{ "metadata": { "ParamSize": 709, "ParamBytes": 18431289344.0, "BitsPerParam": 4.500392846312253 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 389283840, "records": [ { "name": "model.embed_tokens.q_weight", "shape": [ 152064, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 389283840, "byteOffset": 0 } ], "md5sum": "6ee326c7ee286bf91634db03bb2135b6" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 48660480, "records": [ { "name": "model.embed_tokens.q_scale", "shape": [ 152064, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 48660480, "byteOffset": 0 } ], "md5sum": "6b76891a9714803fee683395433fc836" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 20658176, "records": [ { "name": "model.layers.0.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 0 }, { "name": "model.layers.0.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 14336 }, { "name": "model.layers.0.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 18364416 } ], "md5sum": "95ddde814c8b502d816cc49d146be92b" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "c82af1953da237756230d4fd89e17a9c" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "1eb9aaf330403ec6c4b0072f321118f4" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 32440320, "records": [ { "name": "model.layers.0.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14745600 } ], "md5sum": "e5087830e71b388a776c04c7810bc011" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 29526016, "records": [ { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8847360 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8857600 }, { "name": "model.layers.1.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8867840 }, { "name": "model.layers.1.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8882176 }, { "name": "model.layers.1.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 27232256 } ], "md5sum": "291e576fb82c73b1bc0fe1e1c1a34a94" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "3b4be0596823a5dc1c859ccf77298e22" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.1.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "e26509237cd398772ff2b090557e1d47" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 32440320, "records": [ { "name": "model.layers.1.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.1.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.1.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14745600 } ], "md5sum": "16729161a5697c52d42257450702b51c" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 29526016, "records": [ { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8847360 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8857600 }, { "name": "model.layers.2.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8867840 }, { "name": "model.layers.2.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8882176 }, { "name": "model.layers.2.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 27232256 } ], "md5sum": "6764fa6f9d8662d9f4c12da6818f2c71" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "a4fa08d4acb5cdde96f6b736e9d5e9e0" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.2.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "085a0fb45015fcd24298933023292c77" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 32440320, "records": [ { "name": "model.layers.2.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.2.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.2.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14745600 } ], "md5sum": "b8a3bc3cc260361940d956f9aa687cda" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 29526016, "records": [ { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8847360 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8857600 }, { "name": "model.layers.3.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8867840 }, { "name": "model.layers.3.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8882176 }, { "name": "model.layers.3.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 27232256 } ], "md5sum": "059f306bc1ed8ac0cabb01174e5aac04" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "ea84d0f35e6d01848009adf0d003d2df" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.3.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "55d8bc9b7c8dce1571fe75ac286f1e88" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 32440320, "records": [ { "name": "model.layers.3.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.3.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14745600 } ], "md5sum": "5de42c13907110daa3d820f18ee12a00" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 29526016, "records": [ { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8847360 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8857600 }, { "name": "model.layers.4.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8867840 }, { "name": "model.layers.4.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8882176 }, { "name": "model.layers.4.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 27232256 } ], "md5sum": "9a6c9306c62c6dfff4a8f4391c0480de" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "9ced09023d88a036c2d6326669599ba5" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.4.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "e83cdb79752c8f4a8b9ceb489c5739ca" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 32440320, "records": [ { "name": "model.layers.4.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.4.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.4.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14745600 } ], "md5sum": "ad1e67a73ec3be0205aa0f9e7995a8bc" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 29526016, "records": [ { "name": "model.layers.4.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8847360 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8857600 }, { "name": "model.layers.5.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8867840 }, { "name": "model.layers.5.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8882176 }, { "name": "model.layers.5.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 27232256 } ], "md5sum": "2aa6d8f2f841fc2c13d2878a08f7ecb7" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "da44c1e725d01b4066a529075fdcf5b0" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.5.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "f485013f06ff819547912826187ad001" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 32440320, "records": [ { "name": "model.layers.5.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.5.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.5.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14745600 } ], "md5sum": "a272be2be7575ea20b45db1c68d52faf" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 29526016, "records": [ { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8847360 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8857600 }, { "name": "model.layers.6.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8867840 }, { "name": "model.layers.6.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8882176 }, { "name": "model.layers.6.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 27232256 } ], "md5sum": "9a9f36c6f2c76258509b14a5594bb49c" }, { "dataPath": "params_shard_27.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "1e5399d471f3c7f995fa21b2d9de572b" }, { "dataPath": "params_shard_28.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.6.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "c753f18d4eea17263de9eb7676944a4c" }, { "dataPath": "params_shard_29.bin", "format": "raw-shard", "nbytes": 32440320, "records": [ { "name": "model.layers.6.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.6.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14745600 } ], "md5sum": "c41ff3e3a2e0bc1caa4eede8405b9711" }, { "dataPath": "params_shard_30.bin", "format": "raw-shard", "nbytes": 29526016, "records": [ { "name": "model.layers.6.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8847360 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8857600 }, { "name": "model.layers.7.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8867840 }, { "name": "model.layers.7.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8882176 }, { "name": "model.layers.7.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 27232256 } ], "md5sum": "fc6c40cb07d7efe54031ae47a9feeb92" }, { "dataPath": "params_shard_31.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "744067a23cbbcb5049c23fd18beb92bf" }, { "dataPath": "params_shard_32.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.7.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "820940f9f06a90ff082eef3ede723e63" }, { "dataPath": "params_shard_33.bin", "format": "raw-shard", "nbytes": 32440320, "records": [ { "name": "model.layers.7.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.7.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.7.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14745600 } ], "md5sum": "2e0cc169b7d0530a7677cede381639e3" }, { "dataPath": "params_shard_34.bin", "format": "raw-shard", "nbytes": 29526016, "records": [ { "name": "model.layers.7.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8847360 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8857600 }, { "name": "model.layers.8.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8867840 }, { "name": "model.layers.8.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8882176 }, { "name": "model.layers.8.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 27232256 } ], "md5sum": "485cdf12841be21ff1a8a0320f62d717" }, { "dataPath": "params_shard_35.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "ed78cee85d198e6d3481c9749a7b34fb" }, { "dataPath": "params_shard_36.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.8.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "ef6ae6675f5da5f9d40c1b3b3d80927e" }, { "dataPath": "params_shard_37.bin", "format": "raw-shard", "nbytes": 32440320, "records": [ { "name": "model.layers.8.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.8.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.8.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14745600 } ], "md5sum": "2dd8691c132ce04cb0ae0f00ae23655a" }, { "dataPath": "params_shard_38.bin", "format": "raw-shard", "nbytes": 29526016, "records": [ { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8847360 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8857600 }, { "name": "model.layers.9.