0fc2961ba09baef2
+size 70778880
diff --git a/params_shard_97.bin b/params_shard_97.bin
new file mode 100644
index 0000000000000000000000000000000000000000..7119993ba5c54850fb15ae224f37e41108e3fbb9
--- /dev/null
+++ b/params_shard_97.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb6fbbdc176cdc6842bdf0e10ddea1eec00cc5c08420cefa0ee6e07163a0a846
+size 32440320
diff --git a/params_shard_98.bin b/params_shard_98.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c7ed5f9540fb35b6b084a61ff72c1d09b845222c
--- /dev/null
+++ b/params_shard_98.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b202694c7c721fedf35620b863f3bfd91f7f75010d35ae441006308b7b74895
+size 29526016
diff --git a/params_shard_99.bin b/params_shard_99.bin
new file mode 100644
index 0000000000000000000000000000000000000000..cc329c2b8e4402722aa3594750a1d28e02afc0ab
--- /dev/null
+++ b/params_shard_99.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c55347481e8a425628f0e40280bacfc08753f7cefbd1bd0ff4e1f2b624497517
+size 141557760
diff --git a/tokenizer.json b/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..a34650995da6939a945c330eadb0687147ac3ef8
--- /dev/null
+++ b/tokenizer.json
@@ -0,0 +1,303282 @@
+{
+ "version": "1.0",
+ "truncation": null,
+ "padding": null,
+ "added_tokens": [
+ {
+ "id": 151643,
+ "content": "<|end▁of▁sentence|>",
+ "single_word": false,
+ "lstrip": false,
+ "rstrip": false,
+ "normalized": false,
+ "special": true
+ },
+ {
+ "id": 151644,
+ "content": "<|User|>",
+ "single_word": false,
+ "lstrip": false,
+ "rstrip": false,
+ "normalized": false,
+ "special": false
+ },
+ {
+ "id": 151645,
+ "content": "<|Assistant|>",
+ "single_word": false,
+ "lstrip": false,
+ "rstrip": false,
+ "normalized": false,
+ "special": false
+ },
+ {
+ "id": 151646,
+ "content": "<|begin▁of▁sentence|>",
+ "normalized": false,
+ "lstrip": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ {
+ "id": 151647,
+ "content": "<|EOT|>",
+ "normalized": false,
+ "lstrip": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ {
+ "id": 151648,
+ "content": "
&": 5789, + "CON": 5790, + "Ġrepl": 5791, + "Ġregular": 5792, + "Storage": 5793, + "ramework": 5794, + "Ġgoal": 5795, + "Ġtouch": 5796, + ".widget": 5797, + "Ġbuilt": 5798, + "des": 5799, + "Part": 5800, + "(re": 5801, + "Ġworth": 5802, + "hib": 5803, + "game": 5804, + "Ġв": 5805, + "acion": 5806, + "ĠWhite": 5807, + "(type": 5808, + "(`": 5809, + "Ġnatural": 5810, + "Ġinj": 5811, + "Ġcalcul": 5812, + "ĠApril": 5813, + ".List": 5814, + "Ġassociated": 5815, + "ĉSystem": 5816, + "~~": 5817, + "=[": 5818, + "Ġstorage": 5819, + "Ġbytes": 5820, + "Ġtravel": 5821, + "Ġsou": 5822, + "Ġpassed": 5823, + "!=": 5824, + "ascript": 5825, + ".open": 5826, + "Ġgrid": 5827, + "Ġbus": 5828, + "Ġrecogn": 5829, + "Ab": 5830, + "Ġhon": 5831, + "ĠCenter": 5832, + "Ġprec": 5833, + "build": 5834, + "HTML": 5835, + "ĠSan": 5836, + "Ġcountries": 5837, + "aled": 5838, + "token": 5839, + "kt": 5840, + "Ġqual": 5841, + "Last": 5842, + "adow": 5843, + "Ġmanufact": 5844, + "idad": 5845, + "jango": 5846, + "Next": 5847, + "xf": 5848, + ".a": 5849, + "Ġporno": 5850, + "ĠPM": 5851, + "erve": 5852, + "iting": 5853, + "_th": 5854, + "ci": 5855, + "=None": 5856, + "gs": 5857, + "Ġlogin": 5858, + "atives": 5859, + "']);Ċ": 5860, + "Äħ": 5861, + "Ġill": 5862, + "IA": 5863, + "children": 5864, + "DO": 5865, + "Ġlevels": 5866, + "Ġ{{": 5867, + "Ġlooks": 5868, + "Ġ\"#": 5869, + "ToString": 5870, + "Ġnecessary": 5871, + "ĠĠĠĊ": 5872, + "cell": 5873, + "Entry": 5874, + "Ġ'#": 5875, + "Ġextrem": 5876, + "Selector": 5877, + "Ġplaceholder": 5878, + "Load": 5879, + "Ġreleased": 5880, + "ORE": 5881, + "Enumer": 5882, + "ĠTV": 5883, + "SET": 5884, + "inq": 5885, + "Press": 5886, + "ĠDepartment": 5887, + "Ġproperties": 5888, + "Ġrespond": 5889, + "Search": 5890, + "ael": 5891, + "Ġrequ": 5892, + "ĠBook": 5893, + "/Ċ": 5894, + "(st": 5895, + "Ġfinancial": 5896, + "icket": 5897, + "_input": 5898, + "Ġthreat": 5899, + "(in": 5900, + "Strip": 5901, + "ìĿ": 5902, + "ção": 5903, + "Ġevidence": 5904, + "));": 5905, + "ĠBro": 5906, + "Ġ[];Ċ": 5907, + "Ġou": 5908, + "buf": 5909, + "Script": 5910, + "dat": 5911, + "Ġrule": 5912, + "#import": 5913, + "=\"/": 5914, + "Serial": 5915, + "Ġstarting": 5916, + "[index": 5917, + "ae": 5918, + "Ġcontrib": 5919, + "session": 5920, + "_new": 5921, + "utable": 5922, + "ober": 5923, + "Ġ\"./": 5924, + "Ġlogger": 5925, + "Ġrecently": 5926, + "Ġreturned": 5927, + "ččĊ": 5928, + ")))Ċ": 5929, + "itions": 5930, + "Ġseek": 5931, + "Ġcommunic": 5932, + "Ġ\".": 5933, + "Ġusername": 5934, + "ECT": 5935, + "DS": 5936, + "Ġotherwise": 5937, + "ĠGerman": 5938, + ".aw": 5939, + "Adapter": 5940, + "ixel": 5941, + "Ġsystems": 5942, + "Ġdrop": 5943, + "Ġstructure": 5944, + "Ġ$(\"#": 5945, + "encies": 5946, + "anning": 5947, + "ĠLink": 5948, + "ĠResponse": 5949, + "Ġstri": 5950, + "ż": 5951, + "ĠDB": 5952, + "æĹ": 5953, + "android": 5954, + "submit": 5955, + "otion": 5956, + "(@": 5957, + ".test": 5958, + "ĊĊĊĊĊĊĊĊ": 5959, + "];čĊ": 5960, + "Ġdirectly": 5961, + "Ġ\"%": 5962, + "ris": 5963, + "elta": 5964, + "AIL": 5965, + "){čĊ": 5966, + "mine": 5967, + "ĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠ": 5968, + "(k": 5969, + "bon": 5970, + "asic": 5971, + "pite": 5972, + "___": 5973, + "Max": 5974, + "Ġerrors": 5975, + "ĠWhile": 5976, + "Ġarguments": 5977, + "Ġensure": 5978, + "Right": 5979, + "-based": 5980, + "Web": 5981, + "Ġ-=": 5982, + "Ġintrodu": 5983, + "ĠInst": 5984, + "ĠWash": 5985, + "ordin": 5986, + "join": 5987, + "Database": 5988, + "Ġgrad": 5989, + "Ġusually": 5990, + "ITE": 5991, + "Props": 5992, + "?