{ "metadata": { "ParamSize": 709, "ParamBytes": 16895535104.0, "BitsPerParam": 4.125405656518088 }, "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": "2160f6cbda407f70c0d2058e2543e6e5" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 31102976, "records": [ { "name": "model.embed_tokens.q_scale", "shape": [ 152064, 40 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12165120, "byteOffset": 0 }, { "name": "model.layers.0.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 12165120 }, { "name": "model.layers.0.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 12179456 }, { "name": "model.layers.0.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 30529536 } ], "md5sum": "3e7b67ece44d93b493924d79c6e6ce05" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "119dd1b983309d741fb6645287b3702f" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "0bbf6497e76bfb60cf2ba7bdb6ca3a7b" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.1.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "94574e053f2946b34cc18c6ad455e2f4" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.0.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 17940480 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20152320 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.1.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.1.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "14708d8170909015b1096ec11ab4f372" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "70b0cbe76cc3a36fed44a3ce139d4d84" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.1.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "e2056907dbd6075a67a2388fbdcc1291" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.2.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "93aeefac78495adfbff7688d5c74ea96" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.1.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.1.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.1.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 17940480 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20152320 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.2.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.2.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "ea2d624f6622d3445d58d13e5677e4d2" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "bffe6947fe04ebfeda1e870bdc709fed" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.2.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "c791b3013aeb710277c34596cef78ec8" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.3.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "c378315c566a5f4eea531446c9d85f06" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.2.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.2.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.2.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 17940480 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20152320 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.3.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.3.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "4a840d2c0a5f15ef221dd465c48323eb" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "af441f9290d817cdd1d3756fd61a2c89" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.3.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "fe24e0d000e6dda24b0586318950bf02" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.4.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "dd617527c23fefa8e0a614d33e9935cb" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.3.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.3.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 17940480 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20152320 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.4.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.4.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "0cefde893c512bc1b75d0b9ccafb6b5c" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "b4ba7d9a7b5237d57c0f6833a763a740" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.4.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "977fe394c4eb993a1970617469d3e4f1" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.5.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "aa65d4713ffa59abf9d193892930a51f" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.4.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.4.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.4.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.4.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 17940480 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20152320 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.5.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.5.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "f9e308928ed17337766a5d2fad9b50da" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "b8ece74db336880634a7c0d229d243d4" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.5.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "e728ca537c79a652011990af144456e6" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.6.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "7fb726ef8305615d7caaeda6b5560795" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.5.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.5.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.5.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 17940480 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20152320 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.6.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.6.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "17d7098b25d681c038d16067e363d278" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "51e7231580c1a235b660b3d727b3fe5e" }, { "dataPath": "params_shard_27.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.6.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "1f6a5f32f306d7729280d0c7263eef0f" }, { "dataPath": "params_shard_28.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.7.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "5716e7f55bd03f4113e17c9f70e86314" }, { "dataPath": "params_shard_29.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.6.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.6.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.6.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 17940480 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20152320 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.7.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.7.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "ee20465108ed5057b8682ab4546442b3" }, { "dataPath": "params_shard_30.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "27b8aab15ad3a8ca6a78b3636e474d89" }, { "dataPath": "params_shard_31.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.7.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "315248fbdd2a5b0bc0c46c1857538605" }, { "dataPath": "params_shard_32.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.8.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "f790cf2677aad8f00e7e1f23261f8fc6" }, { "dataPath": "params_shard_33.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.7.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.7.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.7.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.7.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 17940480 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20152320 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.8.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.8.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "cf844ba0e6bf9c818d61597e5ab8fa35" }, { "dataPath": "params_shard_34.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "c884d21ea633b395886e367ef4dff398" }, { "dataPath": "params_shard_35.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.8.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "c089da007faf5ee21e96cc88f4617b58" }, { "dataPath": "params_shard_36.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.9.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "f2d4a40314adcbdca25c42cb22fb9b27" }, { "dataPath": "params_shard_37.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.8.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.8.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.8.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 17940480 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20152320 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.9.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.9.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "f71a70dc44ae2b7afacd71c4fd4eb40b" }, { "dataPath": "params_shard_38.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "b25d84bdf6b77388a109b7857ebe8653" }, { "dataPath": "params_shard_39.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.9.