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8867840 }, { "name": "model.layers.9.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8882176 }, { "name": "model.layers.9.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 27232256 } ], "md5sum": "c95390d981177e5aaff087527c2378eb" }, { "dataPath": "params_shard_39.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "bd64dd135c16256a337195e67aceece6" }, { "dataPath": "params_shard_40.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.9.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "4eb3143a428b7acb4f08394d6f3df98d" }, { "dataPath": "params_shard_41.bin", "format": "raw-shard", "nbytes": 32440320, "records": [ { "name": "model.layers.9.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.9.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.9.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14745600 } ], "md5sum": "c756beaa7641a1ddcad0fd00f50616b8" }, { "dataPath": "params_shard_42.bin", "format": "raw-shard", "nbytes": 29526016, "records": [ { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8847360 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8857600 }, { "name": "model.layers.10.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8867840 }, { "name": "model.layers.10.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8882176 }, { "name": "model.layers.10.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 27232256 } ], "md5sum": "81a061acca4847a186096c446fa88497" }, { "dataPath": "params_shard_43.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "0eed2b51546566f0c9ca148e3c596387" }, { "dataPath": "params_shard_44.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.10.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "5558dac1ddd7cdd4a44ece11b33a658c" }, { "dataPath": "params_shard_45.bin", "format": "raw-shard", "nbytes": 32440320, "records": [ { "name": "model.layers.10.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.10.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14745600 } ], "md5sum": "d93b153e9ef10762210814cb543ae58c" }, { "dataPath": "params_shard_46.bin", "format": "raw-shard", "nbytes": 29526016, "records": [ { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8847360 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8857600 }, { "name": "model.layers.11.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8867840 }, { "name": "model.layers.11.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8882176 }, { "name": "model.layers.11.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 27232256 } ], "md5sum": "94ccabc8f70b78a23a208821c47a77eb" }, { "dataPath": "params_shard_47.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "2ea1fa0998b5ec9133e403e17b3793fa" }, { "dataPath": "params_shard_48.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.11.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "7d1143a2d3009bbff29bbd7e7a9a4da3" }, { "dataPath": "params_shard_49.bin", "format": "raw-shard", "nbytes": 32440320, "records": [ { "name": "model.layers.11.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.11.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.11.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14745600 } ], "md5sum": "1ffa05c0b5c29ad4aeb05a2f28623b0f" }, { "dataPath": "params_shard_50.bin", "format": "raw-shard", "nbytes": 29526016, "records": [ { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8847360 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8857600 }, { "name": "model.layers.12.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8867840 }, { "name": "model.layers.12.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8882176 }, { "name": "model.layers.12.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 27232256 } ], "md5sum": "12b9cc1b4b9e2ce1849f4add9d333ad8" }, { "dataPath": "params_shard_51.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "784b992e3cc0af30fc9d39f1155decf7" }, { "dataPath": "params_shard_52.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.12.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "57aa03557a459086b3d1100f151cbde4" }, { "dataPath": "params_shard_53.bin", "format": "raw-shard", "nbytes": 32440320, "records": [ { "name": "model.layers.12.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.12.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.12.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14745600 } ], "md5sum": "95767a5ac866fc69a6e86f2bdf30c343" }, { "dataPath": "params_shard_54.bin", "format": "raw-shard", "nbytes": 29526016, "records": [ { "name": "model.layers.12.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8847360 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8857600 }, { "name": "model.layers.13.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8867840 }, { "name": "model.layers.13.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8882176 }, { "name": "model.layers.13.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 27232256 } ], "md5sum": "d251d06fbb5aa1236778ccfa0909d1e0" }, { "dataPath": "params_shard_55.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "118904e89be1282539e67031dff9a9a4" }, { "dataPath": "params_shard_56.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.13.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "7c19732ba3c390d4d724ab3ae6dd1cd6" }, { "dataPath": "params_shard_57.bin", "format": "raw-shard", "nbytes": 32440320, "records": [ { "name": "model.layers.13.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.13.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.13.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14745600 } ], "md5sum": "3af6c0081fbee67d264a39767b23d87a" }, { "dataPath": "params_shard_58.bin", "format": "raw-shard", "nbytes": 29526016, "records": [ { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8847360 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8857600 }, { "name": "model.layers.14.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8867840 }, { "name": "model.layers.14.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8882176 }, { "name": "model.layers.14.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 27232256 } ], "md5sum": "d7a17aae08b2b784f04cc5ee9ef51a0b" }, { "dataPath": "params_shard_59.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "63e056de878cb11cdc7edf74f3a43eda" }, { "dataPath": "params_shard_60.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.14.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "b05708d5ed8b24678b32241410ca747c" }, { "dataPath": "params_shard_61.bin", "format": "raw-shard", "nbytes": 32440320, "records": [ { "name": "model.layers.14.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.14.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14745600 } ], "md5sum": "0cd7299d66fe460092d1b5ad144524e6" }, { "dataPath": "params_shard_62.bin", "format": "raw-shard", "nbytes": 29526016, "records": [ { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8847360 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8857600 }, { "name": "model.layers.15.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8867840 }, { "name": "model.layers.15.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8882176 }, { "name": "model.layers.15.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 27232256 } ], "md5sum": "6d3a91459f887fd1537a0155d95b7eb4" }, { "dataPath": "params_shard_63.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "b10d01f2068b325aadc2a2a1f97c1bd5" }, { "dataPath": "params_shard_64.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.15.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "2dbfa9f77d62ca4d8203406e6548e4be" }, { "dataPath": "params_shard_65.bin", "format": "raw-shard", "nbytes": 32440320, "records": [ { "name": "model.layers.15.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.15.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.15.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14745600 } ], "md5sum": "4d775744d18750f09d0eca25bbdad6f5" }, { "dataPath": "params_shard_66.bin", "format": "raw-shard", "nbytes": 29526016, "records": [ { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8847360 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8857600 }, { "name": "model.layers.16.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8867840 }, { "name": "model.layers.16.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8882176 }, { "name": "model.layers.16.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 27232256 } ], "md5sum": "c45ee6f050bbcacefc10b5be0bda6c19" }, { "dataPath": "params_shard_67.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "c063301754ad25eef6c7c850e9ddc7c7" }, { "dataPath": "params_shard_68.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.16.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "60c04dca2179ef6d53ba48219d6ef06d" }, { "dataPath": "params_shard_69.bin", "format": "raw-shard", "nbytes": 32440320, "records": [ { "name": "model.layers.16.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.16.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.16.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14745600 } ], "md5sum": "c60662118f4a93fe28fc41f49fb11e5e" }, { "dataPath": "params_shard_70.bin", "format": "raw-shard", "nbytes": 29526016, "records": [ { "name": "model.layers.16.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8847360 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8857600 }, { "name": "model.layers.17.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8867840 }, { "name": "model.layers.17.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8882176 }, { "name": "model.layers.17.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 27232256 } ], "md5sum": "1ba2d5560e945d59c907d57242af00f0" }, { "dataPath": "params_shard_71.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "0c7cfca6f7d42464d10317c677a9953f" }, { "dataPath": "params_shard_72.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.17.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "6c383dcf8f1b5042126dc37b1e539828" }, { "dataPath": "params_shard_73.bin", "format": "raw-shard", "nbytes": 32440320, "records": [ { "name": "model.layers.17.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.17.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.17.