>Ċ": 5993, + "ĠGo": 5994, + "@Override": 5995, + "REF": 5996, + "Ġip": 5997, + "ĠAustral": 5998, + "Ġist": 5999, + "ViewById": 6000, + "Ġserious": 6001, + "Ġcustomer": 6002, + ".prototype": 6003, + "odo": 6004, + "cor": 6005, + "Ġdoor": 6006, + "ĠWITHOUT": 6007, + "Ġplant": 6008, + "Ġbegan": 6009, + "Ġdistance": 6010, + "()).": 6011, + "Ġchance": 6012, + "Ġord": 6013, + "came": 6014, + "pragma": 6015, + "Ġprotect": 6016, + "ragment": 6017, + "ĠNode": 6018, + "ening": 6019, + "Ñĩ": 6020, + "Ġroute": 6021, + "ĠSchool": 6022, + "hi": 6023, + "Ġneighb": 6024, + "After": 6025, + "licit": 6026, + "Ġcontr": 6027, + "Ġprimary": 6028, + "AA": 6029, + ".WriteLine": 6030, + "utils": 6031, + "Ġbi": 6032, + "Red": 6033, + ".Linq": 6034, + ".object": 6035, + "Ġleaders": 6036, + "unities": 6037, + "Ġgun": 6038, + "onth": 6039, + "ĠDev": 6040, + "FILE": 6041, + "Ġcomments": 6042, + "_len": 6043, + "arrow": 6044, + "amount": 6045, + "Range": 6046, + "sert": 6047, + "GridView": 6048, + "Ġupdated": 6049, + "ĠMo": 6050, + "Ġinform": 6051, + "ociety": 6052, + "ala": 6053, + "Access": 6054, + "Ġhab": 6055, + "Ġcreat": 6056, + "_arg": 6057, + "ĠJanuary": 6058, + "ĠDay": 6059, + "\")čĊ": 6060, + "uple": 6061, + "document": 6062, + "gorith": 6063, + "menu": 6064, + "ĠOver": 6065, + "bb": 6066, + ".title": 6067, + "_out": 6068, + "Ġled": 6069, + "uri": 6070, + "Ġ?>": 6071, + "gl": 6072, + "Ġbank": 6073, + "ayment": 6074, + "ĉprintf": 6075, + "MD": 6076, + "Ġsample": 6077, + "Ġhands": 6078, + "ĠVersion": 6079, + "uario": 6080, + "Ġoffers": 6081, + "ityEngine": 6082, + "Ġshape": 6083, + "Ġsleep": 6084, + "_point": 6085, + "Settings": 6086, + "Ġachie": 6087, + "Ġsold": 6088, + "ota": 6089, + ".bind": 6090, + "Am": 6091, + "Ġsafe": 6092, + "Store": 6093, + "Ġshared": 6094, + "Ġpriv": 6095, + "_VAL": 6096, + "Ġsens": 6097, + "){": 6098, + "Ġremember": 6099, + "shared": 6100, + "element": 6101, + "Ġshoot": 6102, + "Vert": 6103, + "cout": 6104, + "Ġenv": 6105, + "_label": 6106, + "Ġ>Ċ": 6107, + "run": 6108, + "Ġscene": 6109, + "(array": 6110, + "device": 6111, + "_title": 6112, + "agon": 6113, + "]čĊ": 6114, + "aby": 6115, + "Ġbecame": 6116, + "boolean": 6117, + "Ġpark": 6118, + "ĠCode": 6119, + "upload": 6120, + "riday": 6121, + "ĠSeptember": 6122, + "Fe": 6123, + "Ġsen": 6124, + "cing": 6125, + "FL": 6126, + "Col": 6127, + "uts": 6128, + "_page": 6129, + "inn": 6130, + "Ġimplied": 6131, + "aling": 6132, + "Ġyourself": 6133, + ".Count": 6134, + "conf": 6135, + "Ġaud": 6136, + "_init": 6137, + ".)": 6138, + "Ġwrote": 6139, + "NG": 6140, + ".Error": 6141, + "ä»": 6142, + ".for": 6143, + "Ġequal": 6144, + "ĠRequest": 6145, + "Ġserial": 6146, + "Ġallows": 6147, + "XX": 6148, + "Ġmiddle": 6149, + "chor": 6150, + "ø": 6151, + "erval": 6152, + ".Column": 6153, + "reading": 6154, + "Ġescort": 6155, + "ĠAugust": 6156, + "Ġquickly": 6157, + "Ġweap": 6158, + "ĠCG": 6159, + "ropri": 6160, + "ho": 6161, + "Ġcop": 6162, + "(struct": 6163, + "ĠBig": 6164, + "Ġvs": 6165, + "Ġfrequ": 6166, + ".Value": 6167, + "Ġactions": 6168, + "Ġproper": 6169, + "Ġinn": 6170, + "Ġobjects": 6171, + "Ġmatrix": 6172, + "avascript": 6173, + "Ġones": 6174, + ".group": 6175, + "Ġgreen": 6176, + "Ġpaint": 6177, + "ools": 6178, + "ycl": 6179, + "encode": 6180, + "olt": 6181, + "comment": 6182, + ".api": 6183, + "Dir": 6184, + "Ġune": 6185, + "izont": 6186, + ".position": 6187, + "Ġdesigned": 6188, + "_val": 6189, + "avi": 6190, + "iring": 6191, + "tab": 6192, + "Ġlayer": 6193, + "Ġviews": 6194, + "Ġreve": 6195, + "rael": 6196, + "ĠON": 6197, + "rics": 6198, + "np": 6199, + "Ġcore": 6200, + "());čĊ": 6201, + "Main": 6202, + "Ġexpert": 6203, + "ĉĉčĊ": 6204, + "_en": 6205, + "Ġ/>": 6206, + "utter": 6207, + "IAL": 6208, + "ails": 6209, + "ĠKing": 6210, + "*/ĊĊ": 6211, + "ĠMet": 6212, + "_end": 6213, + "addr": 6214, + "ora": 6215, + "Ġir": 6216, + "Min": 6217, + "Ġsurpr": 6218, + "Ġrepe": 6219, + "Ġdirectory": 6220, + "PUT": 6221, + "-S": 6222, + "Ġelection": 6223, + "haps": 6224, + ".pre": 6225, + "cm": 6226, + "Values": 6227, + "Ġ\"Ċ": 6228, + "column": 6229, + "ivil": 6230, + "Login": 6231, + "inue": 6232, + "Ġbeautiful": 6233, + "Ġsecret": 6234, + "(event": 6235, + "Ġchat": 6236, + "ums": 6237, + "Ġorigin": 6238, + "Ġeffects": 6239, + "Ġmanagement": 6240, + "illa": 6241, + "tk": 6242, + "Ġsetting": 