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "2944d74529e0db8e33de6d5d1f3a1459" }, { "dataPath": "params_shard_40.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.10.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "7bb1fe32b6001e785c82f67c7690d7db" }, { "dataPath": "params_shard_41.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.9.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.9.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.9.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 17940480 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20152320 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.10.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.10.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "e23a9f00a2cb9698b6653ac36b1b147a" }, { "dataPath": "params_shard_42.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "d185d30973d17350dd8bfabab736440c" }, { "dataPath": "params_shard_43.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.10.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "38c6bb718b1de9d9f7e9c31db494eee7" }, { "dataPath": "params_shard_44.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.11.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "e23ea4f4a7491b9e2336373c15caf9b2" }, { "dataPath": "params_shard_45.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.10.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.10.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 17940480 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20152320 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.11.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.11.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "a452a14dd9795b4cbb672a574e92531d" }, { "dataPath": "params_shard_46.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "d1343ad7477d62e03847f5813223194b" }, { "dataPath": "params_shard_47.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.11.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "1fdace10adebcca80a7fcb89e77b90a4" }, { "dataPath": "params_shard_48.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.12.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "2b4c345718dc03e30b6253112123617a" }, { "dataPath": "params_shard_49.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.11.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.11.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.11.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 17940480 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20152320 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.12.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.12.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "34296b36fab4ce93229c00bee31b22ff" }, { "dataPath": "params_shard_50.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "26129bfca73a8ab19c0648fe94a230e2" }, { "dataPath": "params_shard_51.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.12.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "224191bac3aa158c602002653178983d" }, { "dataPath": "params_shard_52.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.13.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "a07cce1357a66c0347e143e47710df8e" }, { "dataPath": "params_shard_53.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.12.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.12.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.12.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.12.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 17940480 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20152320 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.13.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.13.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "aa64e483e5f20dd4563aa18b5bff6855" }, { "dataPath": "params_shard_54.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "e29690928c42b9621e3f4301d726d89b" }, { "dataPath": "params_shard_55.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.13.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "56399646a1d029a57ae60547081cc64c" }, { "dataPath": "params_shard_56.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.14.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "b848262f4a7cbcabc29f375470547334" }, { "dataPath": "params_shard_57.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.13.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.13.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.13.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 17940480 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20152320 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.14.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.14.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "f1299f4f688a9f2d4e0574ec0c4f69bb" }, { "dataPath": "params_shard_58.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "65d1212958007a5624e8f69725951048" }, { "dataPath": "params_shard_59.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.14.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "6c1de3942623361ff6aa759694cf78c2" }, { "dataPath": "params_shard_60.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.15.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "3211346e07963a5fc1cb7713fd3b5b3e" }, { "dataPath": "params_shard_61.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.14.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.14.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 17940480 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20152320 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.15.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.15.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "1e221b2c244a3eee7888a53f08af3e7d" }, { "dataPath": "params_shard_62.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "1a3a8a7da9b68fa3a507a5752b049e4f" }, { "dataPath": "params_shard_63.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.15.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "d8acc4dee55e1fccdb5cdad5921bb83b" }, { "dataPath": "params_shard_64.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.16.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "2d355331b73623c261a5897ae30e3b00" }, { "dataPath": "params_shard_65.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.15.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.15.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.15.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 17940480 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20152320 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.16.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.16.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "1572b102bded95ab329ecf3986ac96fb" }, { "dataPath": "params_shard_66.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "6116374350074ac6bb3f26489eca8769" }, { "dataPath": "params_shard_67.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.16.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "8cc644440b754dea2d0a170d7e1adc5e" }, { "dataPath": "params_shard_68.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.17.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "3e70a049a96b1f40bdcf83e8db658c6c" }, { "dataPath": "params_shard_69.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.16.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.16.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.16.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.16.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 17940480 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20152320 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.17.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.17.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "39affe6d48a41d2e5bc1f8b688ca86b7" }, { "dataPath": "params_shard_70.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "b2315972297d13bd32ce620b95189ce6" }, { "dataPath": "params_shard_71.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.17.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "57a5f81b247934ccefd30e51c02382bc" }, { "dataPath": "params_shard_72.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.18.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "b213f0092c857edc6b76e130567ed416" }, { "dataPath": "params_shard_73.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.17.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.17.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.17.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.17.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 17940480 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20152320 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.18.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.18.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "6dfc58dcec1894f66e689d884ec4d43a" }, { "dataPath": "params_shard_74.