Upload folder using huggingface_hub

README.md

@@ -0,0 +1,42 @@
+---
+base_model: []
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# mergedd
+
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+
+## Merge Details
+### Merge Method
+
+This model was merged using the passthrough merge method.
+
+### Models Merged
+
+The following models were included in the merge:
+* /home/ubuntu/nvm/Smaug-72B-v0.1
+* /home/ubuntu/nvm/Qwen1.5-72B
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+dtype: float16
+merge_method: passthrough
+slices:
+- sources:
+  - layer_range: [0, 69]
+    model:
+      model:
+        path: /home/ubuntu/nvm/Smaug-72B-v0.1
+- sources:
+  - layer_range: [9, 50]
+    model:
+      model:
+        path: /home/ubuntu/nvm/smallsmaug-fine2
+```

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "/data/models/Qwen1.5-72B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 24576,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 100,
+  "num_key_value_heads": 64,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.38.2",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

mergekit_config.yml

@@ -0,0 +1,13 @@
+dtype: float16
+merge_method: passthrough
+slices:
+- sources:
+  - layer_range: [0, 69]
+    model:
+      model:
+        path: /home/ubuntu/nvm/Smaug-72B-v0.1
+- sources:
+  - layer_range: [9, 50]
+    model:
+      model:
+        path: /home/ubuntu/nvm/smallsmaug-fine2

model-00001-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6ad8fd6ff159aac203bad44d2b74bfafaa194f15dfa49ec459e165d195bd418
+size 9873774704

model-00002-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c13f5ad584ab15c0335cf90aba239be08284257d0f8f6d84c50c4ebd6c8ae32
+size 9798360736

model-00003-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:164818ba87a0a92a3fcc1226c4a28438ed82e03f4cb601c34222d39b476615cc
+size 9932627912

model-00004-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a31b08d5bd60de5753db0db06db9c4802e18cdd5a7275922f0986a227485f5f4
+size 9664076736

model-00005-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16f65c47a7daf1fcb27b5f908be95bf083645b470ef529814506c2d4eb32ed69
+size 9932627912

model-00006-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c14433ba42aea7931aba2bdde43a21a4bccbee6d6606cb92681a307a7390b80
+size 9932545416

model-00007-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5682e3d37f1665f48f96c8b7327b245b3fca7c9927d689b81d8a030a73676511
+size 9664159232

model-00008-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68ebc9833f6f3746b9de6f5a5086d43b994dde3e791a7225e6689a1ccd230cac
+size 9798360808

model-00009-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a13a99b9d5c70058b84a70f12377766ac640ac9bd15001d606798276df705513
+size 9798377072

model-00010-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4eda6410c4e85183114bede1affd7da247ae3dfd33e47f4685b4f1474576f02d
+size 9664093016

model-00011-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c95a83c5f60b5bc3b9f6cc37bb29cb146c99498bf10511f5ed88b0ed8b52057
+size 9932644856

model-00012-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55c0c13de90629cf9cc7a4cc198ef4ca0b8568b3e419849b28c7f32c0abd7a78
+size 9932561928

model-00013-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e25966523c5f4d7f3865ab528bce77dd44e15076dbc5e2718433fc687f8b488
+size 9932561696

model-00014-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a31addadf009596544525703766cdad0a98f38957557d00069fdecaf4a573d24
+size 9798410072

model-00015-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66f2774314f4d0b9b01ef04f28de35224c8566ba5d8ac9f120c90471a84e0022
+size 9932561912

model-00016-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da56ea45a6744afd420e89ffa6138f7fc624ba0cec6b3b99f8f429fc133bd79f
+size 9873758008

model-00017-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f58021382da3c5f1d405e5679cdbf76b1a03ed4964557c17262b98f55e9983c5
+size 9932578424

model-00018-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8388900f19a284275e8b810bc7decb3f79e8bb85a9936922b6a47d47702cce7c
+size 9664175960

model-00019-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9dc366bc2a49707baa0bd5a5b3997548d0d935851b3513930d06a75f1edb1b26
+size 2415969304