6243, + "ĠCour": 6244, + "Ġmassage": 6245, + "ĉend": 6246, + "Ġhappy": 6247, + "Ġfinish": 6248, + "Ġcamera": 6249, + "ĠVer": 6250, + "ĠDemocr": 6251, + "ĠHer": 6252, + "(Q": 6253, + "cons": 6254, + "ita": 6255, + "Ġ'.": 6256, + "{}": 6257, + "ĉC": 6258, + "Ġstuff": 6259, + "Ġ:Ċ": 6260, + "ĠAR": 6261, + "Task": 6262, + "hidden": 6263, + "eros": 6264, + "IGN": 6265, + "atio": 6266, + "ĠHealth": 6267, + "olute": 6268, + "Enter": 6269, + "'>": 6270, + "ĠTwitter": 6271, + "ĠCounty": 6272, + "scribe": 6273, + "Ġ=>Ċ": 6274, + "Ġhy": 6275, + "fit": 6276, + "Ġmilitary": 6277, + "Ġsale": 6278, + "required": 6279, + "non": 6280, + "bootstrap": 6281, + "hold": 6282, + "rim": 6283, + "-old": 6284, + "ĠDown": 6285, + "Ġmention": 6286, + "contact": 6287, + "_group": 6288, + "oday": 6289, + "Ġtown": 6290, + "Ġsolution": 6291, + "uate": 6292, + "elling": 6293, + "]->": 6294, + "otes": 6295, + "ental": 6296, + "omen": 6297, + "ospital": 6298, + "ĠSup": 6299, + "_EN": 6300, + "Ġslow": 6301, + "SESSION": 6302, + "Ġblue": 6303, + "ago": 6304, + "Ġlives": 6305, + "Ġ^": 6306, + ".un": 6307, + "inst": 6308, + "enge": 6309, + "Ġcustomers": 6310, + "Ġcast": 6311, + "udget": 6312, + "ï¼ģ": 6313, + "icens": 6314, + "Ġdetermin": 6315, + "Selected": 6316, + "_pl": 6317, + "ueue": 6318, + "Ġdark": 6319, + "//ĊĊ": 6320, + "si": 6321, + "thern": 6322, + "ĠJapan": 6323, + "/w": 6324, + "PU": 6325, + "ĠEast": 6326, + "ovie": 6327, + "Ġpackage": 6328, + "Ġnor": 6329, + "Ġapi": 6330, + "bot": 6331, + "\"];Ċ": 6332, + "_post": 6333, + "ulate": 6334, + "Ġclub": 6335, + "'));Ċ": 6336, + "Ġloop": 6337, + "PIO": 6338, + "ione": 6339, + "shot": 6340, + "Initial": 6341, + "Ġplayed": 6342, + "register": 6343, + "rought": 6344, + "_max": 6345, + "acement": 6346, + "match": 6347, + "raphics": 6348, + "AST": 6349, + "Ġexisting": 6350, + "Ġcomplex": 6351, + "DA": 6352, + ".Ch": 6353, + ".common": 6354, + "mo": 6355, + "Ġ'../../": 6356, + "ito": 6357, + "Ġanalysis": 6358, + "Ġdeliver": 6359, + "ĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĊ": 6360, + "idx": 6361, + "Ãł": 6362, + "ongo": 6363, + "ĠEnglish": 6364, + "Ċ": 9992, + "_default": 9993, + "ĠDatabase": 9994, + "rep": 9995, + "ESS": 9996, + "nergy": 9997, + ".Find": 9998, + "_mask": 9999, + "Ġrise": 10000, + "Ġkernel": 10001, + "::$": 10002, + ".Q": 10003, + "Ġoffering": 10004, + "decl": 10005, + "ĠCS": 10006, + "Ġlisted": 10007, + "Ġmostly": 10008, + "enger": 10009, + "Ġblocks": 10010, + "olo": 10011, + "Ġgoverning": 10012, + "\\F": 10013, + "Ġconcent": 10014, + ".getText": 10015, + "Ġmb": 10016, + "Ġoccurred": 10017, + "Ġchanging": 10018, + "Scene": 10019, + "_CODE": 10020, + "Beh": 10021, + "\"The": 10022, + "Ġtile": 10023, + "ĠAssociation": 10024, + "ĉP": 10025, + "alty": 10026, + "_ad": 10027, + "odies": 10028, + "iated": 10029, + "Ġprepared": 10030, + "possible": 10031, + "Ġmort": 10032, + "TEST": 10033, + "Ġignore": 10034, + "Ġcalc": 10035, + "Ġrs": 10036, + "ĠassertEquals": 10037, + "Ġsz": 10038, + "ĠTHIS": 10039, + ".\"Ċ": 10040, + "Ġcanvas": 10041, + "java": 10042, + "Ġdut": 10043, + "VALID": 10044, + ".sql": 10045, + ".input": 10046, + "Ġaux": 10047, + "Sup": 10048, + "Ġartist": 10049, + "Vec": 10050, + "_TIME": 10051, + ".stringify": 10052, + "etween": 10053, + "ĠCategory": 10054, + "Ġ[-": 10055, + "ĠDevExpress": 10056, + "ĠJul": 10057, + "Ġring": 10058, + ".ed": 10059, + "YY": 10060, + "Let": 10061, + "TextField": 10062, + "Ġflat": 10063, + "_print": 10064, + "ĠOTHER": 10065, + "adian": 10066, + "Ġchecked": 10067, + "ele": 10068, + "Align": 10069, + "standing": 10070, + "Ġ[],": 10071, + "Ġlab": 10072, + "ucky": 10073, + "ĠChristmas": 10074, + "(image": 10075, + ".module": 10076, + "Ġlots": 10077, + "Ġslightly": 10078, + "(final": 10079, + "erge": 10080, + "è¿": 10081, + "ĠPolice": 10082, + "ĠRight": 10083, + "Ġaward": 10084, + "ĠOS": 10085, + "Ġ{}ĊĊ": 10086, + "Ġptr": 10087, + "oves": 10088, + "icated": 10089, + "ем": 10090, + "Ġmanage": 10091, + "oliday": 10092, + "Amount": 10093, + "oolStrip": 10094, + "tbody": 10095, + "Nav": 10096, + "wrap": 10097, + "BB": 10098, + "Ġwatching": 10099, + "arios": 10100, + "Ġoptional": 10101, + "_K": 10102, + "ĠLicensed": 10103, + ".Map": 10104, + "Timer": 10105, + "ĠAP": 10106, + "ĠRev": 10107, + "(o": 10108, + ",c": 10109, + "umin": 10110, + "etailed": 10111, + "ĠHy": 10112, + "Ġblank": 10113, + "agger": 10114, + "ĠSelf": 10115, + "()[": 10116, + ".make": 10117, + "earn": 10118, + "channel": 10119, + ";Ċ": 10133, + "World": 10134, + "Ġpython": 10135, + "Ġlif": 10136, + "Ġtrav": 10137, + "Ġconven": 10138, + "company": 10139, + "ĠClub": 10140, + "Ver": 10141, + "Btn": 10142, + "Ġzone": 10143, + "products": 10144, + "ĠEduc": 10145, + "Ġverify": 10146, + "ĠMil": 10147, + "ono": 10148, + "]);ĊĊ": 10149, + "ENCE": 10150, + "Ġpacket": 10151, + "Ġcer": 10152, + "Ġenumer": 10153, + "Ġpars": 10154, + "formed": 10155, + "Ġoccup": 10156, + "tre": 10157, + "Ġexercise": 10158, + "Day": 10159, + "_sum": 10160, + "Ġasking": 