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14745600 } ], "md5sum": "603527736f15d745a5aa8c923050f7ca" }, { "dataPath": "params_shard_74.bin", "format": "raw-shard", "nbytes": 29526016, "records": [ { "name": "model.layers.17.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8847360 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8857600 }, { "name": "model.layers.18.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8867840 }, { "name": "model.layers.18.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8882176 }, { "name": "model.layers.18.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 27232256 } ], "md5sum": "087047bd31ac22caa554eb11f2602342" }, { "dataPath": "params_shard_75.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "58edcf0eb9b30161a143a70c15b60168" }, { "dataPath": "params_shard_76.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.18.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "6598cba13804e9a12262957e7333b8bd" }, { "dataPath": "params_shard_77.bin", "format": "raw-shard", "nbytes": 32440320, "records": [ { "name": "model.layers.18.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.18.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.18.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14745600 } ], "md5sum": "a26adf7557950bc529c5c5b168721476" }, { "dataPath": "params_shard_78.bin", "format": "raw-shard", "nbytes": 29526016, "records": [ { "name": "model.layers.18.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8847360 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8857600 }, { "name": "model.layers.19.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8867840 }, { "name": "model.layers.19.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8882176 }, { "name": "model.layers.19.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 27232256 } ], "md5sum": "e678e95bd1d70fe49246fc88b9800f2f" }, { "dataPath": "params_shard_79.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "28910bdb031e6b79e728fd58c1df586b" }, { "dataPath": "params_shard_80.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.19.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "d0077ef98077c7e3aee8a98437265c45" }, { "dataPath": "params_shard_81.bin", "format": "raw-shard", "nbytes": 32440320, "records": [ { "name": "model.layers.19.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.19.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.19.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14745600 } ], "md5sum": "e631cfdcbedb9abcb0e0831a1da7bd87" }, { "dataPath": "params_shard_82.bin", "format": "raw-shard", "nbytes": 29526016, "records": [ { "name": "model.layers.19.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8847360 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8857600 }, { "name": "model.layers.20.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8867840 }, { "name": "model.layers.20.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8882176 }, { "name": "model.layers.20.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 27232256 } ], "md5sum": "93c89fc27c5e04d97243ef94788c22b6" }, { "dataPath": "params_shard_83.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "52f55a87b1e0b19a7068d30f911d7ffc" }, { "dataPath": "params_shard_84.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.20.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "583d581d3debc0fe0a64ceb62e1d68ff" }, { "dataPath": "params_shard_85.bin", "format": "raw-shard", "nbytes": 32440320, "records": [ { "name": "model.layers.20.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.20.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.20.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14745600 } ], "md5sum": "d296b76daa63bbdd1d38818ebb6ff0c0" }, { "dataPath": "params_shard_86.bin", "format": "raw-shard", "nbytes": 29526016, "records": [ { "name": "model.layers.20.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8847360 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8857600 }, { "name": "model.layers.21.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8867840 }, { "name": "model.layers.21.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8882176 }, { "name": "model.layers.21.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 27232256 } ], "md5sum": "da66e0a51a8f6cd0873aad2aceb6e3fb" }, { "dataPath": "params_shard_87.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "6aa9f66c479ac7c32c0463b2bb35ae62" }, { "dataPath": "params_shard_88.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.21.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "8d6730a34a68b49906d918da6bddbe72" }, { "dataPath": "params_shard_89.bin", "format": "raw-shard", "nbytes": 32440320, "records": [ { "name": "model.layers.21.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.21.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.21.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14745600 } ], "md5sum": "be3f1948773dd58b8f5da57bfa7230a5" }, { "dataPath": "params_shard_90.bin", "format": "raw-shard", "nbytes": 29526016, "records": [ { "name": "model.layers.21.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8847360 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8857600 }, { "name": "model.layers.22.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8867840 }, { "name": "model.layers.22.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8882176 }, { "name": "model.layers.22.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 27232256 } ], "md5sum": "741e6e27d5b4c69cbc74119f1475c276" }, { "dataPath": "params_shard_91.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "4d04b1c954e7c7dbcbb1f8dea47e2b73" }, { "dataPath": "params_shard_92.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.22.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "89c756eb45682fc861779dbc579bd6c1" }, { "dataPath": "params_shard_93.bin", "format": "raw-shard", "nbytes": 32440320, "records": [ { "name": "model.layers.22.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.22.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.22.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14745600 } ], "md5sum": "6b59462b8b139ec0cc3b96ff839ee0dc" }, { "dataPath": "params_shard_94.bin", "format": "raw-shard", "nbytes": 29526016, "records": [ { "name": "model.layers.22.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8847360 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8857600 }, { "name": "model.layers.23.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8867840 }, { "name": "model.layers.23.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8882176 }, { "name": "model.layers.23.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 27232256 } ], "md5sum": "da31fc128190ec8ad7d23456c28d47b0" }, { "dataPath": "params_shard_95.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "70e982102766418eb87125e4211fb805" }, { "dataPath": "params_shard_96.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.23.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "4f5e11f7064c23ab8c6c01b53d980621" }, { "dataPath": "params_shard_97.bin", "format": "raw-shard", "nbytes": 32440320, "records": [ { "name": "model.layers.23.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.23.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.23.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14745600 } ], "md5sum": "610494ca7a0f9a9ce3f2a588e01c0b75" }, { "dataPath": "params_shard_98.bin", "format": "raw-shard", "nbytes": 29526016, "records": [ { "name": "model.layers.23.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8847360 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8857600 }, { "name": "model.layers.24.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8867840 }, { "name": "model.layers.24.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8882176 }, { "name": "model.layers.24.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 27232256 } ], "md5sum": "3c33187d879d71f350601ce079edcfaf" }, { "dataPath": "params_shard_99.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "d2d9413153d2ef6b8e59ed1471d3d2ce" }, { "dataPath": "params_shard_100.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.24.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "fb720a76efe770fa868f4a4eff63d242" }, { "dataPath": "params_shard_101.bin", "format": "raw-shard", "nbytes": 32440320, "records": [ { "name": "model.layers.24.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.24.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.24.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14745600 } ], "md5sum": "ab8f9097170d4896cbcb152b1ce287d1" }, { "dataPath": "params_shard_102.bin", "format": "raw-shard", "nbytes": 29526016, "records": [ { "name": "model.layers.24.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.24.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8847360 }, { "name": "model.layers.24.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8857600 }, { "name": "model.layers.25.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8867840 }, { "name": "model.layers.25.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8882176 }, { "name": "model.layers.25.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 27232256 } ], "md5sum": "2fe0c777c05b5ebe2294ce51a31d9f70" }, { "dataPath": "params_shard_103.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "7d7260c289f20d4f480edfc901e67f6c" }, { "dataPath": "params_shard_104.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.25.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "ee0c9145ff88d47a814a720a9d75fd84" }, { "dataPath": "params_shard_105.bin", "format": "raw-shard", "nbytes": 32440320, "records": [ { "name": "model.layers.25.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.25.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.25.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14745600 } ], "md5sum": "f63edfcb706d6f4981b5c8374c6aedac" }, { "dataPath": "params_shard_106.bin", "format": "raw-shard", "nbytes": 29526016, "records": [ { "name": "model.layers.25.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.25.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8847360 }, { "name": "model.layers.25.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8857600 }, { "name": "model.layers.26.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8867840 }, { "name": "model.layers.26.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8882176 }, { "name": "model.layers.26.