{ "metadata": { "ParamSize": 709, "ParamBytes": 16895535104.0, "BitsPerParam": 4.125405656518088 }, "records": [ { "dataPath": "params_shard_0.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": "e514aca4c682d50ee4cb08b855b1154d" }, { "dataPath": "params_shard_1.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": "9cb18e190462c9789f0b70fbd536add8" }, { "dataPath": "params_shard_2.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": "06dad7677b4ed79524a44ddbd1a6fcf9" }, { "dataPath": "params_shard_3.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": "9cf3a271e940b843da9ba8b06c130ebf" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.0.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "ef5c0e5c075cc868c9e78370cbd5905e" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 31574016, "records": [ { "name": "lm_head.q_scale", "shape": [ 40, 152064 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12165120, "byteOffset": 0 }, { "name": "model.embed_tokens.q_scale", "shape": [ 152064, 40 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12165120, "byteOffset": 12165120 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 24330240 }, { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 24340480 }, { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 26552320 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 30976000 }, { "name": "model.layers.0.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 30986240 }, { "name": "model.layers.0.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 31000576 } ], "md5sum": "034fa3f03faa5e0862833237b4997a08" }, { "dataPath": "params_shard_6.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": "ffb4c1f6b544958fda42aeb7a0561d17" }, { "dataPath": "params_shard_7.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": "1d50d56030938741077b8c2417fd9565" }, { "dataPath": "params_shard_8.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": "c24aa7a97eecd8306733ef40411888a6" }, { "dataPath": "params_shard_9.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.1.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.1.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.1.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": "916f5d77066a2e697479774fb5922929" }, { "dataPath": "params_shard_10.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": "0114f243a054ab0982b3e368fa88d4e6" }, { "dataPath": "params_shard_11.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": "364bc012bc3dbbcc979546700586eaad" }, { "dataPath": "params_shard_12.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": "8d3d9ead6aefe403f79d2dd96be98ab9" }, { "dataPath": "params_shard_13.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.10.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.10.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.10.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": "d38ddf35e432739af3c56ad915959601" }, { "dataPath": "params_shard_14.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": "d346237f43db034f039bf0be28eea5a6" }, { "dataPath": "params_shard_15.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": "ca66f1dbce88e8ee582ff28cdcd72592" }, { "dataPath": "params_shard_16.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": "2b259e4b1b8f61d6a7d7be074403e005" }, { "dataPath": "params_shard_17.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.11.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.11.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.11.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": "e9375510bd1991be58e959f36bc674df" }, { "dataPath": "params_shard_18.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": "b7b0d3eb8d9f53be076e6f126c82b454" }, { "dataPath": "params_shard_19.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": "f072c7c988e923467fbba8e570fa8918" }, { "dataPath": "params_shard_20.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": "ac361295b9a492c04db5136930eaaf99" }, { "dataPath": "params_shard_21.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.12.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.12.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.12.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.12.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": "92834dd74fbdafaa368be5189d48d38b" }, { "dataPath": "params_shard_22.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": "6f250ddb642d28d70b2d6779d26e38c1" }, { "dataPath": "params_shard_23.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": "a9876973d82afea1f933fba566974bdb" }, { "dataPath": "params_shard_24.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": "2488ac1e9ae70ea543ad63711e1350ff" }, { "dataPath": "params_shard_25.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.13.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.13.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.13.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": "db0cf5718ad37539595f7b7cf55467e5" }, { "dataPath": "params_shard_26.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": "f66ea1fd330c1d98ede9204fd1c27f4f" }, { "dataPath": "params_shard_27.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": "c2d4691f83ce44f17dd6fc6b3e0b6fe1" }, { "dataPath": "params_shard_28.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": "d28c11a8cf83bd470b4a990726e82586" }, { "dataPath": "params_shard_29.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.14.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.14.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.14.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": "a7aac5f05e15094024233386b6453d35" }, { "dataPath": "params_shard_30.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": "50ff011d62eca6338f26482fca3b0b63" }, { "dataPath": "params_shard_31.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": "5230d3593c8fa3a1c62258f553f5033c" }, { "dataPath": "params_shard_32.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": "0d9f3196ec6bf1c8d6cef24ddc1bddab" }, { "dataPath": "params_shard_33.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.15.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.15.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.15.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": "362bc54c797e7961742221c537a011f1" }, { "dataPath": "params_shard_34.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": "51d6e8dd2adec67c7c9e09163b8d2704" }, { "dataPath": "params_shard_35.