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "da06290cbb25c063a187010f91deccdf" }, { "dataPath": "params_shard_75.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.18.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "d3dd9f61d3a6fb2ebc8d009147edc62c" }, { "dataPath": "params_shard_76.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.19.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "f4701ea2c6bde074e24e0715750bd2cf" }, { "dataPath": "params_shard_77.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.18.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.18.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.18.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.18.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 17940480 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20152320 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.19.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.19.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "5fb47fdbd774a72f1f172125d824ccff" }, { "dataPath": "params_shard_78.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "a766879e78138eaa000eec95ea9377ff" }, { "dataPath": "params_shard_79.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.19.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "df7df24d74f3db624c427f9568e561ff" }, { "dataPath": "params_shard_80.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.20.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "9fc978c2ba9d7fc175ef93e7138076c8" }, { "dataPath": "params_shard_81.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.19.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.19.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.19.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.19.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 17940480 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20152320 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.20.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.20.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "0f6770226bc44adf1ba7fc9bd8f2ec76" }, { "dataPath": "params_shard_82.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "f0f6f5fd27e3b567316ea6024822f1fa" }, { "dataPath": "params_shard_83.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.20.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "883555eefffcf083ece5f455db6c3cdc" }, { "dataPath": "params_shard_84.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.21.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "ebbc6852b3feb201be04a0c7c91d722b" }, { "dataPath": "params_shard_85.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.20.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.20.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.20.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.20.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 17940480 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20152320 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.21.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.21.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "e45a8d0df1e3552bfd0a4d2ab514b0f4" }, { "dataPath": "params_shard_86.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "ffce06c9d902246e7a5b52f13c9e99df" }, { "dataPath": "params_shard_87.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.21.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "2fb2d3cdc6d68235bbfbca1bd6d7e0e2" }, { "dataPath": "params_shard_88.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.22.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "9ece9f579d6a07ada436d104b6c827a1" }, { "dataPath": "params_shard_89.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.21.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.21.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.21.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.21.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 17940480 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20152320 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.22.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.22.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "7524774d4cf32fc49d85adfedd0c3436" }, { "dataPath": "params_shard_90.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "84e9e89e81f285755b398bf90c4721ac" }, { "dataPath": "params_shard_91.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.22.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "e9a352bf2329aaf3c49dcb13516ffdf9" }, { "dataPath": "params_shard_92.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.23.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "bf083879dc03cc194b745feea25f1489" }, { "dataPath": "params_shard_93.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.22.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.22.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.22.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.22.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 17940480 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20152320 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.23.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.23.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "c48df471d1122384219e1d82b4c9e647" }, { "dataPath": "params_shard_94.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "701a4849aa1e1d270908310ffce474b8" }, { "dataPath": "params_shard_95.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.23.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "4a4ac1f12f1201e6763316645c41d99c" }, { "dataPath": "params_shard_96.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.24.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "a112217764718957849bc22544e27862" }, { "dataPath": "params_shard_97.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.23.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.23.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.23.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.23.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 17940480 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20152320 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.24.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.24.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "2c408e376f752ba75faced6f1e9d8f72" }, { "dataPath": "params_shard_98.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "2ada0be5b3542f20f19634c9fb66cd29" }, { "dataPath": "params_shard_99.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.24.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "4edecd2c041ac46d48a1bd3521620eb3" }, { "dataPath": "params_shard_100.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.25.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "05dbda6e592d43e1518f0f3c34948df2" }, { "dataPath": "params_shard_101.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.24.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.24.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.24.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.24.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 17940480 }, { "name": "model.layers.24.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20152320 }, { "name": "model.layers.24.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.25.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.25.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "e6504138d7f091a3be9fbfaf4158b8e2" }, { "dataPath": "params_shard_102.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "327878dabeae075a191d86a723770f2d" }, { "dataPath": "params_shard_103.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.25.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "b0a49538754dd1eb7ef22e2e469e652c" }, { "dataPath": "params_shard_104.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.26.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "5715c38c928ef849eff57e83bb402de0" }, { "dataPath": "params_shard_105.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.25.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.25.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.25.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.25.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 17940480 }, { "name": "model.layers.25.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20152320 }, { "name": "model.layers.25.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.26.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.26.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "5fbece675c2fab8dd915829e16bf710b" }, { "dataPath": "params_shard_106.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "dd31b35d51c3d33a61819f1cace75856" }, { "dataPath": "params_shard_107.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.26.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "1520d129a8dcdedbdc5a96c4b77d9127" }, { "dataPath": "params_shard_108.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.27.