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00019.safetensors", "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00019.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00019.safetensors", "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00019.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00019.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00019.safetensors", "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00019.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00019.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00019.safetensors", "model.embed_tokens.weight": "model-00001-of-00019.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00019.safetensors", "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00019.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00019.safetensors", "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00019.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00019.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00019.safetensors", "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00019.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00001-of-00019.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00019.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00019.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00019.safetensors", "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00019.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00019.safetensors", "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00019.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00019.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00019.safetensors", "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00019.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00019.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00019.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00019.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00019.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00019.safetensors", "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00019.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00019.safetensors", "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00019.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00019.safetensors", "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00019.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00019.safetensors", "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00019.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00019.safetensors", "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00019.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00019.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00019.safetensors", "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00019.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00001-of-00019.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00019.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00001-of-00019.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00019.safetensors", "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00019.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00019.safetensors", "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00019.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00019.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00019.safetensors", "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00019.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00019.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00019.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00019.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00002-of-00019.safetensors", "model.layers.3.input_layernorm.weight": "model-00002-of-00019.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00019.safetensors", "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00019.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00019.safetensors", "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00019.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00019.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00019.safetensors", "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00019.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00019.safetensors", "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00019.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00019.safetensors", "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00019.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00019.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00019.safetensors", "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00019.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00019.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00019.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00019.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00002-of-00019.safetensors", "model.layers.6.input_layernorm.weight": "model-00002-of-00019.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00019.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00019.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00019.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00019.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00002-of-00019.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00019.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00019.safetensors", "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00019.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00019.safetensors", "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00019.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00019.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00019.safetensors", "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00019.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00019.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00019.safetensors", "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00019.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00019.safetensors", "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00019.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00019.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00019.safetensors", "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00019.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00019.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00019.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00019.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00002-of-00019.safetensors", "model.layers.8.input_layernorm.weight": "model-00002-of-00019.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00019.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00019.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00019.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00002-of-00019.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00019.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00019.safetensors", "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00019.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00019.safetensors", "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00019.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00019.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00019.safetensors", "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00019.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00019.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00019.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00019.safetensors", "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00019.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00019.safetensors", "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00019.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00019.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00019.safetensors", "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00019.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00019.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00003-of-00019.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00019.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00019.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00019.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00019.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00003-of-00019.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00019.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00019.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00019.safetensors", "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00019.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00019.safetensors", "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00019.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00019.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00019.safetensors", "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00019.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00019.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00003-of-00019.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00019.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00019.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00019.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00019.safetensors", "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00019.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00019.safetensors", "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00019.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00019.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00019.safetensors", "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00019.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00019.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00003-of-00019.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00019.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00019.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00019.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00019.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00019.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00019.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00019.safetensors", "model.layers.16.self_attn.v_proj.bias": "model-00003-of-00019.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00019.safetensors", "model.layers.16.self_attn.q_proj.bias": "model-00003-of-00019.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00019.safetensors", "model.layers.16.self_attn.k_proj.bias": "model-00003-of-00019.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00019.safetensors", "model.layers.15.self_attn.v_proj.bias": "model-00003-of-00019.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00019.safetensors", "model.layers.15.self_attn.q_proj.bias": "model-00003-of-00019.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00019.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00019.safetensors", "model.layers.15.self_attn.k_proj.bias": "model-00003-of-00019.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00019.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00003-of-00019.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00019.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00019.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00019.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00019.safetensors", "model.layers.14.self_attn.v_proj.bias": "model-00003-of-00019.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00019.safetensors", "model.layers.14.self_attn.q_proj.bias": "model-00003-of-00019.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00019.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00019.safetensors", "model.layers.14.self_attn.k_proj.bias": "model-00003-of-00019.