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 27232256 } ], "md5sum": "18a5f7714c4d6abba0d99270746e0284" }, { "dataPath": "params_shard_107.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "778d6edec20120c1c194f64cc73813fd" }, { "dataPath": "params_shard_108.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.26.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "f1d81d81b2490c02fec8b261d70d79fe" }, { "dataPath": "params_shard_109.bin", "format": "raw-shard", "nbytes": 32440320, "records": [ { "name": "model.layers.26.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.26.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.26.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14745600 } ], "md5sum": "8299fe99ad556773e236577676e6ff4a" }, { "dataPath": "params_shard_110.bin", "format": "raw-shard", "nbytes": 29526016, "records": [ { "name": "model.layers.26.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.26.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8847360 }, { "name": "model.layers.26.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8857600 }, { "name": "model.layers.27.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8867840 }, { "name": "model.layers.27.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8882176 }, { "name": "model.layers.27.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 27232256 } ], "md5sum": "5a17be743f947dead08ccafe02bc6b72" }, { "dataPath": "params_shard_111.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.27.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "eb179123476f10e809925ba55c7d7807" }, { "dataPath": "params_shard_112.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.27.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "97abcadd40a010a32b46d1664f041d09" }, { "dataPath": "params_shard_113.bin", "format": "raw-shard", "nbytes": 32440320, "records": [ { "name": "model.layers.27.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.27.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.27.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14745600 } ], "md5sum": "2dc49a76e75314e0d600151f4fc54708" }, { "dataPath": "params_shard_114.bin", "format": "raw-shard", "nbytes": 29526016, "records": [ { "name": "model.layers.27.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.27.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8847360 }, { "name": "model.layers.27.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8857600 }, { "name": "model.layers.28.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8867840 }, { "name": "model.layers.28.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8882176 }, { "name": "model.layers.28.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 27232256 } ], "md5sum": "4678cabe283e0b11dda061ba2c253ccb" }, { "dataPath": "params_shard_115.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.28.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "f17b5abcfad68a3a243cfd113761c557" }, { "dataPath": "params_shard_116.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.28.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "41d5e5790d134fd83134f789d41e6207" }, { "dataPath": "params_shard_117.bin", "format": "raw-shard", "nbytes": 32440320, "records": [ { "name": "model.layers.28.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.28.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.28.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14745600 } ], "md5sum": "72f5653812b2dd5b4ad2fc336721f848" }, { "dataPath": "params_shard_118.bin", "format": "raw-shard", "nbytes": 29526016, "records": [ { "name": "model.layers.28.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.28.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8847360 }, { "name": "model.layers.28.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8857600 }, { "name": "model.layers.29.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8867840 }, { "name": "model.layers.29.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8882176 }, { "name": "model.layers.29.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 27232256 } ], "md5sum": "45e3ba11dfc87b399949bcd5c5178a63" }, { "dataPath": "params_shard_119.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.29.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "8a682d85382d11402b797fed41949ff2" }, { "dataPath": "params_shard_120.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.29.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "a088581acc08b02e9ee3411584796101" }, { "dataPath": "params_shard_121.bin", "format": "raw-shard", "nbytes": 32440320, "records": [ { "name": "model.layers.29.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.29.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.29.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14745600 } ], "md5sum": "3a555462080a96bc2b20d6fb28529ac4" }, { "dataPath": "params_shard_122.bin", "format": "raw-shard", "nbytes": 29526016, "records": [ { "name": "model.layers.29.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.29.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8847360 }, { "name": "model.layers.29.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8857600 }, { "name": "model.layers.30.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8867840 }, { "name": "model.layers.30.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8882176 }, { "name": "model.layers.30.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 27232256 } ], "md5sum": "3c28e6b45335d87bda64be87610241e4" }, { "dataPath": "params_shard_123.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.30.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "dcd063586b81dc248ef3f50a05e50df0" }, { "dataPath": "params_shard_124.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.30.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "b34761e212d24c75c3f3b584458a34de" }, { "dataPath": "params_shard_125.bin", "format": "raw-shard", "nbytes": 32440320, "records": [ { "name": "model.layers.30.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.30.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.30.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14745600 } ], "md5sum": "dfd2ae956d187595a3337ac68efe3874" }, { "dataPath": "params_shard_126.bin", "format": "raw-shard", "nbytes": 29526016, "records": [ { "name": "model.layers.30.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.30.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8847360 }, { "name": "model.layers.30.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8857600 }, { "name": "model.layers.31.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8867840 }, { "name": "model.layers.31.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8882176 }, { "name": "model.layers.31.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 27232256 } ], "md5sum": "a16f4ff50739dd46a93e63ed585639e7" }, { "dataPath": "params_shard_127.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.31.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "3822ee56b3bcd165f9603f2c4d7f76d9" }, { "dataPath": "params_shard_128.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.31.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "30e53d2b950a470a2f770eeb9f2f9e1b" }, { "dataPath": "params_shard_129.bin", "format": "raw-shard", "nbytes": 32440320, "records": [ { "name": "model.layers.31.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.31.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.31.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14745600 } ], "md5sum": "2c135e5510a4119082cbf83071a94cd5" }, { "dataPath": "params_shard_130.bin", "format": "raw-shard", "nbytes": 29526016, "records": [ { "name": "model.layers.31.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.31.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8847360 }, { "name": "model.layers.31.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8857600 }, { "name": "model.layers.32.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8867840 }, { "name": "model.layers.32.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8882176 }, { "name": "model.layers.32.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 27232256 } ], "md5sum": "8b9ccabf4b2cc85c4eb15890909ec8bc" }, { "dataPath": "params_shard_131.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.32.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "8e14f50f663be627d5e9dbeed807546e" }, { "dataPath": "params_shard_132.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.32.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "fd7d748fa2378433808e2fac859b1e2d" }, { "dataPath": "params_shard_133.bin", "format": "raw-shard", "nbytes": 32440320, "records": [ { "name": "model.layers.32.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.32.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.32.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14745600 } ], "md5sum": "ca5cd4c7ed53f5722ad03df87cfb8b4a" }, { "dataPath": "params_shard_134.bin", "format": "raw-shard", "nbytes": 29526016, "records": [ { "name": "model.layers.32.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.32.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8847360 }, { "name": "model.layers.32.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8857600 }, { "name": "model.layers.33.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8867840 }, { "name": "model.layers.33.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8882176 }, { "name": "model.layers.33.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 27232256 } ], "md5sum": "a1b2df5433b3f9555d5cec6cc2410f1e" }, { "dataPath": "params_shard_135.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.33.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "ab39abd2ebb5cb422c0ed7cab7c182fb" }, { "dataPath": "params_shard_136.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.33.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "128aaed909f5f848a889e46c7fef5f0b" }, { "dataPath": "params_shard_137.bin", "format": "raw-shard", "nbytes": 32440320, "records": [ { "name": "model.layers.33.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.33.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.33.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14745600 } ], "md5sum": "ded36c09ec4d55501df8a80f27692be3" }, { "dataPath": "params_shard_138.bin", "format": "raw-shard", "nbytes": 29526016, "records": [ { "name": "model.layers.33.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.33.