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "ec5af2121c5e2953c8522e9342ff8e5c" }, { "dataPath": "params_shard_109.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.26.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.26.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.26.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.26.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 17940480 }, { "name": "model.layers.26.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20152320 }, { "name": "model.layers.26.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.27.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.27.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "6e02bceda4e0a01619cf5ee0e8efdc2c" }, { "dataPath": "params_shard_110.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.27.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "5cd0e2b0f1aa99430ad4a17b8eee514d" }, { "dataPath": "params_shard_111.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.27.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "866df094fbaca4a3426cd54631fc96f4" }, { "dataPath": "params_shard_112.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.28.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "d85d79d1b1fe09a1d131a85044128777" }, { "dataPath": "params_shard_113.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.27.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.27.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.27.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.27.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 17940480 }, { "name": "model.layers.27.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20152320 }, { "name": "model.layers.27.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.28.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.28.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "709244a8e90e01762c14e92ffe0998f6" }, { "dataPath": "params_shard_114.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.28.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "968e8cb9d0334af826c7efc350d53b8e" }, { "dataPath": "params_shard_115.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.28.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "9fa043aacd80997da0e6a27c0db0495f" }, { "dataPath": "params_shard_116.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.29.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "fc299560c0938278fd75ce262b8e7278" }, { "dataPath": "params_shard_117.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.28.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.28.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.28.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.28.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 17940480 }, { "name": "model.layers.28.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20152320 }, { "name": "model.layers.28.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.29.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.29.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "bb7a341721cc8adda13dc78b65c3da89" }, { "dataPath": "params_shard_118.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.29.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "2ac8aee7a8315acca8f3d0c72d4b3838" }, { "dataPath": "params_shard_119.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.29.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "045d146248d9c4dd6c3fac285da34a72" }, { "dataPath": "params_shard_120.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.30.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "59b3c945307dd14f47fe40907b6ce717" }, { "dataPath": "params_shard_121.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.29.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.29.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.29.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.29.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 17940480 }, { "name": "model.layers.29.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20152320 }, { "name": "model.layers.29.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.30.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.30.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "0072f6be1a905bc1b270b31aff237f38" }, { "dataPath": "params_shard_122.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.30.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "7774723a300f98138a1c40da549fbaf1" }, { "dataPath": "params_shard_123.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.30.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "7a102deb562c1ad2d6f6ba8cea1416e1" }, { "dataPath": "params_shard_124.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.31.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "7077e5a06d582c0b63af856e17bbf05b" }, { "dataPath": "params_shard_125.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.30.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.30.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.30.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.30.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 17940480 }, { "name": "model.layers.30.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20152320 }, { "name": "model.layers.30.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.31.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.31.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "a747d29541a9f943cadef7f7aa00229e" }, { "dataPath": "params_shard_126.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.31.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "4b3ca70cce415094a4f40cb6507de7f4" }, { "dataPath": "params_shard_127.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.31.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "c8edc22cc57966fbc509b8ac1f1cdb27" }, { "dataPath": "params_shard_128.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.32.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "1ab2670f5a992f840a66853373ca57fd" }, { "dataPath": "params_shard_129.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.31.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.31.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.31.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.31.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 17940480 }, { "name": "model.layers.31.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20152320 }, { "name": "model.layers.31.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.32.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.32.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "d397427d77fc63755b97011c5f409bb1" }, { "dataPath": "params_shard_130.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.32.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "58f905932d9ec361f28d52f38fa9f1fc" }, { "dataPath": "params_shard_131.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.32.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "5281d63585003be532ddca700f257a0f" }, { "dataPath": "params_shard_132.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.33.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "24520890af85661be2cb07cf7dcf2bd4" }, { "dataPath": "params_shard_133.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.32.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.32.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.32.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.32.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 17940480 }, { "name": "model.layers.32.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20152320 }, { "name": "model.layers.32.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.33.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.33.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "aee25acd5522ef2f333e4e918166cfc3" }, { "dataPath": "params_shard_134.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.33.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "ccda67286e192f31ec443e9c7a8130a0" }, { "dataPath": "params_shard_135.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.33.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "e6b841d299513d6f2638cf85a739d6a7" }, { "dataPath": "params_shard_136.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.34.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "b31789e0903e19e1c9d2b9ee553856c4" }, { "dataPath": "params_shard_137.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.33.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.33.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.33.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.33.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 17940480 }, { "name": "model.layers.33.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20152320 }, { "name": "model.layers.33.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.34.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.34.