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00019.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00004-of-00019.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00019.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00004-of-00019.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00019.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00019.safetensors", "model.layers.18.self_attn.v_proj.bias": "model-00004-of-00019.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00019.safetensors", "model.layers.18.self_attn.q_proj.bias": "model-00004-of-00019.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00019.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00019.safetensors", "model.layers.18.self_attn.k_proj.bias": "model-00004-of-00019.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00019.safetensors", "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00019.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00019.safetensors", "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00019.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00019.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00019.safetensors", "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00019.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00019.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00004-of-00019.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00019.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00004-of-00019.safetensors", "model.layers.17.input_layernorm.weight": "model-00004-of-00019.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00019.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00019.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00004-of-00019.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00019.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00004-of-00019.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00019.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00019.safetensors", "model.layers.20.self_attn.v_proj.bias": "model-00004-of-00019.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00019.safetensors", "model.layers.20.self_attn.q_proj.bias": "model-00004-of-00019.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00019.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00019.safetensors", "model.layers.20.self_attn.k_proj.bias": "model-00004-of-00019.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00019.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00019.safetensors", "model.layers.19.self_attn.v_proj.bias": "model-00004-of-00019.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00019.safetensors", "model.layers.19.self_attn.q_proj.bias": "model-00004-of-00019.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00019.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00019.safetensors", "model.layers.19.self_attn.k_proj.bias": "model-00004-of-00019.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00019.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00004-of-00019.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00019.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00004-of-00019.safetensors", "model.layers.19.input_layernorm.weight": "model-00004-of-00019.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00019.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00004-of-00019.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00019.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00004-of-00019.safetensors", "model.layers.18.input_layernorm.weight": "model-00004-of-00019.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00019.safetensors", "model.layers.22.self_attn.v_proj.bias": "model-00004-of-00019.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00019.safetensors", "model.layers.22.self_attn.q_proj.bias": "model-00004-of-00019.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00019.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00019.safetensors", "model.layers.22.self_attn.k_proj.bias": "model-00004-of-00019.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00004-of-00019.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00019.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00019.safetensors", "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00019.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00019.safetensors", "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00019.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00019.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00019.safetensors", "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00019.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00019.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00005-of-00019.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00019.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00005-of-00019.safetensors", "model.layers.21.input_layernorm.weight": "model-00005-of-00019.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00019.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00005-of-00019.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00005-of-00019.safetensors", "model.layers.20.input_layernorm.weight": "model-00005-of-00019.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00019.safetensors", "model.layers.24.self_attn.v_proj.bias": "model-00005-of-00019.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00019.safetensors", "model.layers.24.self_attn.q_proj.bias": "model-00005-of-00019.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00019.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00019.safetensors", "model.layers.24.self_attn.k_proj.bias": "model-00005-of-00019.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00019.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00005-of-00019.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00019.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00005-of-00019.safetensors", "model.layers.24.input_layernorm.weight": "model-00005-of-00019.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00019.safetensors", "model.layers.23.self_attn.v_proj.bias": "model-00005-of-00019.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00019.safetensors", "model.layers.23.self_attn.q_proj.bias": "model-00005-of-00019.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00019.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00019.safetensors", "model.layers.23.self_attn.k_proj.bias": "model-00005-of-00019.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00019.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00005-of-00019.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00019.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00005-of-00019.safetensors", "model.layers.23.input_layernorm.weight": "model-00005-of-00019.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00019.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00005-of-00019.safetensors", "model.layers.22.input_layernorm.weight": "model-00005-of-00019.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00019.safetensors", "model.layers.27.self_attn.v_proj.bias": "model-00005-of-00019.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00019.safetensors", "model.layers.27.self_attn.q_proj.bias": "model-00005-of-00019.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00019.safetensors", "model.layers.27.self_attn.k_proj.bias": "model-00005-of-00019.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00019.safetensors", "model.layers.26.self_attn.v_proj.bias": "model-00005-of-00019.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00019.safetensors", "model.layers.26.self_attn.q_proj.bias": "model-00005-of-00019.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00019.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00019.safetensors", "model.layers.26.self_attn.k_proj.bias": "model-00005-of-00019.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00019.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00005-of-00019.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00019.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00005-of-00019.safetensors", "model.layers.26.input_layernorm.weight": "model-00005-of-00019.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00019.safetensors", "model.layers.25.self_attn.v_proj.bias": "model-00005-of-00019.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00019.safetensors", "model.layers.25.self_attn.q_proj.bias": "model-00005-of-00019.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00019.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00019.safetensors", "model.layers.25.self_attn.k_proj.bias": "model-00005-of-00019.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00019.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00005-of-00019.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00019.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00006-of-00019.safetensors", "model.layers.25.input_layernorm.weight": "model-00006-of-00019.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00019.safetensors", "model.layers.29.self_attn.v_proj.bias": "model-00006-of-00019.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00019.safetensors", "model.layers.29.self_attn.q_proj.bias": "model-00006-of-00019.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00019.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00019.safetensors", "model.layers.29.self_attn.k_proj.bias": "model-00006-of-00019.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00019.safetensors", "model.layers.28.self_attn.v_proj.bias": "model-00006-of-00019.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00019.safetensors", "model.layers.28.self_attn.q_proj.bias": "model-00006-of-00019.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00019.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00019.safetensors", "model.layers.28.self_attn.k_proj.bias": "model-00006-of-00019.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00019.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00006-of-00019.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00019.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00006-of-00019.safetensors", "model.layers.28.input_layernorm.weight": "model-00006-of-00019.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00019.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00019.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00006-of-00019.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00019.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00006-of-00019.safetensors", "model.layers.27.input_layernorm.weight": "model-00006-of-00019.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00019.safetensors", "model.layers.31.self_attn.v_proj.bias": "model-00006-of-00019.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00019.safetensors", "model.layers.31.self_attn.q_proj.bias": "model-00006-of-00019.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00019.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00019.safetensors", "model.layers.31.self_attn.k_proj.bias": "model-00006-of-00019.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00019.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00019.safetensors", "model.layers.30.self_attn.v_proj.bias": "model-00006-of-00019.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00019.safetensors", "model.layers.30.self_attn.q_proj.bias": "model-00006-of-00019.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00019.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00019.safetensors", "model.layers.30.self_attn.k_proj.bias": "model-00006-of-00019.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00019.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00006-of-00019.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00019.