10161, + "aption": 10162, + "Ġorders": 10163, + "Ġspending": 10164, + "ĠERR": 10165, + ".Dis": 10166, + "ĠUtil": 10167, + "âĢľI": 10168, + "\\'": 10169, + "?)": 10170, + "/>Ċ": 10171, + "Ġemot": 10172, + "Ġinfluence": 10173, + "ĠAfrica": 10174, + "atters": 10175, + "Ùħ": 10176, + ".session": 10177, + "Ġchief": 10178, + "ĉĉĉĉĉĉĉĉĉĉĉ": 10179, + "Ġtom": 10180, + "cluded": 10181, + "serial": 10182, + "_handler": 10183, + ".Type": 10184, + "aped": 10185, + "Ġpolicies": 10186, + "-ex": 10187, + "-tr": 10188, + "blank": 10189, + "merce": 10190, + "Ġcoverage": 10191, + "Ġrc": 10192, + "_matrix": 10193, + "_box": 10194, + "Ġcharges": 10195, + "ĠBoston": 10196, + "Pe": 10197, + "Ġcircum": 10198, + "Ġfilled": 10199, + "Ġnorth": 10200, + "ictureBox": 10201, + "ĉres": 10202, + "è®": 10203, + "Ġtermin": 10204, + "Ġ[âĢ¦": 10205, + "IRECT": 10206, + "Ġber": 10207, + "Ġ\"../../": 10208, + "retch": 10209, + ".code": 10210, + "_col": 10211, + "ĠGovernment": 10212, + "Ġargv": 10213, + "ĠLord": 10214, + "asi": 10215, + "Exec": 10216, + "ĉlet": 10217, + "vertis": 10218, + "Ġdiscussion": 10219, + "enance": 10220, + "outube": 10221, + "typeof": 10222, + "Ġserved": 10223, + "ĠPut": 10224, + "ĉx": 10225, + "Ġsweet": 10226, + "Before": 10227, + "ategy": 10228, + ".of": 10229, + "ĠMaterial": 10230, + "Sort": 10231, + "ONT": 10232, + "igital": 10233, + "Why": 10234, + "Ġsust": 10235, + "Ġç": 10236, + "abet": 10237, + "Ġsegment": 10238, + "Ġ[],Ċ": 10239, + "ĠMuslim": 10240, + "ĠfindViewById": 10241, + "cut": 10242, + "_TEXT": 10243, + "ĠMary": 10244, + "Ġloved": 10245, + "Ġlie": 10246, + "ĠJO": 10247, + "Ġisset": 10248, + "month": 10249, + "Ġprime": 10250, + "ti": 10251, + "ĠCarol": 10252, + "Use": 10253, + "ĠPop": 10254, + "ĠSave": 10255, + "Interval": 10256, + "execute": 10257, + "dy": 10258, + "ĠIran": 10259, + "_cont": 10260, + "ĉT": 10261, + "Ġphase": 10262, + "checkbox": 10263, + "week": 10264, + "Ġhide": 10265, + "Ġtil": 10266, + "Ġju": 10267, + "Custom": 10268, + "burg": 10269, + "/M": 10270, + "TON": 10271, + "Ġquant": 10272, + "Ġrub": 10273, + "ixels": 10274, + "Ġinstalled": 10275, + "Ġdump": 10276, + "Ġproperly": 10277, + "(List": 10278, + "Ġdecide": 10279, + "apply": 10280, + "Has": 10281, + "Ġkeeping": 10282, + "Ġcitizens": 10283, + "Ġjoint": 10284, + "pool": 10285, + "Socket": 10286, + "_op": 10287, + "Ġweapon": 10288, + "gnore": 10289, + "ĠExec": 10290, + "otten": 10291, + "ĠMS": 10292, + "Ġ(-": 10293, + "ĠReview": 10294, + "Ġexamples": 10295, + "Ġtight": 10296, + "!(": 10297, + "DP": 10298, + "ĠMessageBox": 10299, + "Ġphotograph": 10300, + "URI": 10301, + "ét": 10302, + "low": 10303, + "ĠGrand": 10304, + ".persistence": 10305, + "Ġmaintain": 10306, + "Ġnums": 10307, + "Ġzip": 10308, + "ials": 10309, + "ĠGets": 10310, + "peg": 10311, + "ĠBuffer": 10312, + "~~~~": 10313, + "rastructure": 10314, + "ĠPL": 10315, + "uen": 10316, + "obby": 10317, + "sizeof": 10318, + "Ġpic": 10319, + "Ġseed": 10320, + "Ġexperienced": 10321, + "Ġodd": 10322, + "Ġkick": 10323, + "Ġprocedure": 10324, + "avigator": 10325, + "-on": 10326, + ",j": 10327, + "ĠAlthough": 10328, + "ĠuserId": 10329, + "accept": 10330, + "Blue": 10331, + "IColor": 10332, + "layer": 10333, + "available": 10334, + "Ġends": 10335, + ".table": 10336, + "Ġdataset": 10337, + "bus": 10338, + "Ġexplain": 10339, + "(pro": 10340, + "ĠCommittee": 10341, + "Ġnoted": 10342, + "]:Ċ": 10343, + "Dim": 10344, + "stdio": 10345, + ".\",Ċ": 10346, + "_source": 10347, + "ĠWeek": 10348, + "ĠEdge": 10349, + "Ġoperating": 10350, + "Ġeste": 10351, + "ipl": 10352, + "agination": 10353, + "Ġproceed": 10354, + "Ġanimation": 10355, + ".Models": 10356, + "ĠWatch": 10357, + "iat": 10358, + "Ġoppon": 10359, + "/A": 10360, + "Report": 10361, + "Ġsounds": 10362, + "_buf": 10363, + "IELD": 10364, + "Ġbund": 10365, + "ĉget": 10366, + ".pr": 10367, + "(tmp": 10368, + "Ġkid": 10369, + ">ĊĊĊ": 10370, + "Ġyang": 10371, + "NotFound": 10372, + "ÑĨ": 10373, + "math": 10374, + "@gmail": 10375, + "ĠLIMIT": 10376, + "redients": 10377, + "Ġvent": 10378, + "avigate": 10379, + "Look": 10380, + "Ġreligious": 10381, + "Ġrand": 10382, + "rio": 10383, + "(GL": 10384, + "_ip": 10385, + "uan": 10386, + "iciency": 10387, + "ĠChange": 10388, + ">čĊčĊ": 10389, + "ĠEntity": 10390, + "Ġrencontre": 10391, + "ĠRet": 10392, + "plan": 10393, + "én": 10394, + "BOOL": 10395, + "uries": 10396, + "train": 10397, + "Definition": 10398, + "============": 10399, + "zz": 10400, + "Animation": 10401, + "ĠOK": 10402, + "_menu": 10403, + ".bl": 10404, + "_score": 10405, + "Ġacad": 10406, + "(System": 10407, + "Ġrefresh": 10408, + "'=>$": 10409, + ".Graphics": 10410, + "amento": 10411, + "pid": 10412, + "tc": 10413, + "Ġtips": 10414, + "Ġhomes": 10415, + "Ġfuel": 10416, + "âĸ": 10417, + "_helper": 10418, + "ĠĠčĊ": 10419, + "ĠRoom": 10420, + ".Close": 10421, + "_attr": 10422, + "ĠMount": 10423, + "ĠEv": 10424, + "arser": 10425, + "_top": 10426, + "eah": 10427, + "ĠDelete": 10428, + "ãĢį": 10429, + "uke": 10430, + "Ġusage": 10431, + "aria": 10432, + "_dev": 10433, + "Ġtexture": 10434, + "Ġconversation": 10435, + "eper": 10436, + "Bean": 10437, + "done": 10438, + "nonatomic": 10439, + "ĠSecond": 10440, + "Ġshooting": 10441, + "_pre": 10442, + "Components": 10443, + "Ġ]ĊĊ": 10444, + "__,": 10445, + "stitution": 10446, + ".Char": 10447, + ">();ĊĊ": 10448, + "Ġpresented": 10449, + "Ġwa": 10450, + "oker": 10451, + "-ĊĊ": 10452, + "iner": 10453, + "Ġbecoming": 10454, + "Ġincident": 10455, + "Att": 10456, + "Ġrevealed": 10457, + "forc": 10458, + "Ġboot": 10459, + ".page": 10460, + "Enumerator": 10461, + "_->": 10462, + "Photo": 10463, + "Ġspring": 10464, + ".