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "4f08dc97743de07320b7ab3e01b48dcc" }, { "dataPath": "params_shard_138.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.34.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "931d799b4221cac82100b80d88692a85" }, { "dataPath": "params_shard_139.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.34.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "3336b2fa2e272db789c66bf2b361c720" }, { "dataPath": "params_shard_140.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.35.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "2b18275c4239150aed533ce51827369f" }, { "dataPath": "params_shard_141.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.34.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.34.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.34.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.34.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 17940480 }, { "name": "model.layers.34.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20152320 }, { "name": "model.layers.34.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.35.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.35.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "5ecb264fceb38a49c98e0d230ae28f8f" }, { "dataPath": "params_shard_142.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.35.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "9a1ef78265ea6d872c015f832d0fa3d5" }, { "dataPath": "params_shard_143.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.35.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "01755d31ccbcf7036f7cfaec5949b0c5" }, { "dataPath": "params_shard_144.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.36.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "2e35b8fcf4ae7dd9a1beb4b849de3f1c" }, { "dataPath": "params_shard_145.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.35.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.35.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.35.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.35.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 17940480 }, { "name": "model.layers.35.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20152320 }, { "name": "model.layers.35.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.36.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.36.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "626e255e5e7690ef0872d531b36e338c" }, { "dataPath": "params_shard_146.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.36.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "de3a8eb0d18638c0f9d4afb4658c9560" }, { "dataPath": "params_shard_147.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.36.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "043cd5c3413c1335b358c295d43d42fb" }, { "dataPath": "params_shard_148.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.37.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "ff1c6c4973342f2faf776793e6585e17" }, { "dataPath": "params_shard_149.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.36.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.36.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.36.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.36.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 17940480 }, { "name": "model.layers.36.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20152320 }, { "name": "model.layers.36.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.37.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.37.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "99c3980fcd6937f3dc24d19fba8f4134" }, { "dataPath": "params_shard_150.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.37.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "7a918b4561804225473b8e3bfb7e1335" }, { "dataPath": "params_shard_151.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.37.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "b861b297d56ac6541fa304b47fd85b77" }, { "dataPath": "params_shard_152.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.38.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "6715df4058c9fed0199a73d5d82464f5" }, { "dataPath": "params_shard_153.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.37.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.37.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.37.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.37.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 17940480 }, { "name": "model.layers.37.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20152320 }, { "name": "model.layers.37.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.38.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.38.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "f93ea50e0787957f0101c3a80900aa9b" }, { "dataPath": "params_shard_154.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.38.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "9aa8dc9dac6e5504ed69ad983343c620" }, { "dataPath": "params_shard_155.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.38.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "6bb58194eeeeb552559c7b71ee6065f2" }, { "dataPath": "params_shard_156.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.39.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "374180a4c7fef97b48ffc5825d5ba0f6" }, { "dataPath": "params_shard_157.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.38.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.38.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.38.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.38.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 17940480 }, { "name": "model.layers.38.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20152320 }, { "name": "model.layers.38.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.39.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.39.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "838526860f24873ed1dbc21d7656f751" }, { "dataPath": "params_shard_158.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.39.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "68e6c31e94f5504bbecfbeaccfada0aa" }, { "dataPath": "params_shard_159.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.39.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "1525dd24f902765585611cca3b5d73f8" }, { "dataPath": "params_shard_160.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.40.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "39d81091371af41c874358e0053c3eee" }, { "dataPath": "params_shard_161.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.39.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.39.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.39.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.39.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 17940480 }, { "name": "model.layers.39.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20152320 }, { "name": "model.layers.39.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.40.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.40.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "51d158ba008cfc3ee58379d40c38551f" }, { "dataPath": "params_shard_162.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.40.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "e376330c3202f3742681eb202baff45f" }, { "dataPath": "params_shard_163.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.40.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "3370cc282a0901e322921fac361b2f08" }, { "dataPath": "params_shard_164.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.41.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "c4414ce1701f39ca9ec67ab28d76f1a6" }, { "dataPath": "params_shard_165.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.40.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.40.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.40.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.40.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 17940480 }, { "name": "model.layers.40.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20152320 }, { "name": "model.layers.40.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.41.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.41.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "be8a4165d49bdd85f715274d7d5e99f3" }, { "dataPath": "params_shard_166.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.41.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "a078e70ed9c6a3af22bf13447f7263b0" }, { "dataPath": "params_shard_167.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.41.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "102b4979cde838e7bc5ef818efb3dcdc" }, { "dataPath": "params_shard_168.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.42.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "3787cb38574ed062b69aa230d23188f1" }, { "dataPath": "params_shard_169.