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00006-of-00019.safetensors", "model.layers.30.input_layernorm.weight": "model-00006-of-00019.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00019.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00006-of-00019.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00019.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00006-of-00019.safetensors", "model.layers.29.input_layernorm.weight": "model-00006-of-00019.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00006-of-00019.safetensors", "model.layers.33.self_attn.v_proj.bias": "model-00006-of-00019.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00006-of-00019.safetensors", "model.layers.33.self_attn.q_proj.bias": "model-00006-of-00019.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00006-of-00019.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00006-of-00019.safetensors", "model.layers.33.self_attn.k_proj.bias": "model-00006-of-00019.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00006-of-00019.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00006-of-00019.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00006-of-00019.safetensors", "model.layers.32.self_attn.v_proj.bias": "model-00006-of-00019.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00006-of-00019.safetensors", "model.layers.32.self_attn.q_proj.bias": "model-00006-of-00019.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00019.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00007-of-00019.safetensors", "model.layers.32.self_attn.k_proj.bias": "model-00007-of-00019.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00019.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00007-of-00019.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00007-of-00019.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00007-of-00019.safetensors", "model.layers.32.input_layernorm.weight": "model-00007-of-00019.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00019.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00007-of-00019.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00007-of-00019.safetensors", "model.layers.31.input_layernorm.weight": "model-00007-of-00019.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00007-of-00019.safetensors", "model.layers.35.self_attn.v_proj.bias": "model-00007-of-00019.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00007-of-00019.safetensors", "model.layers.35.self_attn.q_proj.bias": "model-00007-of-00019.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00007-of-00019.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00007-of-00019.safetensors", "model.layers.35.self_attn.k_proj.bias": "model-00007-of-00019.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00007-of-00019.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00007-of-00019.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00007-of-00019.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00007-of-00019.safetensors", "model.layers.35.input_layernorm.weight": "model-00007-of-00019.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00007-of-00019.safetensors", "model.layers.34.self_attn.v_proj.bias": "model-00007-of-00019.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00007-of-00019.safetensors", "model.layers.34.self_attn.q_proj.bias": "model-00007-of-00019.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00007-of-00019.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00007-of-00019.safetensors", "model.layers.34.self_attn.k_proj.bias": "model-00007-of-00019.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00007-of-00019.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00007-of-00019.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00007-of-00019.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00007-of-00019.safetensors", "model.layers.34.input_layernorm.weight": "model-00007-of-00019.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00007-of-00019.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00007-of-00019.safetensors", "model.layers.33.input_layernorm.weight": "model-00007-of-00019.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00007-of-00019.safetensors", "model.layers.38.self_attn.v_proj.bias": "model-00007-of-00019.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00007-of-00019.safetensors", "model.layers.38.self_attn.q_proj.bias": "model-00007-of-00019.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00007-of-00019.safetensors", "model.layers.38.self_attn.k_proj.bias": "model-00007-of-00019.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00007-of-00019.safetensors", "model.layers.37.self_attn.v_proj.bias": "model-00007-of-00019.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00007-of-00019.safetensors", "model.layers.37.self_attn.q_proj.bias": "model-00007-of-00019.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00007-of-00019.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00007-of-00019.safetensors", "model.layers.37.self_attn.k_proj.bias": "model-00007-of-00019.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00007-of-00019.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00007-of-00019.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00007-of-00019.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00007-of-00019.safetensors", "model.layers.37.input_layernorm.weight": "model-00007-of-00019.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00007-of-00019.safetensors", "model.layers.36.self_attn.v_proj.bias": "model-00007-of-00019.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00007-of-00019.safetensors", "model.layers.36.self_attn.q_proj.bias": "model-00007-of-00019.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00007-of-00019.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00007-of-00019.safetensors", "model.layers.36.self_attn.k_proj.bias": "model-00007-of-00019.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00007-of-00019.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00007-of-00019.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00007-of-00019.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00008-of-00019.safetensors", "model.layers.36.input_layernorm.weight": "model-00008-of-00019.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00008-of-00019.safetensors", "model.layers.40.self_attn.v_proj.bias": "model-00008-of-00019.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00008-of-00019.safetensors", "model.layers.40.self_attn.q_proj.bias": "model-00008-of-00019.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00008-of-00019.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00008-of-00019.safetensors", "model.layers.40.self_attn.k_proj.bias": "model-00008-of-00019.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00008-of-00019.safetensors", "model.layers.39.self_attn.v_proj.bias": "model-00008-of-00019.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00008-of-00019.safetensors", "model.layers.39.self_attn.q_proj.bias": "model-00008-of-00019.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00008-of-00019.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00008-of-00019.safetensors", "model.layers.39.self_attn.k_proj.bias": "model-00008-of-00019.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00008-of-00019.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00008-of-00019.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00008-of-00019.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00008-of-00019.safetensors", "model.layers.39.input_layernorm.weight": "model-00008-of-00019.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00008-of-00019.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00008-of-00019.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00008-of-00019.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00008-of-00019.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00008-of-00019.safetensors", "model.layers.38.input_layernorm.weight": "model-00008-of-00019.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00008-of-00019.safetensors", "model.layers.42.self_attn.v_proj.bias": "model-00008-of-00019.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00008-of-00019.safetensors", "model.layers.42.self_attn.q_proj.bias": "model-00008-of-00019.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00008-of-00019.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00008-of-00019.safetensors", "model.layers.42.self_attn.k_proj.bias": "model-00008-of-00019.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00008-of-00019.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00008-of-00019.safetensors", "model.layers.41.self_attn.v_proj.bias": "model-00008-of-00019.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00008-of-00019.safetensors", "model.layers.41.self_attn.q_proj.bias": "model-00008-of-00019.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00008-of-00019.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00008-of-00019.safetensors", "model.layers.41.self_attn.k_proj.bias": "model-00008-of-00019.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00008-of-00019.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00008-of-00019.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00008-of-00019.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00008-of-00019.safetensors", "model.layers.41.input_layernorm.weight": "model-00008-of-00019.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00008-of-00019.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00008-of-00019.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00008-of-00019.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00008-of-00019.safetensors", "model.layers.40.input_layernorm.weight": "model-00008-of-00019.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00008-of-00019.safetensors", "model.layers.77.self_attn.v_proj.bias": "model-00008-of-00019.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00008-of-00019.safetensors", "model.layers.77.self_attn.q_proj.bias": "model-00008-of-00019.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00008-of-00019.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00008-of-00019.safetensors", "model.layers.77.self_attn.k_proj.bias": "model-00008-of-00019.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00008-of-00019.safetensors", "model.layers.76.self_attn.v_proj.bias": "model-00008-of-00019.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00008-of-00019.safetensors", "model.layers.76.self_attn.q_proj.bias": "model-00008-of-00019.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00008-of-00019.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00008-of-00019.safetensors", "model.layers.76.self_attn.k_proj.bias": "model-00008-of-00019.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00008-of-00019.safetensors", "model.layers.76.mlp.up_proj.weight": "model-00008-of-00019.safetensors", "model.layers.76.mlp.gate_proj.weight": "model-00008-of-00019.safetensors", "model.layers.76.mlp.down_proj.weight": "model-00009-of-00019.safetensors", "model.layers.76.input_layernorm.weight": "model-00009-of-00019.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00009-of-00019.safetensors", "model.layers.75.self_attn.v_proj.bias": "model-00009-of-00019.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00009-of-00019.safetensors", "model.layers.75.self_attn.q_proj.bias": "model-00009-of-00019.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00009-of-00019.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00009-of-00019.safetensors", "model.layers.75.self_attn.k_proj.bias": "model-00009-of-00019.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00009-of-00019.safetensors", "model.layers.75.mlp.up_proj.weight": "model-00009-of-00019.safetensors", "model.layers.75.mlp.gate_proj.weight": "model-00009-of-00019.safetensors", "model.layers.75.mlp.down_proj.weight": "model-00009-of-00019.safetensors", "model.layers.75.input_layernorm.weight": "model-00009-of-00019.