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8847360 }, { "name": "model.layers.33.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8857600 }, { "name": "model.layers.34.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8867840 }, { "name": "model.layers.34.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8882176 }, { "name": "model.layers.34.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 27232256 } ], "md5sum": "0fe9bd0408e940553596be839a720f60" }, { "dataPath": "params_shard_139.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.34.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "93f426074bc1a45ee0401d5c9cb89ac0" }, { "dataPath": "params_shard_140.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.34.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "29b97f38c376dcac7a99886a77d14b46" }, { "dataPath": "params_shard_141.bin", "format": "raw-shard", "nbytes": 32440320, "records": [ { "name": "model.layers.34.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.34.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.34.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14745600 } ], "md5sum": "af3d50ec055a29452e09d86b0e2760f1" }, { "dataPath": "params_shard_142.bin", "format": "raw-shard", "nbytes": 29526016, "records": [ { "name": "model.layers.34.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.34.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8847360 }, { "name": "model.layers.34.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8857600 }, { "name": "model.layers.35.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8867840 }, { "name": "model.layers.35.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8882176 }, { "name": "model.layers.35.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 27232256 } ], "md5sum": "5d9ae9e4b62bde490296022c4e01a4b2" }, { "dataPath": "params_shard_143.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.35.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "0eb4494b024fd94fad69955cf2d84c62" }, { "dataPath": "params_shard_144.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.35.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "3aebc6fca3b31d1486e58df26a568aae" }, { "dataPath": "params_shard_145.bin", "format": "raw-shard", "nbytes": 32440320, "records": [ { "name": "model.layers.35.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.35.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.35.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14745600 } ], "md5sum": "9d7249b32a818eadf5f02c7d27fae346" }, { "dataPath": "params_shard_146.bin", "format": "raw-shard", "nbytes": 29526016, "records": [ { "name": "model.layers.35.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.35.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8847360 }, { "name": "model.layers.35.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8857600 }, { "name": "model.layers.36.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8867840 }, { "name": "model.layers.36.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8882176 }, { "name": "model.layers.36.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 27232256 } ], "md5sum": "5e09c86db241fff7e77044053ae17a03" }, { "dataPath": "params_shard_147.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.36.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "c8a1035826fe4bfc76a3f179285b3c1b" }, { "dataPath": "params_shard_148.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.36.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "5039aae5ea5ba7c397f68bc0eaac84e7" }, { "dataPath": "params_shard_149.bin", "format": "raw-shard", "nbytes": 32440320, "records": [ { "name": "model.layers.36.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.36.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.36.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14745600 } ], "md5sum": "31f9c3aa95bf85566e1b23e526205ab3" }, { "dataPath": "params_shard_150.bin", "format": "raw-shard", "nbytes": 29526016, "records": [ { "name": "model.layers.36.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.36.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8847360 }, { "name": "model.layers.36.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8857600 }, { "name": "model.layers.37.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8867840 }, { "name": "model.layers.37.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8882176 }, { "name": "model.layers.37.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 27232256 } ], "md5sum": "a7d1faca4ded3c589bcd169007944b66" }, { "dataPath": "params_shard_151.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.37.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "b0f923af894a4105f7f006854fff9187" }, { "dataPath": "params_shard_152.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.37.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "001337a37a6e8e82561fe9816a13c30f" }, { "dataPath": "params_shard_153.bin", "format": "raw-shard", "nbytes": 32440320, "records": [ { "name": "model.layers.37.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.37.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.37.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14745600 } ], "md5sum": "7be4b10e736ee666eefec8d026f74e4d" }, { "dataPath": "params_shard_154.bin", "format": "raw-shard", "nbytes": 29526016, "records": [ { "name": "model.layers.37.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.37.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8847360 }, { "name": "model.layers.37.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8857600 }, { "name": "model.layers.38.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8867840 }, { "name": "model.layers.38.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8882176 }, { "name": "model.layers.38.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 27232256 } ], "md5sum": "45cc53045ebc6442734db2ef536d69ca" }, { "dataPath": "params_shard_155.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.38.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "4768c16a5dcb22bf1f0f72b7e5b03688" }, { "dataPath": "params_shard_156.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.38.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "52de1487be51dc7b1ff1c065828efc38" }, { "dataPath": "params_shard_157.bin", "format": "raw-shard", "nbytes": 32440320, "records": [ { "name": "model.layers.38.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.38.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.38.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14745600 } ], "md5sum": "71c06c965f6d1a1e93e23d54acd055a0" }, { "dataPath": "params_shard_158.bin", "format": "raw-shard", "nbytes": 29526016, "records": [ { "name": "model.layers.38.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.38.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8847360 }, { "name": "model.layers.38.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8857600 }, { "name": "model.layers.39.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8867840 }, { "name": "model.layers.39.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8882176 }, { "name": "model.layers.39.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 27232256 } ], "md5sum": "00e644baf6f725576c1bf5dce415f9c3" }, { "dataPath": "params_shard_159.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.39.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "f3ec2021fa5d2b12ea2fab43f667dc95" }, { "dataPath": "params_shard_160.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.39.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "88adcbb27944329cb5e51ab729b2bbfb" }, { "dataPath": "params_shard_161.bin", "format": "raw-shard", "nbytes": 32440320, "records": [ { "name": "model.layers.39.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.39.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.39.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14745600 } ], "md5sum": "3338ba876c2e9fea18f292967ec1b840" }, { "dataPath": "params_shard_162.bin", "format": "raw-shard", "nbytes": 29526016, "records": [ { "name": "model.layers.39.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.39.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8847360 }, { "name": "model.layers.39.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8857600 }, { "name": "model.layers.40.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8867840 }, { "name": "model.layers.40.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8882176 }, { "name": "model.layers.40.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 27232256 } ], "md5sum": "80fd977f079a91b5043c2043aef6cc9d" }, { "dataPath": "params_shard_163.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.40.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "56df082709840156bc479cad63f2ecd9" }, { "dataPath": "params_shard_164.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.40.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "c038c997f3117c3909187e9ad8ccdb02" }, { "dataPath": "params_shard_165.bin", "format": "raw-shard", "nbytes": 32440320, "records": [ { "name": "model.layers.40.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.40.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.40.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14745600 } ], "md5sum": "013881bff163544fffc190a4b6cfb55a" }, { "dataPath": "params_shard_166.bin", "format": "raw-shard", "nbytes": 29526016, "records": [ { "name": "model.layers.40.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.40.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8847360 }, { "name": "model.layers.40.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8857600 }, { "name": "model.layers.41.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8867840 }, { "name": "model.layers.41.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8882176 }, { "name": "model.layers.41.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 27232256 } ], "md5sum": "a04cef12c89f8bf4350e9c36382f2273" }, { "dataPath": "params_shard_167.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.41.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "5a7d79456a3d068474023922facc78a3" }, { "dataPath": "params_shard_168.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.41.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "467624ff098d7bc472a0c0d5fc0625d8" }, { "dataPath": "params_shard_169.bin", "format": "raw-shard", "nbytes": 32440320, "records": [ { "name": "model.layers.41.