\",": 10465, + "ĠDictionary": 10466, + "BJECT": 10467, + "Ġlocations": 10468, + "Ġsamples": 10469, + "InputStream": 10470, + "ĠBrown": 10471, + "Ġstats": 10472, + "quality": 10473, + "Ñħ": 10474, + "-dis": 10475, + "Ġhelping": 10476, + "Ġped": 10477, + "(se": 10478, + "ĠWho": 10479, + "alian": 10480, + "internal": 10481, + "Ġft": 10482, + ">().": 10483, + "->{": 10484, + "Ġmine": 10485, + "Ġsector": 10486, + "Ġgro": 10487, + "Ġopportunities": 10488, + "Ġü": 10489, + "Ġmp": 10490, + "Ġalleged": 10491, + "Ġdoubt": 10492, + "Mouse": 10493, + "About": 10494, + "_part": 10495, + "Ġchair": 10496, + "Ġstopped": 10497, + "loop": 10498, + "entities": 10499, + "Ġapps": 10500, + "ansion": 10501, + "Ġmental": 10502, + "ĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠ": 10503, + "FR": 10504, + "Ġdefend": 10505, + "care": 10506, + "Ġideal": 10507, + "/api": 10508, + "urface": 10509, + "Ġele": 10510, + "ulator": 10511, + "ĠRights": 10512, + "anguages": 10513, + "Ġfunds": 10514, + "Ġadapt": 10515, + "Attributes": 10516, + "Ġdeploy": 10517, + "opts": 10518, + "Ġvalidation": 10519, + "Ġconcerns": 10520, + "uce": 10521, + ".num": 10522, + "ulture": 10523, + "ila": 10524, + "Ġcup": 10525, + "Ġpure": 10526, + ".Fore": 10527, + "ĠHashMap": 10528, + ".valueOf": 10529, + "asm": 10530, + "MO": 10531, + "Ġcs": 10532, + "Ġstores": 10533, + "Ġ************************************************************************": 10534, + "Ġcommunication": 10535, + "mem": 10536, + ".EventHandler": 10537, + ".Status": 10538, + "_right": 10539, + ".setOn": 10540, + "Sheet": 10541, + "Ġidentify": 10542, + "enerated": 10543, + "ordered": 10544, + "Ġ\"[": 10545, + "Ġswe": 10546, + "Condition": 10547, + "ĠAccording": 10548, + "Ġprepare": 10549, + "Ġrob": 10550, + "Pool": 10551, + "Ġsport": 10552, + "rv": 10553, + "ĠRouter": 10554, + "Ġalternative": 10555, + "([]": 10556, + "ĠChicago": 10557, + "ipher": 10558, + "ische": 10559, + "ĠDirector": 10560, + "kl": 10561, + "ĠWil": 10562, + "keys": 10563, + "Ġmysql": 10564, + "Ġwelcome": 10565, + "king": 10566, + "ĠManager": 10567, + "Ġcaught": 10568, + ")}Ċ": 10569, + "Score": 10570, + "_PR": 10571, + "Ġsurvey": 10572, + "hab": 10573, + "Headers": 10574, + "ADER": 10575, + "Ġdecor": 10576, + "Ġturns": 10577, + "Ġradius": 10578, + "errupt": 10579, + "Cor": 10580, + "Ġmel": 10581, + "Ġintr": 10582, + "(q": 10583, + "ĠAC": 10584, + "amos": 10585, + "MAX": 10586, + "ĠGrid": 10587, + "ĠJesus": 10588, + "ĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠ": 10589, + ".DE": 10590, + "Ġts": 10591, + "Ġlinked": 10592, + "free": 10593, + "ĠQt": 10594, + "Ġ/**čĊ": 10595, + "Ġfaster": 10596, + "ctr": 10597, + "_J": 10598, + "DT": 10599, + ".Check": 10600, + "Ġcombination": 10601, + "Ġintended": 10602, + "-the": 10603, + "-type": 10604, + "ectors": 10605, + "ami": 10606, + "uting": 10607, + "Ġuma": 10608, + "XML": 10609, + "UCT": 10610, + "Ap": 10611, + "ĠRandom": 10612, + "Ġran": 10613, + ".sort": 10614, + "Ġsorted": 10615, + ".Un": 10616, + "_PER": 10617, + "itory": 10618, + "Ġpriority": 10619, + "ĠGal": 10620, + "ĠOld": 10621, + "hot": 10622, + "ĠDisplay": 10623, + "(sub": 10624, + "_TH": 10625, + "_Y": 10626, + "ĠCare": 10627, + "loading": 10628, + "Kind": 10629, + "_handle": 10630, + ",,": 10631, + "rase": 10632, + "_replace": 10633, + ".addEventListener": 10634, + "ĠRT": 10635, + "Ġentered": 10636, + "gers": 10637, + "Ġich": 10638, + "(start": 10639, + "/app": 10640, + "Ġbrother": 10641, + "Memory": 10642, + "Outlet": 10643, + "Ġutf": 10644, + "prec": 10645, + "Ġnavigation": 10646, + "ORK": 10647, + "Ġdst": 10648, + "Detail": 10649, + "Ġaudience": 10650, + "Ġdur": 10651, + "Ġcluster": 10652, + "unched": 10653, + "Ġ],": 10654, + "Ġcomfortable": 10655, + ".values": 10656, + "ĠTotal": 10657, + "Ġsnap": 10658, + "Ġstandards": 10659, + "Ġperformed": 10660, + "hand": 10661, + "(\"@": 10662, + "åŃ": 10663, + "Ġphil": 10664, + "ibr": 10665, + "trim": 10666, + "Ġforget": 10667, + "Ġdoctor": 10668, + ".TextBox": 10669, + "icons": 10670, + ",s": 10671, + "ĠOp": 10672, + "Sm": 10673, + "Stop": 10674, + "ĉList": 10675, + "ĉu": 10676, + "Comment": 10677, + "_VERSION": 10678, + ".Xtra": 10679, + "Person": 10680, + "rb": 10681, + "LOB": 10682, + "ĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĊ": 10683, + "ĠCentral": 10684, + "ICK": 