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00009-of-00019.safetensors", "model.layers.44.self_attn.v_proj.bias": "model-00009-of-00019.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00009-of-00019.safetensors", "model.layers.44.self_attn.q_proj.bias": "model-00009-of-00019.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00009-of-00019.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00009-of-00019.safetensors", "model.layers.44.self_attn.k_proj.bias": "model-00009-of-00019.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00009-of-00019.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00009-of-00019.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00009-of-00019.safetensors", "model.layers.43.self_attn.v_proj.bias": "model-00009-of-00019.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00009-of-00019.safetensors", "model.layers.43.self_attn.q_proj.bias": "model-00009-of-00019.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00009-of-00019.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00009-of-00019.safetensors", "model.layers.43.self_attn.k_proj.bias": "model-00009-of-00019.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00009-of-00019.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00009-of-00019.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00009-of-00019.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00009-of-00019.safetensors", "model.layers.43.input_layernorm.weight": "model-00009-of-00019.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00009-of-00019.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00009-of-00019.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00009-of-00019.safetensors", "model.layers.42.input_layernorm.weight": "model-00009-of-00019.safetensors", "model.layers.80.self_attn.q_proj.weight": "model-00009-of-00019.safetensors", "model.layers.80.self_attn.q_proj.bias": "model-00009-of-00019.safetensors", "model.layers.80.self_attn.k_proj.weight": "model-00009-of-00019.safetensors", "model.layers.80.self_attn.k_proj.bias": "model-00009-of-00019.safetensors", "model.layers.79.self_attn.v_proj.weight": "model-00009-of-00019.safetensors", "model.layers.79.self_attn.v_proj.bias": "model-00009-of-00019.safetensors", "model.layers.79.self_attn.q_proj.weight": "model-00009-of-00019.safetensors", "model.layers.79.self_attn.q_proj.bias": "model-00009-of-00019.safetensors", "model.layers.79.self_attn.o_proj.weight": "model-00009-of-00019.safetensors", "model.layers.79.self_attn.k_proj.weight": "model-00009-of-00019.safetensors", "model.layers.79.self_attn.k_proj.bias": "model-00009-of-00019.safetensors", "model.layers.79.post_attention_layernorm.weight": "model-00009-of-00019.safetensors", "model.layers.79.mlp.up_proj.weight": "model-00009-of-00019.safetensors", "model.layers.79.mlp.gate_proj.weight": "model-00009-of-00019.safetensors", "model.layers.79.mlp.down_proj.weight": "model-00009-of-00019.safetensors", "model.layers.79.input_layernorm.weight": "model-00009-of-00019.safetensors", "model.layers.78.self_attn.v_proj.weight": "model-00009-of-00019.safetensors", "model.layers.78.self_attn.v_proj.bias": "model-00009-of-00019.safetensors", "model.layers.78.self_attn.q_proj.weight": "model-00009-of-00019.safetensors", "model.layers.78.self_attn.q_proj.bias": "model-00009-of-00019.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00009-of-00019.safetensors", "model.layers.78.self_attn.k_proj.weight": "model-00009-of-00019.safetensors", "model.layers.78.self_attn.k_proj.bias": "model-00009-of-00019.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00009-of-00019.safetensors", "model.layers.78.mlp.up_proj.weight": "model-00009-of-00019.safetensors", "model.layers.78.mlp.gate_proj.weight": "model-00009-of-00019.safetensors", "model.layers.78.mlp.down_proj.weight": "model-00009-of-00019.safetensors", "model.layers.78.input_layernorm.weight": "model-00009-of-00019.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00009-of-00019.safetensors", "model.layers.77.mlp.up_proj.weight": "model-00010-of-00019.safetensors", "model.layers.77.mlp.gate_proj.weight": "model-00010-of-00019.safetensors", "model.layers.77.mlp.down_proj.weight": "model-00010-of-00019.safetensors", "model.layers.77.input_layernorm.weight": "model-00010-of-00019.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00010-of-00019.safetensors", "model.layers.46.self_attn.v_proj.bias": "model-00010-of-00019.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00010-of-00019.safetensors", "model.layers.46.self_attn.q_proj.bias": "model-00010-of-00019.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00010-of-00019.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00010-of-00019.safetensors", "model.layers.46.self_attn.k_proj.bias": "model-00010-of-00019.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00010-of-00019.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00010-of-00019.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00010-of-00019.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00010-of-00019.safetensors", "model.layers.46.input_layernorm.weight": "model-00010-of-00019.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00010-of-00019.safetensors", "model.layers.45.self_attn.v_proj.bias": "model-00010-of-00019.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00010-of-00019.safetensors", "model.layers.45.self_attn.q_proj.bias": "model-00010-of-00019.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00010-of-00019.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00010-of-00019.safetensors", "model.layers.45.self_attn.k_proj.bias": "model-00010-of-00019.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00010-of-00019.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00010-of-00019.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00010-of-00019.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00010-of-00019.safetensors", "model.layers.45.input_layernorm.weight": "model-00010-of-00019.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00010-of-00019.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00010-of-00019.safetensors", "model.layers.44.input_layernorm.weight": "model-00010-of-00019.safetensors", "model.layers.82.self_attn.v_proj.weight": "model-00010-of-00019.safetensors", "model.layers.82.self_attn.v_proj.bias": "model-00010-of-00019.safetensors", "model.layers.82.self_attn.q_proj.weight": "model-00010-of-00019.safetensors", "model.layers.82.self_attn.q_proj.bias": "model-00010-of-00019.safetensors", "model.layers.82.self_attn.o_proj.weight": "model-00010-of-00019.safetensors", "model.layers.82.self_attn.k_proj.weight": "model-00010-of-00019.safetensors", "model.layers.82.self_attn.k_proj.bias": "model-00010-of-00019.safetensors", "model.layers.82.post_attention_layernorm.weight": "model-00010-of-00019.safetensors", "model.layers.82.mlp.up_proj.weight": "model-00010-of-00019.safetensors", "model.layers.82.mlp.gate_proj.weight": "model-00010-of-00019.safetensors", "model.layers.82.mlp.down_proj.weight": "model-00010-of-00019.safetensors", "model.layers.82.input_layernorm.weight": "model-00010-of-00019.safetensors", "model.layers.81.self_attn.v_proj.weight": "model-00010-of-00019.safetensors", "model.layers.81.self_attn.v_proj.bias": "model-00010-of-00019.safetensors", "model.layers.81.self_attn.q_proj.weight": "model-00010-of-00019.safetensors", "model.layers.81.self_attn.q_proj.bias": "model-00010-of-00019.safetensors", "model.layers.81.self_attn.o_proj.weight": "model-00010-of-00019.safetensors", "model.layers.81.self_attn.k_proj.weight": "model-00010-of-00019.safetensors", "model.layers.81.self_attn.k_proj.bias": "model-00010-of-00019.safetensors", "model.layers.81.post_attention_layernorm.weight": "model-00010-of-00019.safetensors", "model.layers.81.mlp.up_proj.weight": "model-00010-of-00019.safetensors", "model.layers.81.mlp.gate_proj.weight": "model-00010-of-00019.safetensors", "model.layers.81.mlp.down_proj.weight": "model-00010-of-00019.safetensors", "model.layers.81.input_layernorm.weight": "model-00010-of-00019.safetensors", "model.layers.80.self_attn.v_proj.weight": "model-00010-of-00019.safetensors", "model.layers.80.self_attn.v_proj.bias": "model-00010-of-00019.safetensors", "model.layers.80.self_attn.o_proj.weight": "model-00010-of-00019.safetensors", "model.layers.80.post_attention_layernorm.weight": "model-00010-of-00019.safetensors", "model.layers.80.mlp.up_proj.weight": "model-00010-of-00019.safetensors", "model.layers.80.mlp.gate_proj.weight": "model-00010-of-00019.safetensors", "model.layers.80.mlp.down_proj.weight": "model-00011-of-00019.safetensors", "model.layers.80.input_layernorm.weight": "model-00011-of-00019.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00011-of-00019.safetensors", "model.layers.49.self_attn.v_proj.bias": "model-00011-of-00019.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00011-of-00019.safetensors", "model.layers.49.self_attn.q_proj.bias": "model-00011-of-00019.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00011-of-00019.safetensors", "model.layers.49.self_attn.k_proj.bias": "model-00011-of-00019.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00011-of-00019.safetensors", "model.layers.48.self_attn.v_proj.bias": "model-00011-of-00019.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00011-of-00019.safetensors", "model.layers.48.self_attn.q_proj.bias": "model-00011-of-00019.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00011-of-00019.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00011-of-00019.safetensors", "model.layers.48.self_attn.k_proj.bias": "model-00011-of-00019.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00011-of-00019.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00011-of-00019.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00011-of-00019.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00011-of-00019.safetensors", "model.layers.48.input_layernorm.weight": "model-00011-of-00019.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00011-of-00019.safetensors", "model.layers.47.self_attn.v_proj.bias": "model-00011-of-00019.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00011-of-00019.safetensors", "model.layers.47.self_attn.q_proj.bias": "model-00011-of-00019.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00011-of-00019.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00011-of-00019.safetensors", "model.layers.47.self_attn.k_proj.bias": "model-00011-of-00019.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00011-of-00019.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00011-of-00019.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00011-of-00019.