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.41.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.41.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.41.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.41.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 17940480 }, { "name": "model.layers.41.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20152320 }, { "name": "model.layers.41.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.42.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.42.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "5199a6ff9ba1cc51bf62c1aea790a9d2" }, { "dataPath": "params_shard_170.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.42.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "64680482c6620b22869d3125ee422abb" }, { "dataPath": "params_shard_171.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.42.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "13a5d6abd1d4e9accdb8fc2b54268005" }, { "dataPath": "params_shard_172.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.43.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "cf73c32865dffac58f10ff7ded1318db" }, { "dataPath": "params_shard_173.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.42.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.42.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.42.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.42.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 17940480 }, { "name": "model.layers.42.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20152320 }, { "name": "model.layers.42.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.43.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.43.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "6bddf71d18cf11ac9a9ada290fee87f1" }, { "dataPath": "params_shard_174.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.43.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "ff87f3db3dcd6e10ccf8428efa483469" }, { "dataPath": "params_shard_175.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.43.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "b8c25432754145973d783fcdeff83261" }, { "dataPath": "params_shard_176.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.44.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "002eedac2e4115717764ceed27db8f88" }, { "dataPath": "params_shard_177.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.43.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.43.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.43.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.43.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 17940480 }, { "name": "model.layers.43.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20152320 }, { "name": "model.layers.43.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.44.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.44.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "e85a5acd64990d644d7199e709b34451" }, { "dataPath": "params_shard_178.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.44.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "d232d273dcd9f4be8beb00f4133c7b1b" }, { "dataPath": "params_shard_179.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.44.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "f9ae30fafcf433b8658e2e499ce23a71" }, { "dataPath": "params_shard_180.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.45.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "a25047ec68f3d46c53e4a855514e66b5" }, { "dataPath": "params_shard_181.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.44.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.44.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.44.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.44.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 17940480 }, { "name": "model.layers.44.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20152320 }, { "name": "model.layers.44.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.45.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.45.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "4f3b6ffe4897a33ff3001474a32c9a4d" }, { "dataPath": "params_shard_182.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.45.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "4fcc28226d557d950f9933d456aae8d0" }, { "dataPath": "params_shard_183.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.45.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "91bf07c36335eeaf00ebbec8d62f81ab" }, { "dataPath": "params_shard_184.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.46.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "95ffee93c9d2f4b508ac10d87633147d" }, { "dataPath": "params_shard_185.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.45.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.45.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.45.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.45.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 17940480 }, { "name": "model.layers.45.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20152320 }, { "name": "model.layers.45.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.46.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.46.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "1b07832d6b01e8ae06a395e53b5961de" }, { "dataPath": "params_shard_186.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.46.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "703a4d735956756f562d91bb7b45b11f" }, { "dataPath": "params_shard_187.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.46.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "3438d1f58cf8f125a07348c6c507d6be" }, { "dataPath": "params_shard_188.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.47.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "515e7a2cb93bca3c00d95e7fc6f6a8c5" }, { "dataPath": "params_shard_189.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.46.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.46.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.46.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.46.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 17940480 }, { "name": "model.layers.46.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20152320 }, { "name": "model.layers.46.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.47.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.47.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "d0b671afdc393b5290f3f5493e70b026" }, { "dataPath": "params_shard_190.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.47.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "af8f500889b2e95a4290c5e8580703bf" }, { "dataPath": "params_shard_191.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.47.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "88154cc67ac23106b0b21f8ca3601d61" }, { "dataPath": "params_shard_192.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.48.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "f4a3154ea87ed593529b33aefb6b2c6c" }, { "dataPath": "params_shard_193.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.47.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.47.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.47.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.47.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 17940480 }, { "name": "model.layers.47.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20152320 }, { "name": "model.layers.47.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.48.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.48.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "3595a1fabe9757621b616ac893db66aa" }, { "dataPath": "params_shard_194.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.48.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "9994a0c53cf465a55a845171a41d36a7" }, { "dataPath": "params_shard_195.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.48.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "b2d2ec85f61a1d0c4b5e4056aa230e0b" }, { "dataPath": "params_shard_196.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.49.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "3d5ff400d76f66d49affc65944451542" }, { "dataPath": "params_shard_197.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.48.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.48.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.48.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.48.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 17940480 }, { "name": "model.layers.48.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20152320 }, { "name": "model.layers.48.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.49.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.49.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "069bcdd0e63bbb120a7249de211b9286" }, { "dataPath": "params_shard_198.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.49.