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.41.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.41.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14745600 } ], "md5sum": "22695100c194af7bc88f7c8ffbb15cf6" }, { "dataPath": "params_shard_170.bin", "format": "raw-shard", "nbytes": 29526016, "records": [ { "name": "model.layers.41.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.41.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8847360 }, { "name": "model.layers.41.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8857600 }, { "name": "model.layers.42.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8867840 }, { "name": "model.layers.42.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8882176 }, { "name": "model.layers.42.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 27232256 } ], "md5sum": "22d3083fd815ddb8a9fdbb99d9cfba69" }, { "dataPath": "params_shard_171.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.42.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "2d5ad7c3d173b76dffd70913b20fb9cd" }, { "dataPath": "params_shard_172.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.42.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "4b8a4f863172a1774a986fd99dcc0e4b" }, { "dataPath": "params_shard_173.bin", "format": "raw-shard", "nbytes": 32440320, "records": [ { "name": "model.layers.42.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.42.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.42.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14745600 } ], "md5sum": "cc159c9b22da993d352e9ce99a9536b3" }, { "dataPath": "params_shard_174.bin", "format": "raw-shard", "nbytes": 29526016, "records": [ { "name": "model.layers.42.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.42.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8847360 }, { "name": "model.layers.42.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8857600 }, { "name": "model.layers.43.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8867840 }, { "name": "model.layers.43.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8882176 }, { "name": "model.layers.43.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 27232256 } ], "md5sum": "da0da146d2e15cec6584d43d3fea2af0" }, { "dataPath": "params_shard_175.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.43.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "d4a62c9fef616341ad6b2e409d67ed38" }, { "dataPath": "params_shard_176.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.43.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "6e5441968705c796a374bcc5fe60f086" }, { "dataPath": "params_shard_177.bin", "format": "raw-shard", "nbytes": 32440320, "records": [ { "name": "model.layers.43.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.43.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.43.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14745600 } ], "md5sum": "725e5eefa74f1d053d718815381f42d5" }, { "dataPath": "params_shard_178.bin", "format": "raw-shard", "nbytes": 29526016, "records": [ { "name": "model.layers.43.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.43.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8847360 }, { "name": "model.layers.43.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8857600 }, { "name": "model.layers.44.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8867840 }, { "name": "model.layers.44.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8882176 }, { "name": "model.layers.44.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 27232256 } ], "md5sum": "5116fc33fa82888f65a33c6847f26168" }, { "dataPath": "params_shard_179.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.44.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "49a86a0c7c137ea71aad50de11a67e2c" }, { "dataPath": "params_shard_180.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.44.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "509c55affdc3aac4fc4cad6b7cb50aa9" }, { "dataPath": "params_shard_181.bin", "format": "raw-shard", "nbytes": 32440320, "records": [ { "name": "model.layers.44.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.44.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.44.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14745600 } ], "md5sum": "8de110376a5525616adb552a3b861db8" }, { "dataPath": "params_shard_182.bin", "format": "raw-shard", "nbytes": 29526016, "records": [ { "name": "model.layers.44.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.44.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8847360 }, { "name": "model.layers.44.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8857600 }, { "name": "model.layers.45.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8867840 }, { "name": "model.layers.45.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8882176 }, { "name": "model.layers.45.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 27232256 } ], "md5sum": "42e0fd02ce3d1d90e7fe6ec2ac72c9bf" }, { "dataPath": "params_shard_183.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.45.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "91083936caf7f3b541bcc79ddc9f5c7f" }, { "dataPath": "params_shard_184.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.45.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "5f924e24a2573f32f3bf4ee50beb7b21" }, { "dataPath": "params_shard_185.bin", "format": "raw-shard", "nbytes": 32440320, "records": [ { "name": "model.layers.45.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.45.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.45.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14745600 } ], "md5sum": "845980d1fd0e7f725255366865774110" }, { "dataPath": "params_shard_186.bin", "format": "raw-shard", "nbytes": 29526016, "records": [ { "name": "model.layers.45.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.45.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8847360 }, { "name": "model.layers.45.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8857600 }, { "name": "model.layers.46.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8867840 }, { "name": "model.layers.46.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8882176 }, { "name": "model.layers.46.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 27232256 } ], "md5sum": "c8ab8525639e77d5a8dd91d71d5ef748" }, { "dataPath": "params_shard_187.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.46.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "29be161a9524afa827be94d434bc76ff" }, { "dataPath": "params_shard_188.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.46.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "748ee1f7ce5b86b4f7495386bd894c56" }, { "dataPath": "params_shard_189.bin", "format": "raw-shard", "nbytes": 32440320, "records": [ { "name": "model.layers.46.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.46.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.46.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14745600 } ], "md5sum": "60bca83d5572e23ff65870353ce112b7" }, { "dataPath": "params_shard_190.bin", "format": "raw-shard", "nbytes": 29526016, "records": [ { "name": "model.layers.46.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.46.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8847360 }, { "name": "model.layers.46.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8857600 }, { "name": "model.layers.47.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8867840 }, { "name": "model.layers.47.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8882176 }, { "name": "model.layers.47.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 27232256 } ], "md5sum": "639beea33026d0c2c2d07c87d29a3474" }, { "dataPath": "params_shard_191.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.47.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "26f600b2af777835cd1425034f2e2e02" }, { "dataPath": "params_shard_192.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.47.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "8ff56d2a0c9fb1bb444390cbd86ba874" }, { "dataPath": "params_shard_193.bin", "format": "raw-shard", "nbytes": 32440320, "records": [ { "name": "model.layers.47.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.47.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.47.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14745600 } ], "md5sum": "acfb6c18b66aa3e3fadff9901c8131f8" }, { "dataPath": "params_shard_194.bin", "format": "raw-shard", "nbytes": 29526016, "records": [ { "name": "model.layers.47.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.47.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8847360 }, { "name": "model.layers.47.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8857600 }, { "name": "model.layers.48.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8867840 }, { "name": "model.layers.48.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8882176 }, { "name": "model.layers.48.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 27232256 } ], "md5sum": "eaa803a36206a86102e82071b0ae8aeb" }, { "dataPath": "params_shard_195.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.48.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "4e146e872ec4ec9cfe73dd7ed259cd64" }, { "dataPath": "params_shard_196.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.48.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "7c12aadcc98d1397efa9ce26ff31d7ac" }, { "dataPath": "params_shard_197.bin", "format": "raw-shard", "nbytes": 32440320, "records": [ { "name": "model.layers.48.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.48.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.48.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14745600 } ], "md5sum": "37505cd0c3d985caab95791aad1e5008" }, { "dataPath": "params_shard_198.bin", "format": "raw-shard", "nbytes": 29526016, "records": [ { "name": "model.layers.48.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.48.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8847360 }, { "name": "model.layers.48.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8857600 }, { "name": "model.layers.49.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8867840 }, { "name": "model.layers.49.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8882176 }, { "name": "model.layers.49.