10685, + "raq": 10686, + "Ġputting": 10687, + "Ġmd": 10688, + "ĠLove": 10689, + "Program": 10690, + "Border": 10691, + "oor": 10692, + "Ġallowing": 10693, + "after": 10694, + "Ġentries": 10695, + "ĠMaybe": 10696, + "]).": 10697, + "ĠShort": 10698, + ")\\": 10699, + ".now": 10700, + "friend": 10701, + "Ġprefer": 10702, + "ĠGPIO": 10703, + "osis": 10704, + "ĠGameObject": 10705, + "Ġskip": 10706, + "Ġcompetition": 10707, + "_match": 10708, + "lications": 10709, + "_CONT": 10710, + ".groupBox": 10711, + "Ġals": 10712, + "\"We": 10713, + "_eq": 10714, + "lan": 10715, + "_search": 10716, + "ĠMusic": 10717, + "asis": 10718, + "Ġbind": 10719, + "ĠIsland": 10720, + "rum": 10721, + "(E": 10722, + "Ġseat": 10723, + "Video": 10724, + "Ġack": 10725, + "reek": 10726, + "={()": 10727, + "Ġrating": 10728, + "Ġrestaurant": 10729, + "DEX": 10730, + "(buf": 10731, + "pping": 10732, + "uality": 10733, + "Ġleague": 10734, + "Ġfocused": 10735, + "apon": 10736, + "$data": 10737, + "CLUD": 10738, + "CLUDING": 10739, + "Ġabsolute": 10740, + "(query": 10741, + "Ġtells": 10742, + "Ang": 10743, + "Ġcommunities": 10744, + "Ġhonest": 10745, + "oking": 10746, + "Ġapart": 10747, + "arity": 10748, + "/$": 10749, + "_module": 10750, + "ĠEnc": 10751, + ".an": 10752, + ".Config": 10753, + "Cre": 10754, + "Ġshock": 10755, + "ĠArab": 10756, + "IENT": 10757, + "/re": 10758, + "Ġretrie": 10759, + "ycler": 10760, + "isa": 10761, + "ĠOrgan": 10762, + ".graph": 10763, + "Ġí": 10764, + "ĠBAS": 10765, + "Enum": 10766, + "Ġpossibly": 10767, + "ÑĢаÐ": 10768, + "ĠJapanese": 10769, + "Ġcraft": 10770, + "ĠPlace": 10771, + "Ġtalent": 10772, + "Ġfunding": 10773, + "Ġconfirmed": 10774, + "Ġcycle": 10775, + "/x": 10776, + "GE": 10777, + "Ġhearing": 10778, + "Ġplants": 10779, + "Ġmouth": 10780, + "pages": 10781, + "oria": 10782, + "ĠRemove": 10783, + "_total": 10784, + "Ġod": 10785, + "ollapse": 10786, + "door": 10787, + "Ġbought": 10788, + "Ġaddr": 10789, + "ARCH": 10790, + "_dim": 10791, + "dden": 10792, + "Ġdecades": 10793, + "REQUEST": 10794, + "Ġversions": 10795, + "fire": 10796, + "Ġmoves": 10797, + "fb": 10798, + "Ġcoffee": 10799, + ".connect": 10800, + "ĠRow": 10801, + "Ġschema": 10802, + "Scope": 10803, + "-Type": 10804, + "Ġfighting": 10805, + "Ġretail": 10806, + "Ġmodified": 10807, + "TF": 10808, + "Files": 10809, + "nie": 10810, + "_command": 10811, + "stone": 10812, + "ĠÑĤ": 10813, + "_thread": 10814, + "Ġbond": 10815, + "ĠDevelopment": 10816, + "Ġpt": 10817, + "FORM": 10818, + "plet": 10819, + "Ġidentified": 10820, + "cpp": 10821, + "Ġcoding": 10822, + "oked": 10823, + "ĠMaster": 10824, + "IDTH": 10825, + "Ġresidents": 10826, + "redit": 10827, + "ĠPhoto": 10828, + "=-": 10829, + "unte": 10830, + "ateur": 10831, + "_STATE": 10832, + "ĠSing": 10833, + "Ġsheet": 10834, + ".val": 10835, + "orse": 10836, + "Ġhers": 10837, + "Ġdetermined": 10838, + "Common": 10839, + "Ġwed": 10840, + "_queue": 10841, + "PH": 10842, + "ĠAtl": 10843, + "cred": 10844, + "/LICENSE": 10845, + "Ġmes": 10846, + "Ġadvanced": 10847, + ".java": 10848, + ".Sh": 10849, + "Go": 10850, + "kill": 10851, + "fp": 10852, + "_settings": 10853, + "Ġpal": 10854, + "Ġtruck": 10855, + "Ġcombined": 10856, + "Ġ\"${": 10857, + "ĠCorpor": 10858, + "Ġjoined": 10859, + "ĠJose": 10860, + "ĠCup": 10861, + "uns": 10862, + "estival": 10863, + "levision": 10864, + "Ġbroken": 10865, + "Ġmarriage": 10866, + "ĠWestern": 10867, + "Ġrepresents": 10868, + "ĠTitle": 10869, + "Ġss": 10870, + ".Ass": 10871, + "ongoose": 10872, + "iento": 10873, + "<>();Ċ": 10874, + "Ġabsolutely": 10875, + "Ġsmooth": 10876, + "TERN": 10877, + "ĠUnless": 10878, + "Word": 10879, + "Ġmerge": 10880, + "igan": 10881, + "ĠVol": 10882, + "Ġnn": 10883, + ".getId": 10884, + "Ġз": 10885, + "Ġsexy": 10886, + "Ġseeking": 10887, + "Single": 10888, + ".this": 10889, + "Ġkom": 10890, + "bound": 10891, + ";\"": 10892, + "ĠfontSize": 10893, + "_df": 10894, + "Ġinjury": 10895, + "(H": 10896, + "Ġissued": 10897, + "_END": 10898, + ":self": 10899, + "Ġpatch": 10900, + "Ġleaves": 10901, + "Ġadopt": 10902, + "FileName": 10903, + "ãĢIJ": 10904, + "Ġexecutive": 10905, + "ĠByte": 10906, + "]))Ċ": 10907, + "Ġnu": 10908, + "outing": 10909, + "cluding": 10910, + "-R": 10911, + ".options": 10912, + "Ġsubstant": 10913, + "avax": 10914, + "ĠBUT": 10915, + "Ġtechnical": 10916, + "Ġtwice": 10917, + "Ġmás": 10918, + "Ġunivers": 10919, + "yr": 10920, + "Ġdrag": 10921, + "ĠDC": 10922, + "Ġsed": 10923, + "Ġbot": 10924, + "ĠPal": 10925, + "ĠHall": 10926, + "forcement": 10927, + "Ġauch": 10928, + ".mod": 10929, + "notation": 10930, + "_files": 10931, + ".line": 10932, + "_flag": 10933, + "[name": 10934, + "Ġresolution": 10935, + "Ġbott": 10936, + "(\"[": 10937, + "ende": 10938, + "(arr": 10939, + "Free": 10940, + "(@\"": 10941, + "ĠDistrict": 10942, + "PEC": 10943, + ":-": 10944, + "Picker": 10945, + "ĠJo": 10946, + "ĠĠĠĠĠĊ": 10947, + "ĠRiver": 10948, + "_rows": 10949, + "Ġhelpful": 10950, + "Ġmassive": 10951, + "---Ċ": 10952, + "Ġmeasures": 