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "748e482d7dbf63b3753be89a80859134" }, { "dataPath": "params_shard_199.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.49.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "00d49e1eda6b6ca614f8f0cc5fa1521f" }, { "dataPath": "params_shard_200.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.50.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "f1c751d62e2d1794a381124553a385b7" }, { "dataPath": "params_shard_201.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.49.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.49.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.49.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.49.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 17940480 }, { "name": "model.layers.49.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20152320 }, { "name": "model.layers.49.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.50.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.50.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "7524c75aeb936919d71f37b4bd39a0af" }, { "dataPath": "params_shard_202.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.50.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "27980e95cb6d8d10d10b237f18ba0bc2" }, { "dataPath": "params_shard_203.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.50.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "ab1108e739c650ddc736199879bc08b0" }, { "dataPath": "params_shard_204.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.51.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "33ad4ca86b20f8a651d3df4cf569bbf1" }, { "dataPath": "params_shard_205.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.50.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.50.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.50.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.50.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 17940480 }, { "name": "model.layers.50.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20152320 }, { "name": "model.layers.50.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.51.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.51.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "cac4a093113db35da3f95fd91f0f3e2a" }, { "dataPath": "params_shard_206.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.51.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "3c37f007492f8cba9562554dc8f4f373" }, { "dataPath": "params_shard_207.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.51.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "8c7a52989da9769cbbc63545ffef9f9c" }, { "dataPath": "params_shard_208.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.52.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "5a594a1873cc20888fce790aafd98768" }, { "dataPath": "params_shard_209.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.51.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.51.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.51.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.51.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 17940480 }, { "name": "model.layers.51.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20152320 }, { "name": "model.layers.51.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.52.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.52.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "acc40d31f42002acd4a1fd50dd70069f" }, { "dataPath": "params_shard_210.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.52.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "440b34764937367439e428a0c1b61257" }, { "dataPath": "params_shard_211.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.52.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "90db33ba1225a24999c24fe938bc3328" }, { "dataPath": "params_shard_212.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.53.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "0fb9426f5b3c71580e713f833ac12683" }, { "dataPath": "params_shard_213.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.52.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.52.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.52.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.52.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 17940480 }, { "name": "model.layers.52.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20152320 }, { "name": "model.layers.52.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.53.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.53.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "10e51be53fc743c1410976867848b599" }, { "dataPath": "params_shard_214.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.53.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "113013aff8050f785af7e738774119ae" }, { "dataPath": "params_shard_215.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.53.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "64edecd78d7bfcefdd26e88085f9f6e2" }, { "dataPath": "params_shard_216.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.54.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "2d15cbf82473a4a5071da340b576b941" }, { "dataPath": "params_shard_217.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.53.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.53.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.53.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.53.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 17940480 }, { "name": "model.layers.53.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20152320 }, { "name": "model.layers.53.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.54.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.54.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "dfb201548db77bb9a98f2e04c9204d0e" }, { "dataPath": "params_shard_218.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.54.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "a89caf16a40e49022cecead4806ada4d" }, { "dataPath": "params_shard_219.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.54.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "75ebdc208de081a2f7816aea2dec4cf5" }, { "dataPath": "params_shard_220.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.55.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "2d623ed33fd7ed53675427436a7bce1d" }, { "dataPath": "params_shard_221.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.54.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.54.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.54.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.54.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 17940480 }, { "name": "model.layers.54.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20152320 }, { "name": "model.layers.54.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.55.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.55.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "797095d9e274247b90b07cd6feac3f22" }, { "dataPath": "params_shard_222.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.55.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "3a5c819a8445e41badbd475e513c96d7" }, { "dataPath": "params_shard_223.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.55.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "daa14cd0be6d653b11b6e6c2da8518bc" }, { "dataPath": "params_shard_224.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.56.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "05822cee9f1457b36fa0c67953d1d959" }, { "dataPath": "params_shard_225.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.55.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.55.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.55.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.55.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 17940480 }, { "name": "model.layers.55.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20152320 }, { "name": "model.layers.55.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.56.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.56.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "5e91903be3764d5e63651b017afc53f7" }, { "dataPath": "params_shard_226.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.56.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "acf4b82bbedcb07ab4eac2511217ebf9" }, { "dataPath": "params_shard_227.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.56.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "7dae008d7bc32cf56fe11747fede857a" }, { "dataPath": "params_shard_228.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.57.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "f139967c301a14b663ac32d70bef87a5" }, { "dataPath": "params_shard_229.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.56.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.56.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.56.