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 27232256 } ], "md5sum": "b80f742b5eeea0fb46e3aa9455e0e72c" }, { "dataPath": "params_shard_199.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.49.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "a75e12288c6ae54a3a5d34fa00b05cb6" }, { "dataPath": "params_shard_200.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.49.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "2b1b1b95576ce27b8e63445eeb32c28e" }, { "dataPath": "params_shard_201.bin", "format": "raw-shard", "nbytes": 32440320, "records": [ { "name": "model.layers.49.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.49.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.49.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14745600 } ], "md5sum": "e1c54b4753c263eb7f09567bc64abd48" }, { "dataPath": "params_shard_202.bin", "format": "raw-shard", "nbytes": 29526016, "records": [ { "name": "model.layers.49.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.49.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8847360 }, { "name": "model.layers.49.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8857600 }, { "name": "model.layers.50.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8867840 }, { "name": "model.layers.50.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8882176 }, { "name": "model.layers.50.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 27232256 } ], "md5sum": "aab549151b13e198d9868fb9461f79e7" }, { "dataPath": "params_shard_203.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.50.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "a5fe3521e29213a0a0f41f4cdaa68147" }, { "dataPath": "params_shard_204.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.50.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "629c5f69407c4edd0f1f1a16856dcdbc" }, { "dataPath": "params_shard_205.bin", "format": "raw-shard", "nbytes": 32440320, "records": [ { "name": "model.layers.50.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.50.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.50.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14745600 } ], "md5sum": "b64653fdf63880eeaa1699d67d97abe1" }, { "dataPath": "params_shard_206.bin", "format": "raw-shard", "nbytes": 29526016, "records": [ { "name": "model.layers.50.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.50.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8847360 }, { "name": "model.layers.50.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8857600 }, { "name": "model.layers.51.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8867840 }, { "name": "model.layers.51.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8882176 }, { "name": "model.layers.51.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 27232256 } ], "md5sum": "4f77a3dd3df2374732d7987e6958ab1e" }, { "dataPath": "params_shard_207.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.51.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "392a4d9ff1efa92623df87949d6d5445" }, { "dataPath": "params_shard_208.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.51.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "bc2cb3d6343c515a504b1fda2d67d2e0" }, { "dataPath": "params_shard_209.bin", "format": "raw-shard", "nbytes": 32440320, "records": [ { "name": "model.layers.51.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.51.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.51.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14745600 } ], "md5sum": "e1b07cb11df31f03fee7e586f7eef9b0" }, { "dataPath": "params_shard_210.bin", "format": "raw-shard", "nbytes": 29526016, "records": [ { "name": "model.layers.51.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.51.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8847360 }, { "name": "model.layers.51.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8857600 }, { "name": "model.layers.52.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8867840 }, { "name": "model.layers.52.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8882176 }, { "name": "model.layers.52.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 27232256 } ], "md5sum": "40e58ceea9d04d13a69ba7efc3dfec5e" }, { "dataPath": "params_shard_211.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.52.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "f16c2f1ff0c5563f09cd5cc8830b7483" }, { "dataPath": "params_shard_212.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.52.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "79cf8705acf14574d15541fbac5e64ab" }, { "dataPath": "params_shard_213.bin", "format": "raw-shard", "nbytes": 32440320, "records": [ { "name": "model.layers.52.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.52.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.52.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14745600 } ], "md5sum": "c10608373139f67102b2b34e303cb4cc" }, { "dataPath": "params_shard_214.bin", "format": "raw-shard", "nbytes": 29526016, "records": [ { "name": "model.layers.52.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.52.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8847360 }, { "name": "model.layers.52.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8857600 }, { "name": "model.layers.53.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8867840 }, { "name": "model.layers.53.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8882176 }, { "name": "model.layers.53.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 27232256 } ], "md5sum": "1c1250fd7e2cb23d8cf51f89748cd206" }, { "dataPath": "params_shard_215.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.53.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "02d3fea1b53666036f73e28d539345fa" }, { "dataPath": "params_shard_216.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.53.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "a1a25adf8c7aa2b9b08f8b4d5da0b6a0" }, { "dataPath": "params_shard_217.bin", "format": "raw-shard", "nbytes": 32440320, "records": [ { "name": "model.layers.53.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.53.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.53.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14745600 } ], "md5sum": "b0fcca48b168fe77d18f2fb7924ef4a7" }, { "dataPath": "params_shard_218.bin", "format": "raw-shard", "nbytes": 29526016, "records": [ { "name": "model.layers.53.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.53.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8847360 }, { "name": "model.layers.53.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8857600 }, { "name": "model.layers.54.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8867840 }, { "name": "model.layers.54.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8882176 }, { "name": "model.layers.54.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 27232256 } ], "md5sum": "8ba01737a917b4fa44757d5f93fb4f7b" }, { "dataPath": "params_shard_219.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.54.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "ff3be6b5eb7bec031ef984bd6728b8fc" }, { "dataPath": "params_shard_220.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.54.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "7dcc859ca5e3d4176576852db97fce68" }, { "dataPath": "params_shard_221.bin", "format": "raw-shard", "nbytes": 32440320, "records": [ { "name": "model.layers.54.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.54.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.54.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14745600 } ], "md5sum": "3db139ccafdbc7a0749691aeac7fc187" }, { "dataPath": "params_shard_222.bin", "format": "raw-shard", "nbytes": 29526016, "records": [ { "name": "model.layers.54.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.54.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8847360 }, { "name": "model.layers.54.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8857600 }, { "name": "model.layers.55.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8867840 }, { "name": "model.layers.55.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8882176 }, { "name": "model.layers.55.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 27232256 } ], "md5sum": "9839e84f687f07b918f78bc290ec5d41" }, { "dataPath": "params_shard_223.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.55.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "4c127341d6c8b966177286d4b4d5b7fe" }, { "dataPath": "params_shard_224.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.55.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "e00f6e16b421ae2335d403e0dc2d5c15" }, { "dataPath": "params_shard_225.bin", "format": "raw-shard", "nbytes": 32440320, "records": [ { "name": "model.layers.55.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.55.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.55.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14745600 } ], "md5sum": "732e1eb5e2a4b58541b3113468f93358" }, { "dataPath": "params_shard_226.bin", "format": "raw-shard", "nbytes": 29526016, "records": [ { "name": "model.layers.55.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.55.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8847360 }, { "name": "model.layers.55.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8857600 }, { "name": "model.layers.56.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8867840 }, { "name": "model.layers.56.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8882176 }, { "name": "model.layers.56.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 27232256 } ], "md5sum": "c69df1103fddeb1fca2dbc0dfedf008f" }, { "dataPath": "params_shard_227.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.56.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "491a69d5b8f42a9df267ee632166b6ea" }, { "dataPath": "params_shard_228.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.56.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "7682f9d654166191597f095d786e348e" }, { "dataPath": "params_shard_229.bin", "format": "raw-shard", "nbytes": 32440320, "records": [ { "name": "model.layers.56.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.56.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.56.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14745600 } ], "md5sum": "0a5fa28cd2cddd581494f613004d4a17" }, { "dataPath": "params_shard_230.bin", "format": "raw-shard", "nbytes": 29526016, "records": [ { "name": "model.layers.56.