10953, + "ĠRuntime": 10954, + "Ġworry": 10955, + "ĠSpec": 10956, + "ĉD": 10957, + "ãĢij": 10958, + "Ġ){Ċ": 10959, + "Ġworse": 10960, + "(filename": 10961, + "Ġlay": 10962, + "Ġmagic": 10963, + "ĠTheir": 10964, + "oul": 10965, + "stroy": 10966, + "ĠWhere": 10967, + "Ġsudden": 10968, + "Ġdefe": 10969, + "Ġbinding": 10970, + "Ġflight": 10971, + "ĠOnInit": 10972, + "ĠWomen": 10973, + "ĠPolicy": 10974, + "Ġdrugs": 10975, + "ishing": 10976, + "('../": 10977, + "ĠMel": 10978, + "peat": 10979, + "tor": 10980, + "Ġproposed": 10981, + "Ġstated": 10982, + "_RES": 10983, + "Ġeast": 10984, + "ĠCONDITION": 10985, + "_desc": 10986, + "Ġwinning": 10987, + "folio": 10988, + "Mapper": 10989, + "ĠPan": 10990, + "ĠAnge": 10991, + ".servlet": 10992, + "Ġcopies": 10993, + "LM": 10994, + "Ġvm": 10995, + "åį": 10996, + "Ġdictionary": 10997, + "Seg": 10998, + "elines": 10999, + "ĠSend": 11000, + "Ġiron": 11001, + "ĠFort": 11002, + ".domain": 11003, + "Ġdebate": 11004, + "NotNull": 11005, + "eq": 11006, + "acher": 11007, + "lf": 11008, + "ĉfmt": 11009, + "Ġlawy": 11010, + "ÄŁ": 11011, + "ĠMen": 11012, + "Ġtrim": 11013, + "(NULL": 11014, + "Ġ!!": 11015, + "Ġpad": 11016, + "Ġfollows": 11017, + "\"][\"": 11018, + "requ": 11019, + "ĠEp": 11020, + ".github": 11021, + "(img": 11022, + "eto": 11023, + "('\\": 11024, + "Services": 11025, + "umbnail": 11026, + "_main": 11027, + "pleted": 11028, + "fortunately": 11029, + "Ġwindows": 11030, + "Ġplane": 11031, + "ĠConnection": 11032, + ".local": 11033, + "uard": 11034, + "}\\": 11035, + "==\"": 11036, + "andon": 11037, + "ĠRoy": 11038, + "west": 11039, + "iginal": 11040, + "emies": 11041, + "itz": 11042, + "'):Ċ": 11043, + "ĠPeter": 11044, + "Ġtough": 11045, + "Ġreduced": 11046, + "Ġcalculate": 11047, + "Ġrapid": 11048, + "customer": 11049, + "Ġefficient": 11050, + "Ġmedium": 11051, + "Ġfell": 11052, + ".ref": 11053, + "ĠCas": 11054, + "Ġfeedback": 11055, + "Speed": 11056, + "(output": 11057, + "aje": 11058, + "Ġcategories": 11059, + "Ġfee": 11060, + "};": 11061, + "Ġdeleted": 11062, + "reh": 11063, + "Ġproof": 11064, + "Desc": 11065, + "Build": 11066, + "Ġsides": 11067, + ".ArrayList": 11068, + "-%": 11069, + "ĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠ": 11070, + "ر": 11071, + ".match": 11072, + "ли": 11073, + "Ġfeels": 11074, + "Ġachieve": 11075, + "Ġclim": 11076, + "_ON": 11077, + "ĠCD": 11078, + "Ġteacher": 11079, + "_current": 11080, + "bn": 11081, + "_PL": 11082, + "isting": 11083, + "Enable": 11084, + "GEN": 11085, + "Ġtv": 11086, + "Ġsock": 11087, + "Ġplays": 11088, + "Ġdiscount": 11089, + "ĠKE": 11090, + "ĠDebug": 11091, + "Fore": 11092, + "ĠIraq": 11093, + "Ġappearance": 11094, + "Mon": 11095, + "Ġstyled": 11096, + "ĠHuman": 11097, + "iot": 11098, + "ĠHistory": 11099, + "Ġsac": 11100, + "ĠCollection": 11101, + "Ġrecommended": 11102, + ".Selected": 11103, + "Ġorganizations": 11104, + "Ġdiscovered": 11105, + "cohol": 11106, + "adas": 11107, + "ĠThomas": 11108, + "May": 11109, + "Ġconserv": 11110, + "Ġdomin": 11111, + "ĠFollow": 11112, + "ĠSection": 11113, + "ĠThanks": 11114, + "Username": 11115, + "Ġrecipe": 11116, + "Ġwonderful": 11117, + ".sleep": 11118, + "_if": 11119, + "ĉĊĉĊ": 11120, + "orno": 11121, + "Ġru": 11122, + "_target": 11123, + ".\"\"": 11124, + "à¦": 11125, + "EventArgs": 11126, + "Ġinputs": 11127, + "Ġfif": 11128, + "Ġvision": 11129, + "cy": 11130, + "ĠSeries": 11131, + ")(((": 11132, + "Ġtrading": 11133, + "Ġmarker": 11134, + "Begin": 11135, + "Ġtypically": 11136, + "Ġcauses": 11137, + "dropdown": 11138, + "_DEBUG": 11139, + "Ġdetect": 11140, + "country": 11141, + "!\");Ċ": 11142, + "ĉR": 11143, + "appy": 11144, + "Ġcref": 11145, + "('<": 11146, + "\"=>": 11147, + "ĠLE": 11148, + "reader": 11149, + "Ġadministr": 11150, + "õ": 11151, + "ucket": 11152, + "Ġfashion": 11153, + ".char": 11154, + "izar": 11155, + "Ġdisable": 11156, + "Ġsuc": 11157, + "ĠLive": 11158, + "issue": 11159, + "Ġmetadata": 11160, + "flags": 11161, + "ĠðŁ": 11162, + "Ġcommitted": 11163, + "Ġva": 11164, + "Ġrough": 11165, + "Ġ'''Ċ": 11166, + "Ġhighlight": 11167, + "_vars": 11168, + "VO": 11169, + "Ġencoding": 11170, + "-Z": 11171, + "_sign": 11172, + "$(\"#": 11173, + "Ġrain": 11174, + "reatest": 11175, + "ĠEND": 11176, + "Selection": 11177, + "Ġcandidates": 11178, + "Ġsav": 11179, + ".Empty": 11180, + "Ġdecisions": 11181, + "Ġcollabor": 11182, + "ridge": 11183, + "feed": 11184, + "ression": 11185, + "Ġpersons": 11186, + "VM": 11187, + "ega": 11188, + "_BIT": 11189, + "According": 11190, + "acked": 11191, + "Ġdollars": 11192, + "_loss": 11193, + "ĠCost": 11194, + "}\"Ċ": 11195, + "Notification": 11196, + "Ġprostit": 11197, + "Ġauthority": 11198, + ".rec": 11199, + "Ġspokes": 11200, + "ĠToday": 11201, + "istant": 11202, + "ĠHead": 11203, + "âĢĿ.": 11204, + "ertainment": 11205, + "cean": 11206, + "culate": 11207, + "Ġven": 11208, + "However": 11209, + "_arr": 11210, + "Ġtokens": 11211, + "Graph": 11212, + "ĠJud": 11213, + "ĠVirgin": 11214, + "ĠSerial": 