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00011-of-00019.safetensors", "model.layers.47.input_layernorm.weight": "model-00011-of-00019.safetensors", "model.layers.85.self_attn.v_proj.weight": "model-00011-of-00019.safetensors", "model.layers.85.self_attn.v_proj.bias": "model-00011-of-00019.safetensors", "model.layers.85.self_attn.q_proj.weight": "model-00011-of-00019.safetensors", "model.layers.85.self_attn.q_proj.bias": "model-00011-of-00019.safetensors", "model.layers.85.self_attn.o_proj.weight": "model-00011-of-00019.safetensors", "model.layers.85.self_attn.k_proj.weight": "model-00011-of-00019.safetensors", "model.layers.85.self_attn.k_proj.bias": "model-00011-of-00019.safetensors", "model.layers.85.mlp.up_proj.weight": "model-00011-of-00019.safetensors", "model.layers.85.mlp.gate_proj.weight": "model-00011-of-00019.safetensors", "model.layers.84.self_attn.v_proj.weight": "model-00011-of-00019.safetensors", "model.layers.84.self_attn.v_proj.bias": "model-00011-of-00019.safetensors", "model.layers.84.self_attn.q_proj.weight": "model-00011-of-00019.safetensors", "model.layers.84.self_attn.q_proj.bias": "model-00011-of-00019.safetensors", "model.layers.84.self_attn.o_proj.weight": "model-00011-of-00019.safetensors", "model.layers.84.self_attn.k_proj.weight": "model-00011-of-00019.safetensors", "model.layers.84.self_attn.k_proj.bias": "model-00011-of-00019.safetensors", "model.layers.84.post_attention_layernorm.weight": "model-00011-of-00019.safetensors", "model.layers.84.mlp.up_proj.weight": "model-00011-of-00019.safetensors", "model.layers.84.mlp.gate_proj.weight": "model-00011-of-00019.safetensors", "model.layers.84.mlp.down_proj.weight": "model-00011-of-00019.safetensors", "model.layers.84.input_layernorm.weight": "model-00011-of-00019.safetensors", "model.layers.83.self_attn.v_proj.weight": "model-00011-of-00019.safetensors", "model.layers.83.self_attn.v_proj.bias": "model-00011-of-00019.safetensors", "model.layers.83.self_attn.q_proj.weight": "model-00011-of-00019.safetensors", "model.layers.83.self_attn.q_proj.bias": "model-00011-of-00019.safetensors", "model.layers.83.self_attn.o_proj.weight": "model-00011-of-00019.safetensors", "model.layers.83.self_attn.k_proj.weight": "model-00011-of-00019.safetensors", "model.layers.83.self_attn.k_proj.bias": "model-00011-of-00019.safetensors", "model.layers.83.post_attention_layernorm.weight": "model-00011-of-00019.safetensors", "model.layers.83.mlp.up_proj.weight": "model-00011-of-00019.safetensors", "model.layers.83.mlp.gate_proj.weight": "model-00011-of-00019.safetensors", "model.layers.83.mlp.down_proj.weight": "model-00011-of-00019.safetensors", "model.layers.83.input_layernorm.weight": "model-00011-of-00019.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00011-of-00019.safetensors", "model.layers.51.self_attn.v_proj.bias": "model-00011-of-00019.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00011-of-00019.safetensors", "model.layers.51.self_attn.q_proj.bias": "model-00011-of-00019.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00011-of-00019.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00011-of-00019.safetensors", "model.layers.51.self_attn.k_proj.bias": "model-00011-of-00019.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00011-of-00019.safetensors", "model.layers.50.self_attn.v_proj.bias": "model-00011-of-00019.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00011-of-00019.safetensors", "model.layers.50.self_attn.q_proj.bias": "model-00011-of-00019.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00012-of-00019.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00012-of-00019.safetensors", "model.layers.50.self_attn.k_proj.bias": "model-00012-of-00019.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00012-of-00019.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00012-of-00019.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00012-of-00019.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00012-of-00019.safetensors", "model.layers.50.input_layernorm.weight": "model-00012-of-00019.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00012-of-00019.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00012-of-00019.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00012-of-00019.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00012-of-00019.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00012-of-00019.safetensors", "model.layers.49.input_layernorm.weight": "model-00012-of-00019.safetensors", "model.layers.88.self_attn.v_proj.weight": "model-00012-of-00019.safetensors", "model.layers.88.self_attn.v_proj.bias": "model-00012-of-00019.safetensors", "model.layers.88.self_attn.q_proj.weight": "model-00012-of-00019.safetensors", "model.layers.88.self_attn.q_proj.bias": "model-00012-of-00019.safetensors", "model.layers.88.self_attn.o_proj.weight": "model-00012-of-00019.safetensors", "model.layers.88.self_attn.k_proj.weight": "model-00012-of-00019.safetensors", "model.layers.88.self_attn.k_proj.bias": "model-00012-of-00019.safetensors", "model.layers.88.mlp.gate_proj.weight": "model-00012-of-00019.safetensors", "model.layers.87.self_attn.v_proj.weight": "model-00012-of-00019.safetensors", "model.layers.87.self_attn.v_proj.bias": "model-00012-of-00019.safetensors", "model.layers.87.self_attn.q_proj.weight": "model-00012-of-00019.safetensors", "model.layers.87.self_attn.q_proj.bias": "model-00012-of-00019.safetensors", "model.layers.87.self_attn.o_proj.weight": "model-00012-of-00019.safetensors", "model.layers.87.self_attn.k_proj.weight": "model-00012-of-00019.safetensors", "model.layers.87.self_attn.k_proj.bias": "model-00012-of-00019.safetensors", "model.layers.87.post_attention_layernorm.weight": "model-00012-of-00019.safetensors", "model.layers.87.mlp.up_proj.weight": "model-00012-of-00019.safetensors", "model.layers.87.mlp.gate_proj.weight": "model-00012-of-00019.safetensors", "model.layers.87.mlp.down_proj.weight": "model-00012-of-00019.safetensors", "model.layers.87.input_layernorm.weight": "model-00012-of-00019.safetensors", "model.layers.86.self_attn.v_proj.weight": "model-00012-of-00019.safetensors", "model.layers.86.self_attn.v_proj.bias": "model-00012-of-00019.safetensors", "model.layers.86.self_attn.q_proj.weight": "model-00012-of-00019.safetensors", "model.layers.86.self_attn.q_proj.bias": "model-00012-of-00019.safetensors", "model.layers.86.self_attn.o_proj.weight": "model-00012-of-00019.safetensors", "model.layers.86.self_attn.k_proj.weight": "model-00012-of-00019.safetensors", "model.layers.86.self_attn.k_proj.bias": "model-00012-of-00019.safetensors", "model.layers.86.post_attention_layernorm.weight": "model-00012-of-00019.safetensors", "model.layers.86.mlp.up_proj.weight": "model-00012-of-00019.safetensors", "model.layers.86.mlp.gate_proj.weight": "model-00012-of-00019.safetensors", "model.layers.86.mlp.down_proj.weight": "model-00012-of-00019.safetensors", "model.layers.86.input_layernorm.weight": "model-00012-of-00019.safetensors", "model.layers.85.post_attention_layernorm.weight": "model-00012-of-00019.safetensors", "model.layers.85.mlp.down_proj.weight": "model-00012-of-00019.safetensors", "model.layers.85.input_layernorm.weight": "model-00012-of-00019.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00012-of-00019.safetensors", "model.layers.53.self_attn.v_proj.bias": "model-00012-of-00019.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00012-of-00019.safetensors", "model.layers.53.self_attn.q_proj.bias": "model-00012-of-00019.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00012-of-00019.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00012-of-00019.safetensors", "model.layers.53.self_attn.k_proj.bias": "model-00012-of-00019.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00012-of-00019.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00012-of-00019.safetensors", "model.layers.52.self_attn.v_proj.bias": "model-00012-of-00019.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00012-of-00019.safetensors", "model.layers.52.self_attn.q_proj.bias": "model-00012-of-00019.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00012-of-00019.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00012-of-00019.safetensors", "model.layers.52.self_attn.k_proj.bias": "model-00012-of-00019.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00012-of-00019.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00012-of-00019.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00012-of-00019.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00013-of-00019.safetensors", "model.layers.52.input_layernorm.weight": "model-00013-of-00019.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00013-of-00019.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00013-of-00019.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00013-of-00019.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00013-of-00019.safetensors", "model.layers.51.input_layernorm.weight": "model-00013-of-00019.safetensors", "model.layers.91.self_attn.v_proj.weight": "model-00013-of-00019.safetensors", "model.layers.91.self_attn.v_proj.bias": "model-00013-of-00019.safetensors", "model.layers.91.self_attn.q_proj.weight": "model-00013-of-00019.safetensors", "model.layers.91.self_attn.q_proj.bias": "model-00013-of-00019.safetensors", "model.layers.91.self_attn.o_proj.weight": "model-00013-of-00019.safetensors", "model.layers.91.self_attn.k_proj.weight": "model-00013-of-00019.safetensors", "model.layers.91.self_attn.k_proj.bias": "model-00013-of-00019.safetensors", "model.layers.90.self_attn.v_proj.weight": "model-00013-of-00019.safetensors", "model.layers.90.self_attn.v_proj.bias": "model-00013-of-00019.safetensors", "model.layers.90.self_attn.q_proj.weight": "model-00013-of-00019.safetensors", "model.layers.90.self_attn.q_proj.bias": "model-00013-of-00019.safetensors", "model.layers.90.self_attn.o_proj.weight": "model-00013-of-00019.safetensors", "model.layers.90.self_attn.k_proj.weight": "model-00013-of-00019.safetensors", "model.layers.90.self_attn.k_proj.bias": "model-00013-of-00019.safetensors", "model.layers.90.post_attention_layernorm.weight": "model-00013-of-00019.safetensors", "model.layers.90.mlp.up_proj.weight": "model-00013-of-00019.safetensors", "model.layers.90.mlp.gate_proj.weight": "model-00013-of-00019.safetensors", "model.layers.90.mlp.down_proj.weight": "model-00013-of-00019.safetensors", "model.layers.90.input_layernorm.weight": "model-00013-of-00019.safetensors", "model.layers.89.self_attn.v_proj.weight": "model-00013-of-00019.safetensors", "model.layers.89.self_attn.v_proj.bias": "model-00013-of-00019.safetensors", "model.layers.89.self_attn.q_proj.weight": "model-00013-of-00019.safetensors", "model.layers.89.self_attn.q_proj.bias": "model-00013-of-00019.safetensors", "model.layers.89.self_attn.o_proj.weight": "model-00013-of-00019.safetensors", "model.layers.89.self_attn.k_proj.weight": "model-00013-of-00019.safetensors", "model.layers.89.self_attn.k_proj.bias": "model-00013-of-00019.safetensors", "model.layers.89.post_attention_layernorm.weight": "model-00013-of-00019.safetensors", "model.layers.89.mlp.up_proj.weight": "model-00013-of-00019.safetensors", "model.layers.89.mlp.gate_proj.weight": "model-00013-of-00019.safetensors", "model.layers.89.mlp.down_proj.weight": "model-00013-of-00019.safetensors", "model.layers.89.input_layernorm.weight": "model-00013-of-00019.safetensors", "model.layers.88.post_attention_layernorm.weight": "model-00013-of-00019.safetensors", "model.layers.88.mlp.up_proj.weight": "model-00013-of-00019.safetensors", "model.layers.88.mlp.down_proj.weight": "model-00013-of-00019.safetensors", "model.layers.88.input_layernorm.weight": "model-00013-of-00019.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00013-of-00019.safetensors", "model.layers.55.self_attn.v_proj.bias": "model-00013-of-00019.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00013-of-00019.safetensors", "model.layers.55.self_attn.q_proj.bias": "model-00013-of-00019.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00013-of-00019.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00013-of-00019.safetensors", "model.layers.55.self_attn.k_proj.bias": "model-00013-of-00019.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00013-of-00019.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00013-of-00019.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00013-of-00019.safetensors", "model.layers.54.self_attn.v_proj.bias": "model-00013-of-00019.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00013-of-00019.safetensors", "model.layers.54.self_attn.q_proj.bias": "model-00013-of-00019.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00013-of-00019.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00013-of-00019.safetensors", "model.layers.54.self_attn.k_proj.bias": "model-00013-of-00019.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00013-of-00019.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00013-of-00019.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00013-of-00019.