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.56.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8847360 }, { "name": "model.layers.56.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8857600 }, { "name": "model.layers.57.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8867840 }, { "name": "model.layers.57.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8882176 }, { "name": "model.layers.57.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 27232256 } ], "md5sum": "1e9d7195c1378a4f1ad9cfb2b45009d4" }, { "dataPath": "params_shard_231.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.57.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "22122a9a59f26f564b8afa79a079e94b" }, { "dataPath": "params_shard_232.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.57.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "4fd15cf7903420ba12e9a0a34769b6d9" }, { "dataPath": "params_shard_233.bin", "format": "raw-shard", "nbytes": 32440320, "records": [ { "name": "model.layers.57.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.57.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.57.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14745600 } ], "md5sum": "1707e5278fdd458f0e6845541576b4fa" }, { "dataPath": "params_shard_234.bin", "format": "raw-shard", "nbytes": 29526016, "records": [ { "name": "model.layers.57.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.57.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8847360 }, { "name": "model.layers.57.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8857600 }, { "name": "model.layers.58.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8867840 }, { "name": "model.layers.58.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8882176 }, { "name": "model.layers.58.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 27232256 } ], "md5sum": "adae917f3f71d2fa06eaadba1a4bc9d5" }, { "dataPath": "params_shard_235.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.58.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "6cc4502bbf4d8527b8b9728bc47535a8" }, { "dataPath": "params_shard_236.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.58.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "15493428ec93d78719f01e6af49e4c8c" }, { "dataPath": "params_shard_237.bin", "format": "raw-shard", "nbytes": 32440320, "records": [ { "name": "model.layers.58.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.58.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.58.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14745600 } ], "md5sum": "37931e149df6041cd040713b42d5ba87" }, { "dataPath": "params_shard_238.bin", "format": "raw-shard", "nbytes": 29526016, "records": [ { "name": "model.layers.58.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.58.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8847360 }, { "name": "model.layers.58.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8857600 }, { "name": "model.layers.59.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8867840 }, { "name": "model.layers.59.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8882176 }, { "name": "model.layers.59.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 27232256 } ], "md5sum": "ebf9b5fe5bc251c1efa2c822f1266244" }, { "dataPath": "params_shard_239.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.59.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "649c116c1f4b074ee4248482e2b47db0" }, { "dataPath": "params_shard_240.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.59.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "2af1177422365c30aa325433565d8a20" }, { "dataPath": "params_shard_241.bin", "format": "raw-shard", "nbytes": 32440320, "records": [ { "name": "model.layers.59.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.59.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.59.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14745600 } ], "md5sum": "8a985147c2a9cd3d4ff36afdab7a0c62" }, { "dataPath": "params_shard_242.bin", "format": "raw-shard", "nbytes": 29526016, "records": [ { "name": "model.layers.59.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.59.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8847360 }, { "name": "model.layers.59.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8857600 }, { "name": "model.layers.60.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8867840 }, { "name": "model.layers.60.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8882176 }, { "name": "model.layers.60.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 27232256 } ], "md5sum": "796cb119a27ece8c01bd0c38ac3b8965" }, { "dataPath": "params_shard_243.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.60.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "4fcee22f38d845e9580ec8189c989709" }, { "dataPath": "params_shard_244.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.60.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "f56e457980c0f137c1535893aed0dcc8" }, { "dataPath": "params_shard_245.bin", "format": "raw-shard", "nbytes": 32440320, "records": [ { "name": "model.layers.60.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.60.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.60.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14745600 } ], "md5sum": "a44d3f13628121ee0318ce1e11ac1f91" }, { "dataPath": "params_shard_246.bin", "format": "raw-shard", "nbytes": 29526016, "records": [ { "name": "model.layers.60.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.60.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8847360 }, { "name": "model.layers.60.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8857600 }, { "name": "model.layers.61.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8867840 }, { "name": "model.layers.61.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8882176 }, { "name": "model.layers.61.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 27232256 } ], "md5sum": "cdfd73472d770387b35c9da6b8ed2ba7" }, { "dataPath": "params_shard_247.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.61.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "72e4067b43ba31121b5688347c10fb1c" }, { "dataPath": "params_shard_248.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.61.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "da86ccc13dfe096af34e4470c8a5060c" }, { "dataPath": "params_shard_249.bin", "format": "raw-shard", "nbytes": 32440320, "records": [ { "name": "model.layers.61.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.61.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.61.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14745600 } ], "md5sum": "85106044e6b43b31207c804176a7a98e" }, { "dataPath": "params_shard_250.bin", "format": "raw-shard", "nbytes": 29526016, "records": [ { "name": "model.layers.61.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.61.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8847360 }, { "name": "model.layers.61.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8857600 }, { "name": "model.layers.62.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8867840 }, { "name": "model.layers.62.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8882176 }, { "name": "model.layers.62.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 27232256 } ], "md5sum": "ad3280928742c07ea1e3fd4873bd1743" }, { "dataPath": "params_shard_251.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.62.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "3467eb1f4fc0bbbbc630fb4cbe868b23" }, { "dataPath": "params_shard_252.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.62.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "f7b143430be0a275e532fa1ce6330634" }, { "dataPath": "params_shard_253.bin", "format": "raw-shard", "nbytes": 32440320, "records": [ { "name": "model.layers.62.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.62.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.62.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14745600 } ], "md5sum": "17602d8416afad20dc6f27cd53ebceee" }, { "dataPath": "params_shard_254.bin", "format": "raw-shard", "nbytes": 29526016, "records": [ { "name": "model.layers.62.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.62.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8847360 }, { "name": "model.layers.62.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8857600 }, { "name": "model.layers.63.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8867840 }, { "name": "model.layers.63.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8882176 }, { "name": "model.layers.63.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 27232256 } ], "md5sum": "918d5c9b796463ff36c22ebc87f28e9f" }, { "dataPath": "params_shard_255.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.63.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "be2ccd033d8abd1fef123b2b13c1857b" }, { "dataPath": "params_shard_256.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.63.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "085c7809680c6bec4dedc819c9b5f9f4" }, { "dataPath": "params_shard_257.bin", "format": "raw-shard", "nbytes": 32440320, "records": [ { "name": "model.layers.63.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.63.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.63.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14745600 } ], "md5sum": "34a78136413fb5417731a8e5f6b3c29a" }, { "dataPath": "params_shard_258.bin", "format": "raw-shard", "nbytes": 389283840, "records": [ { "name": "lm_head.q_weight", "shape": [ 152064, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 389283840, "byteOffset": 0 } ], "md5sum": "170cfd7195423a839d94f70e1ab88918" }, { "dataPath": "params_shard_259.bin", "format": "raw-shard", "nbytes": 48660480, "records": [ { "name": "lm_head.q_scale", "shape": [ 152064, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 48660480, "byteOffset": 0 } ], "md5sum": "e6cb79c9436e609911bbf42f620ab15e" }, { "dataPath": "params_shard_260.bin", "format": "raw-shard", "nbytes": 8878080, "records": [ { "name": "model.layers.63.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.63.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8847360 }, { "name": "model.layers.63.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8857600 }, { "name": "model.norm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8867840 } ], "md5sum": "72e8f4296f1154164844dbb1aed4ba5c" } ] }