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.56.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 17940480 }, { "name": "model.layers.56.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20152320 }, { "name": "model.layers.56.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.57.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.57.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "d308708405e74aeeccd311cff9b97b11" }, { "dataPath": "params_shard_230.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.57.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "b9c431f6a2e0dae210224e1d81573e40" }, { "dataPath": "params_shard_231.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.57.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "bc0797370fbd5638d7ae57f3e96c03f3" }, { "dataPath": "params_shard_232.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.58.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "b9109d9848f836e97745086eaa8b29e4" }, { "dataPath": "params_shard_233.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.57.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.57.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.57.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.57.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 17940480 }, { "name": "model.layers.57.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20152320 }, { "name": "model.layers.57.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.58.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.58.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "50e66174cb716541b499ebd6a89ad56c" }, { "dataPath": "params_shard_234.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.58.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "92107572a4c50fd005d3a644ab69dbd4" }, { "dataPath": "params_shard_235.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.58.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "d5f13b196a006bc15d4fee2b3ede5c7a" }, { "dataPath": "params_shard_236.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.59.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "712fc8aff74c3bd8255a3a33c6503b8f" }, { "dataPath": "params_shard_237.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.58.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.58.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.58.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.58.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 17940480 }, { "name": "model.layers.58.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20152320 }, { "name": "model.layers.58.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.59.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.59.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "ea4b6c1f1497cc4e06cf04dbce59c43c" }, { "dataPath": "params_shard_238.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.59.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "931d813731cb8656c8dba0ef8d7752c1" }, { "dataPath": "params_shard_239.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.59.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "d504d6bed5290fbcfe16a0c40ee085ab" }, { "dataPath": "params_shard_240.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.60.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "59b5d7e8cc9df0805a63260d304a2eff" }, { "dataPath": "params_shard_241.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.59.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.59.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.59.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.59.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 17940480 }, { "name": "model.layers.59.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20152320 }, { "name": "model.layers.59.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.60.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.60.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "962dfc64cb1143fbaed9076816a82b6b" }, { "dataPath": "params_shard_242.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.60.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "9e743b1073cc7328c3f93fe96065ca57" }, { "dataPath": "params_shard_243.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.60.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "9d3cf9efaa9b67f00baf253f28373444" }, { "dataPath": "params_shard_244.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.61.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "04596f452078ea3830ee679dc57e424d" }, { "dataPath": "params_shard_245.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.60.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.60.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.60.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.60.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 17940480 }, { "name": "model.layers.60.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20152320 }, { "name": "model.layers.60.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.61.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.61.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "ffebd6c05ce0f67964035af0df5b1102" }, { "dataPath": "params_shard_246.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.61.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "44f3d11d7194b5c0ae43fa1003d059d0" }, { "dataPath": "params_shard_247.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.61.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "9b85ceb37a98bc96d24f27d9cbe9d2e1" }, { "dataPath": "params_shard_248.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.62.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "cb9fd6ec6f3dba630bd7b9b04944766a" }, { "dataPath": "params_shard_249.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.61.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.61.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.61.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.61.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 17940480 }, { "name": "model.layers.61.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20152320 }, { "name": "model.layers.61.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.62.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.62.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "ea3dde8a543fbd02679e87ec1e4f21e7" }, { "dataPath": "params_shard_250.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.62.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "81b1d5dcbb6db64635997fe00e4d9fda" }, { "dataPath": "params_shard_251.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.62.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "98bca412296ab3ae73f30150ce557fa2" }, { "dataPath": "params_shard_252.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.63.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "f5c1050e97a9f8bddb1097a90bc2e6e1" }, { "dataPath": "params_shard_253.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.62.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.62.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.62.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.62.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 17940480 }, { "name": "model.layers.62.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20152320 }, { "name": "model.layers.62.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.63.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.63.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "a71c36eadf9412ee5b9ab4506d681675" }, { "dataPath": "params_shard_254.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.63.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "6bb3cd53f75fcce7e6cdfffa0fcdc3a4" }, { "dataPath": "params_shard_255.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.63.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "ddf4b635c6e5a5fe2d9cdb3d44069ced" }, { "dataPath": "params_shard_256.bin", "format": "raw-shard", "nbytes": 389283840, "records": [ { "name": "lm_head.q_weight", "shape": [ 640, 152064 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 389283840, "byteOffset": 0 } ], "md5sum": "fc6101d4aec293d4610b4d061da07594" }, { "dataPath": "params_shard_257.bin", "format": "raw-shard", "nbytes": 32348160, "records": [ { "name": "model.layers.63.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.63.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.63.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.63.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 17940480 }, { "name": "model.layers.63.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20152320 }, { "name": "model.layers.63.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.norm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20172800 }, { "name": "lm_head.q_scale", "shape": [ 40, 152064 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12165120, "byteOffset": 20183040 } ], "md5sum": "814c979637fb930826b64089b7044687" } ] }