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00013-of-00019.safetensors", "model.layers.54.input_layernorm.weight": "model-00013-of-00019.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00013-of-00019.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00013-of-00019.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00014-of-00019.safetensors", "model.layers.53.input_layernorm.weight": "model-00014-of-00019.safetensors", "model.layers.94.self_attn.q_proj.weight": "model-00014-of-00019.safetensors", "model.layers.94.self_attn.q_proj.bias": "model-00014-of-00019.safetensors", "model.layers.94.self_attn.k_proj.weight": "model-00014-of-00019.safetensors", "model.layers.94.self_attn.k_proj.bias": "model-00014-of-00019.safetensors", "model.layers.93.self_attn.v_proj.weight": "model-00014-of-00019.safetensors", "model.layers.93.self_attn.v_proj.bias": "model-00014-of-00019.safetensors", "model.layers.93.self_attn.q_proj.weight": "model-00014-of-00019.safetensors", "model.layers.93.self_attn.q_proj.bias": "model-00014-of-00019.safetensors", "model.layers.93.self_attn.o_proj.weight": "model-00014-of-00019.safetensors", "model.layers.93.self_attn.k_proj.weight": "model-00014-of-00019.safetensors", "model.layers.93.self_attn.k_proj.bias": "model-00014-of-00019.safetensors", "model.layers.93.post_attention_layernorm.weight": "model-00014-of-00019.safetensors", "model.layers.93.mlp.up_proj.weight": "model-00014-of-00019.safetensors", "model.layers.93.mlp.gate_proj.weight": "model-00014-of-00019.safetensors", "model.layers.93.mlp.down_proj.weight": "model-00014-of-00019.safetensors", "model.layers.93.input_layernorm.weight": "model-00014-of-00019.safetensors", "model.layers.92.self_attn.v_proj.weight": "model-00014-of-00019.safetensors", "model.layers.92.self_attn.v_proj.bias": "model-00014-of-00019.safetensors", "model.layers.92.self_attn.q_proj.weight": "model-00014-of-00019.safetensors", "model.layers.92.self_attn.q_proj.bias": "model-00014-of-00019.safetensors", "model.layers.92.self_attn.o_proj.weight": "model-00014-of-00019.safetensors", "model.layers.92.self_attn.k_proj.weight": "model-00014-of-00019.safetensors", "model.layers.92.self_attn.k_proj.bias": "model-00014-of-00019.safetensors", "model.layers.92.post_attention_layernorm.weight": "model-00014-of-00019.safetensors", "model.layers.92.mlp.up_proj.weight": "model-00014-of-00019.safetensors", "model.layers.92.mlp.gate_proj.weight": "model-00014-of-00019.safetensors", "model.layers.92.mlp.down_proj.weight": "model-00014-of-00019.safetensors", "model.layers.92.input_layernorm.weight": "model-00014-of-00019.safetensors", "model.layers.91.post_attention_layernorm.weight": "model-00014-of-00019.safetensors", "model.layers.91.mlp.up_proj.weight": "model-00014-of-00019.safetensors", "model.layers.91.mlp.gate_proj.weight": "model-00014-of-00019.safetensors", "model.layers.91.mlp.down_proj.weight": "model-00014-of-00019.safetensors", "model.layers.91.input_layernorm.weight": "model-00014-of-00019.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00014-of-00019.safetensors", "model.layers.57.self_attn.v_proj.bias": "model-00014-of-00019.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00014-of-00019.safetensors", "model.layers.57.self_attn.q_proj.bias": "model-00014-of-00019.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00014-of-00019.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00014-of-00019.safetensors", "model.layers.57.self_attn.k_proj.bias": "model-00014-of-00019.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00014-of-00019.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00014-of-00019.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00014-of-00019.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00014-of-00019.safetensors", "model.layers.57.input_layernorm.weight": "model-00014-of-00019.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00014-of-00019.safetensors", "model.layers.56.self_attn.v_proj.bias": "model-00014-of-00019.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00014-of-00019.safetensors", "model.layers.56.self_attn.q_proj.bias": "model-00014-of-00019.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00014-of-00019.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00014-of-00019.safetensors", "model.layers.56.self_attn.k_proj.bias": "model-00014-of-00019.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00014-of-00019.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00014-of-00019.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00014-of-00019.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00014-of-00019.safetensors", "model.layers.56.input_layernorm.weight": "model-00014-of-00019.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00014-of-00019.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00014-of-00019.safetensors", "model.layers.55.input_layernorm.weight": "model-00014-of-00019.safetensors", "model.layers.96.self_attn.v_proj.weight": "model-00014-of-00019.safetensors", "model.layers.96.self_attn.v_proj.bias": "model-00014-of-00019.safetensors", "model.layers.96.self_attn.q_proj.weight": "model-00014-of-00019.safetensors", "model.layers.96.self_attn.q_proj.bias": "model-00014-of-00019.safetensors", "model.layers.96.self_attn.o_proj.weight": "model-00014-of-00019.safetensors", "model.layers.96.self_attn.k_proj.weight": "model-00014-of-00019.safetensors", "model.layers.96.self_attn.k_proj.bias": "model-00014-of-00019.safetensors", "model.layers.96.post_attention_layernorm.weight": "model-00014-of-00019.safetensors", "model.layers.96.mlp.up_proj.weight": "model-00015-of-00019.safetensors", "model.layers.96.mlp.gate_proj.weight": "model-00015-of-00019.safetensors", "model.layers.96.mlp.down_proj.weight": "model-00015-of-00019.safetensors", "model.layers.96.input_layernorm.weight": "model-00015-of-00019.safetensors", "model.layers.95.self_attn.v_proj.weight": "model-00015-of-00019.safetensors", "model.layers.95.self_attn.v_proj.bias": "model-00015-of-00019.safetensors", "model.layers.95.self_attn.q_proj.weight": "model-00015-of-00019.safetensors", "model.layers.95.self_attn.q_proj.bias": "model-00015-of-00019.safetensors", "model.layers.95.self_attn.o_proj.weight": "model-00015-of-00019.safetensors", "model.layers.95.self_attn.k_proj.weight": "model-00015-of-00019.safetensors", "model.layers.95.self_attn.k_proj.bias": "model-00015-of-00019.safetensors", "model.layers.95.post_attention_layernorm.weight": "model-00015-of-00019.safetensors", "model.layers.95.mlp.up_proj.weight": "model-00015-of-00019.safetensors", "model.layers.95.mlp.gate_proj.weight": "model-00015-of-00019.safetensors", "model.layers.95.mlp.down_proj.weight": "model-00015-of-00019.safetensors", "model.layers.95.input_layernorm.weight": "model-00015-of-00019.safetensors", "model.layers.94.self_attn.v_proj.weight": "model-00015-of-00019.safetensors", "model.layers.94.self_attn.v_proj.bias": "model-00015-of-00019.safetensors", "model.layers.94.self_attn.o_proj.weight": "model-00015-of-00019.safetensors", "model.layers.94.post_attention_layernorm.weight": "model-00015-of-00019.safetensors", "model.layers.94.mlp.up_proj.weight": "model-00015-of-00019.safetensors", "model.layers.94.mlp.gate_proj.weight": "model-00015-of-00019.safetensors", "model.layers.94.mlp.down_proj.weight": "model-00015-of-00019.safetensors", "model.layers.94.input_layernorm.weight": "model-00015-of-00019.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00015-of-00019.safetensors", "model.layers.60.self_attn.v_proj.bias": "model-00015-of-00019.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00015-of-00019.safetensors", "model.layers.60.self_attn.q_proj.bias": "model-00015-of-00019.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00015-of-00019.safetensors", "model.layers.60.self_attn.k_proj.bias": "model-00015-of-00019.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00015-of-00019.safetensors", "model.layers.59.self_attn.v_proj.bias": "model-00015-of-00019.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00015-of-00019.safetensors", "model.layers.59.self_attn.q_proj.bias": "model-00015-of-00019.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00015-of-00019.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00015-of-00019.safetensors", "model.layers.59.self_attn.k_proj.bias": "model-00015-of-00019.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00015-of-00019.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00015-of-00019.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00015-of-00019.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00015-of-00019.safetensors", "model.layers.59.input_layernorm.weight": "model-00015-of-00019.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00015-of-00019.safetensors", "model.layers.58.self_attn.v_proj.bias": "model-00015-of-00019.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00015-of-00019.safetensors", "model.layers.58.self_attn.q_proj.bias": "model-00015-of-00019.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00015-of-00019.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00015-of-00019.safetensors", "model.layers.58.self_attn.k_proj.bias": "model-00015-of-00019.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00015-of-00019.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00015-of-00019.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00015-of-00019.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00015-of-00019.safetensors", "model.layers.58.input_layernorm.weight": "model-00015-of-00019.safetensors", "model.layers.99.self_attn.v_proj.weight": "model-00015-of-00019.safetensors", "model.layers.99.self_attn.v_proj.bias": "model-00015-of-00019.safetensors", "model.layers.99.self_attn.q_proj.weight": "model-00015-of-00019.safetensors", "model.layers.99.self_attn.q_proj.bias": "model-00015-of-00019.safetensors", "model.layers.99.self_attn.o_proj.weight": "model-00015-of-00019.safetensors", "model.layers.99.self_attn.k_proj.weight": "model-00015-of-00019.safetensors", "model.layers.99.self_attn.k_proj.bias": "model-00015-of-00019.safetensors", "model.layers.99.mlp.up_proj.weight": "model-00015-of-00019.safetensors", "model.layers.99.mlp.gate_proj.weight": "model-00015-of-00019.safetensors", "model.layers.98.self_attn.v_proj.weight": "model-00015-of-00019.safetensors", "model.layers.98.self_attn.v_proj.bias": "model-00015-of-00019.safetensors", "model.layers.98.self_attn.q_proj.weight": "model-00015-of-00019.safetensors", "model.layers.98.self_attn.q_proj.bias": "model-00015-of-00019.safetensors", "model.layers.98.self_attn.o_proj.weight": "model-00016-of-00019.safetensors", "model.layers.98.self_attn.k_proj.weight": "model-00016-of-00019.safetensors", "model.layers.98.self_attn.k_proj.bias": "model-00016-of-00019.safetensors", "model.layers.98.post_attention_layernorm.weight": "model-00016-of-00019.safetensors", "model.layers.98.mlp.up_proj.weight": "model-00016-of-00019.safetensors", "model.layers.98.mlp.gate_proj.weight": "model-00016-of-00019.safetensors", "model.layers.98.mlp.down_proj.weight": "model-00016-of-00019.safetensors", "model.layers.98.input_layernorm.weight": "model-00016-of-00019.safetensors", "model.layers.97.self_attn.v_proj.weight": "model-00016-of-00019.safetensors", "model.layers.97.self_attn.v_proj.bias": "model-00016-of-00019.safetensors", "model.layers.97.self_attn.q_proj.weight": "model-00016-of-00019.safetensors", "model.layers.97.self_attn.q_proj.bias": "model-00016-of-00019.safetensors", "model.layers.97.self_attn.o_proj.weight": "model-00016-of-00019.safetensors", "model.layers.97.self_attn.k_proj.weight": "model-00016-of-00019.safetensors", "model.layers.97.self_attn.k_proj.bias": "model-00016-of-00019.safetensors", "model.layers.97.post_attention_layernorm.weight": "model-00016-of-00019.safetensors", "model.layers.97.mlp.up_proj.weight": "model-00016-of-00019.safetensors", "model.layers.97.mlp.gate_proj.weight": "model-00016-of-00019.safetensors", "model.layers.97.mlp.down_proj.weight": "model-00016-of-00019.safetensors", "model.layers.97.input_layernorm.weight": "model-00016-of-00019.