11215, + "unning": 11216, + "Mutable": 11217, + "agers": 11218, + ".csv": 11219, + "Ġdeveloping": 11220, + "Ġinstructions": 11221, + "Ġpromise": 11222, + "Ġrequested": 11223, + "_encode": 11224, + "/\"": 11225, + "ĠIcon": 11226, + "uilt": 11227, + "-day": 11228, + "Ġintelligence": 11229, + ".IS": 11230, + "ĠObservable": 11231, + "ĠHard": 11232, + "Bool": 11233, + "idential": 11234, + ".Anchor": 11235, + "Ġselling": 11236, + "CI": 11237, + "AGES": 11238, + "tle": 11239, + "bur": 11240, + "UFFER": 11241, + "RY": 11242, + "Ġbigger": 11243, + "Ġrat": 11244, + "Ġfamous": 11245, + "Ġtypename": 11246, + "Ġexplained": 11247, + "}}Ċ": 11248, + "Ġnuclear": 11249, + "-N": 11250, + "Ġcrisis": 11251, + "ĠEnter": 11252, + "Ġanswers": 11253, + "/${": 11254, + "/pl": 11255, + "Ġsequ": 11256, + "_next": 11257, + "mask": 11258, + "Ġstanding": 11259, + "Ġplenty": 11260, + "ĠCross": 11261, + "ĉret": 11262, + "dro": 11263, + "ĠCast": 11264, + "=true": 11265, + "ĠChris": 11266, + "icio": 11267, + "ĠMike": 11268, + "Decimal": 11269, + "addComponent": 11270, + "Len": 11271, + "Ġcock": 11272, + "Ġ#{": 11273, + "URN": 11274, + "": 11403, + "Ġ*=": 11404, + "ĠPS": 11405, + "Ġdangerous": 11406, + "[p": 11407, + "OME": 11408, + "Other": 11409, + "ĠStringBuilder": 11410, + "Points": 11411, + "heading": 11412, + "Ġcurrency": 11413, + "Ġpercentage": 11414, + "_API": 11415, + "Ġclassic": 11416, + "thead": 11417, + "ĠMO": 11418, + "FE": 11419, + "Idx": 11420, + "await": 11421, + "Ġè": 11422, + "Ġaccident": 11423, + "Ġvariant": 11424, + "Ġmyst": 11425, + "ĠLand": 11426, + "ĠBre": 11427, + "Ġharm": 11428, + "ĠAcc": 11429, + "Ġcharged": 11430, + "iones": 11431, + "Visibility": 11432, + "arry": 11433, + "ĠLanguage": 11434, + "Ġwalking": 11435, + "\".ĊĊ": 11436, + "ifer": 11437, + "Ġleadership": 11438, + ".From": 11439, + "ynam": 11440, + "Ġtimestamp": 11441, + "ipt": 11442, + "ĠHas": 11443, + "REFER": 11444, + "ĠIts": 11445, + "Ġlistener": 11446, + "UTE": 11447, + "_description": 11448, + "Ġexperiences": 11449, + "Ġcreates": 11450, + "RS": 11451, + "cart": 11452, + "black": 11453, + "Ġchoices": 11454, + "war": 11455, + "Ġ'''": 11456, + "Ġordered": 11457, + "Ġevening": 11458, + "Ġpil": 11459, + "Ġtun": 11460, + "ĠBad": 11461, + "(app": 11462, + "random": 11463, + "Ġexplicit": 11464, + "Ġarrived": 11465, + "Ġfly": 11466, + "Ġeconom": 11467, + "-mail": 11468, + "Ġlists": 11469, + "Ġarchitect": 11470, + "ĠPay": 11471, + "Ġds": 11472, + "ĠSol": 11473, + "Ġvehicles": 11474, + "Hz": 11475, + "-com": 11476, + "Ġking": 11477, + "_equal": 11478, + "ĠHelp": 11479, + "Ġabuse": 11480, + "--;Ċ": 11481, + "Ġextr": 11482, + "Ġchemical": 11483, + "ä¿": 11484, + "Ġorient": 11485, + "Ġbreath": 11486, + "ĠSpace": 11487, + "(element": 11488, + "wait": 11489, + "DED": 11490, + "igma": 11491, + "Ġentr": 11492, + "Ġsob": 11493, + "-name": 11494, + "Ġaffected": 11495, + "ika": 11496, + "Ġcoal": 11497, + "_work": 11498, + "Ġhundreds": 11499, + "Ġpolitics": 11500, + "subject": 11501, + "Ġconsumer": 11502, + "ANGE": 11503, + "Ġrepeated": 11504, + "Send": 11505, + "Ġ#[": 11506, + "Ġprotocol": 11507, + "Ġleads": 11508, + "useum": 11509, + "Every": 11510, + "Import": 11511, + "(count": 11512, + "Ġchallenges": 11513, + "Ġnovel": 11514, + "Ġdepart": 11515, + "bits": 11516, + ".Current": 11517, + "Ġ`${": 11518, + "oting": 11519, + "(\\": 11520, + "Ġcreative": 11521, + "Ġbuff": 11522, + "Ġintroduced": 11523, + "usic": 11524, + "modules": 11525, + "Are": 11526, + "-doc": 11527, + "language": 11528, + "_cache": 11529, + "Ġtod": 11530, + "?>": 11531, + "omething": 11532, + "Ġhun": 11533, + "åº": 11534, + "aters": 11535, + "Intent": 11536, + "Ġimplemented": 11537, + "ĠCase": 11538, + "Children": 11539, + "Ġnotification": 11540, + "Renderer": 11541, + "Wrapper": 11542, + "Objects": 11543, + "tl": 11544, + ".Contains": 11545, + "Plugin": 11546, + ".row": 11547, + "Ġforg": 11548, + "Ġpermit": 11549, + "Ġtargets": 11550, + "ĠIF": 11551, + "Ġtip": 11552, + "sex": 11553, + "Ġsupports": 11554, + "Ġfold": 11555, + "photo": 11556, + "},čĊ": 11557, + "Ġgoogle": 11558, + "$('#": 11559, + "Ġsharing": 11560, + "Ġgoods": 11561, + "vs": 11562, + "ĠDan": 11563, + "Rate": 11564, + "ĠMartin": 11565, + "Ġmanner": 11566, + "lie": 11567, + ".The": 11568, + "Internal": 11569, + "ĠCONTR": 11570, + "Mock": 11571, + "RIGHT": 11572, + "Ġ'{": 11573, + "Ġcontrols": 11574, + "Mat": 11575, + "Ġmand": 11576, + "Ġextended": 11577, + "Ok": 11578, + "Ġembed": 11579, + "Ġplanet": 11580, + "ĠNon": 11581, + "-ch": 11582, + ")\",": 11583, + "epar": 11584, + "Ġbelieved": 11585, + "ĠEnvironment": 11586, + "ĠFriend": 11587, + "-res": 11588, + "Ġhandling": 11589, + "nic": 11590, + "-level": 11591, + "scri": 11592, + "Xml": 11593, + "BE": 11594, + "ungen": 11595, + "Ġalter": 11596, + "[idx": 11597, + "Pop": 11598, + "cam": 11599, + "Ġ(((": 11600, + "Ġshipping": 11601, + "Ġbattery": 11602, + "iddleware": 11603, + "MC": 11604, + "Ġimpl": 11605, + "otation": 11606, + "ĠLab": 11607, + "