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00016-of-00019.safetensors", "model.layers.62.self_attn.v_proj.bias": "model-00016-of-00019.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00016-of-00019.safetensors", "model.layers.62.self_attn.q_proj.bias": "model-00016-of-00019.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00016-of-00019.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00016-of-00019.safetensors", "model.layers.62.self_attn.k_proj.bias": "model-00016-of-00019.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00016-of-00019.safetensors", "model.layers.61.self_attn.v_proj.bias": "model-00016-of-00019.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00016-of-00019.safetensors", "model.layers.61.self_attn.q_proj.bias": "model-00016-of-00019.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00016-of-00019.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00016-of-00019.safetensors", "model.layers.61.self_attn.k_proj.bias": "model-00016-of-00019.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00016-of-00019.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00016-of-00019.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00016-of-00019.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00016-of-00019.safetensors", "model.layers.61.input_layernorm.weight": "model-00016-of-00019.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00016-of-00019.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00016-of-00019.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00016-of-00019.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00016-of-00019.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00016-of-00019.safetensors", "model.layers.60.input_layernorm.weight": "model-00016-of-00019.safetensors", "lm_head.weight": "model-00016-of-00019.safetensors", "model.norm.weight": "model-00016-of-00019.safetensors", "model.layers.99.post_attention_layernorm.weight": "model-00016-of-00019.safetensors", "model.layers.99.mlp.down_proj.weight": "model-00016-of-00019.safetensors", "model.layers.99.input_layernorm.weight": "model-00016-of-00019.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00016-of-00019.safetensors", "model.layers.64.self_attn.v_proj.bias": "model-00016-of-00019.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00017-of-00019.safetensors", "model.layers.64.self_attn.q_proj.bias": "model-00017-of-00019.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00017-of-00019.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00017-of-00019.safetensors", "model.layers.64.self_attn.k_proj.bias": "model-00017-of-00019.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00017-of-00019.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00017-of-00019.safetensors", "model.layers.63.self_attn.v_proj.bias": "model-00017-of-00019.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00017-of-00019.safetensors", "model.layers.63.self_attn.q_proj.bias": "model-00017-of-00019.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00017-of-00019.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00017-of-00019.safetensors", "model.layers.63.self_attn.k_proj.bias": "model-00017-of-00019.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00017-of-00019.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00017-of-00019.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00017-of-00019.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00017-of-00019.safetensors", "model.layers.63.input_layernorm.weight": "model-00017-of-00019.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00017-of-00019.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00017-of-00019.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00017-of-00019.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00017-of-00019.safetensors", "model.layers.62.input_layernorm.weight": "model-00017-of-00019.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00017-of-00019.safetensors", "model.layers.66.self_attn.v_proj.bias": "model-00017-of-00019.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00017-of-00019.safetensors", "model.layers.66.self_attn.q_proj.bias": "model-00017-of-00019.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00017-of-00019.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00017-of-00019.safetensors", "model.layers.66.self_attn.k_proj.bias": "model-00017-of-00019.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00017-of-00019.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00017-of-00019.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00017-of-00019.safetensors", "model.layers.65.self_attn.v_proj.bias": "model-00017-of-00019.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00017-of-00019.safetensors", "model.layers.65.self_attn.q_proj.bias": "model-00017-of-00019.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00017-of-00019.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00017-of-00019.safetensors", "model.layers.65.self_attn.k_proj.bias": "model-00017-of-00019.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00017-of-00019.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00017-of-00019.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00017-of-00019.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00017-of-00019.safetensors", "model.layers.65.input_layernorm.weight": "model-00017-of-00019.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00017-of-00019.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00017-of-00019.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00017-of-00019.safetensors", "model.layers.64.input_layernorm.weight": "model-00017-of-00019.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00017-of-00019.safetensors", "model.layers.68.self_attn.v_proj.bias": "model-00017-of-00019.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00017-of-00019.safetensors", "model.layers.68.self_attn.q_proj.bias": "model-00017-of-00019.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00017-of-00019.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00017-of-00019.safetensors", "model.layers.68.self_attn.k_proj.bias": "model-00017-of-00019.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00017-of-00019.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00017-of-00019.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00017-of-00019.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00017-of-00019.safetensors", "model.layers.68.input_layernorm.weight": "model-00017-of-00019.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00017-of-00019.safetensors", "model.layers.67.self_attn.v_proj.bias": "model-00017-of-00019.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00017-of-00019.safetensors", "model.layers.67.self_attn.q_proj.bias": "model-00017-of-00019.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00017-of-00019.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00017-of-00019.safetensors", "model.layers.67.self_attn.k_proj.bias": "model-00017-of-00019.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00017-of-00019.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00018-of-00019.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00018-of-00019.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00018-of-00019.safetensors", "model.layers.67.input_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00018-of-00019.safetensors", "model.layers.66.input_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.71.self_attn.v_proj.bias": "model-00018-of-00019.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.71.self_attn.q_proj.bias": "model-00018-of-00019.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.71.self_attn.k_proj.bias": "model-00018-of-00019.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.70.self_attn.v_proj.bias": "model-00018-of-00019.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.70.self_attn.q_proj.bias": "model-00018-of-00019.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00018-of-00019.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.70.self_attn.k_proj.bias": "model-00018-of-00019.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00018-of-00019.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00018-of-00019.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00018-of-00019.safetensors", "model.layers.70.input_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.69.self_attn.v_proj.bias": "model-00018-of-00019.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.69.self_attn.q_proj.bias": "model-00018-of-00019.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00018-of-00019.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.69.self_attn.k_proj.bias": "model-00018-of-00019.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00018-of-00019.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00018-of-00019.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00018-of-00019.safetensors", "model.layers.69.input_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.73.self_attn.v_proj.bias": "model-00018-of-00019.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.73.self_attn.q_proj.bias": "model-00018-of-00019.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00018-of-00019.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.73.self_attn.k_proj.bias": "model-00018-of-00019.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.72.self_attn.v_proj.bias": "model-00018-of-00019.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.72.self_attn.q_proj.bias": "model-00018-of-00019.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00018-of-00019.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.72.self_attn.k_proj.bias": "model-00018-of-00019.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.72.mlp.up_proj.weight": "model-00018-of-00019.safetensors", "model.layers.72.mlp.gate_proj.weight": "model-00018-of-00019.safetensors", "model.layers.72.mlp.down_proj.weight": "model-00018-of-00019.safetensors", "model.layers.72.input_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00018-of-00019.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00018-of-00019.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00018-of-00019.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00018-of-00019.safetensors", "model.layers.71.input_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.74.self_attn.v_proj.bias": "model-00018-of-00019.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.74.self_attn.q_proj.bias": "model-00018-of-00019.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00018-of-00019.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.74.self_attn.k_proj.bias": "model-00018-of-00019.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.74.mlp.up_proj.weight": "model-00019-of-00019.safetensors", "model.layers.74.mlp.gate_proj.weight": "model-00019-of-00019.safetensors", "model.layers.74.mlp.down_proj.weight": "model-00019-of-00019.safetensors", "model.layers.74.input_layernorm.weight": "model-00019-of-00019.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00019-of-00019.safetensors", "model.layers.73.mlp.up_proj.weight": "model-00019-of-00019.safetensors", "model.layers.73.mlp.gate_proj.weight": "model-00019-of-00019.safetensors", "model.layers.73.mlp.down_proj.weight": "model-00019-of-00019.safetensors", "model.layers.73.input_layernorm.weight": "model-00019-of-00019.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = 'You are a helpful assistant.' %}{% endif %}{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in loop_messages %}{% if loop.index0 == 0 %}{{'<|im_start|>system\n' + system_message + '<|im_end|>\n'}}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}