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": "3cf0a54ba3fb8784fa15593df890b628" }, { "dataPath": "params_shard_36.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": "402801c5c379962b172b6c18bc0724b4" }, { "dataPath": "params_shard_37.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.16.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.16.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.16.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.16.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": "eeb784751bda3f7472710e55ba7c98c3" }, { "dataPath": "params_shard_38.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": "95c80c01c527dab61b5b932590ee350c" }, { "dataPath": "params_shard_39.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": "fff693a327d921b8e909e23d02eba397" }, { "dataPath": "params_shard_40.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": "5761436559db39f44239e420956c96f5" }, { "dataPath": "params_shard_41.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.17.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.17.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.17.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.17.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": "b2672e2beb049000ad033a3d4755737a" }, { "dataPath": "params_shard_42.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": "7cd69ffcc9a195f6bfe807412dedbd86" }, { "dataPath": "params_shard_43.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": "5a9e5bf27ecf3b55faaa2a6cc5dd0518" }, { "dataPath": "params_shard_44.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": "ebca7cc04bcabe46320b4869482939a0" }, { "dataPath": "params_shard_45.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.18.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.18.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.18.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.18.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": "92322a3d2bc91e360980f5990acfdca3" }, { "dataPath": "params_shard_46.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": "bdd3e519ca2fb440ab7ff91246698022" }, { "dataPath": "params_shard_47.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": "211c698c8869992ccb79bdca68a8444f" }, { "dataPath": "params_shard_48.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": "815bc0f80e56793cf2e68f4d134ca462" }, { "dataPath": "params_shard_49.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.19.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.19.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.19.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.19.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": "224aa969234d62e700d931ec1e21e262" }, { "dataPath": "params_shard_50.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": "0c4828a30434f15834be04976ce8bd43" }, { "dataPath": "params_shard_51.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": "261c91c378bffef4361c596ef061a146" }, { "dataPath": "params_shard_52.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": "91619426adde771e6a780cafbe0b5bdd" }, { "dataPath": "params_shard_53.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.2.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.2.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.2.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": "6498639c39e6df461f75945173d611b5" }, { "dataPath": "params_shard_54.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": "e3f18601a71ef851af116c3793e277a8" }, { "dataPath": "params_shard_55.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": "00a79e4653205ca670d06ac3f2cb03f2" }, { "dataPath": "params_shard_56.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": "e8bdb0261b918a6c02923c091d053873" }, { "dataPath": "params_shard_57.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.20.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.20.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.20.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.20.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": "34c3163bac91ce27b1abc1aa3382e154" }, { "dataPath": "params_shard_58.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": "f55968be109830ee73bc5f8e68842273" }, { "dataPath": "params_shard_59.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": "efe24b37b2e583d26bd82f27f87b823c" }, { "dataPath": "params_shard_60.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": "0f690e450a0239e5d98e228e5d746942" }, { "dataPath": "params_shard_61.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.21.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.21.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.21.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.21.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": "d5a13b29e87787b217a98c1e4f291211" }, { "dataPath": "params_shard_62.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": "1aae928d1df22c726185ac225bab72c4" }, { "dataPath": "params_shard_63.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": "b8fab896a0c2e1446edaa67dbff8c66d" }, { "dataPath": "params_shard_64.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": "61c349bebaca9f363b514cd0e2978313" }, { "dataPath": "params_shard_65.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.22.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.22.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.22.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.22.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": "a489e93a30b8e58bd8ca5c9bdfd65d4d" }, { "dataPath": "params_shard_66.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": "9de5d042e528a91f9b32c57bffdd0914" }, { "dataPath": "params_shard_67.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": "a7faca051d2ab44cd16a8cef002643d7" }, { "dataPath": "params_shard_68.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": "25fea6f9eca4e3ba9cb8d28877cf7f4d" }, { "dataPath": "params_shard_69.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.23.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.23.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.23.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.23.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": "7ad512dea896dfa6d5e02325ac84f553" }, { "dataPath": "params_shard_70.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": "37734868c1f5efc3c85964e1fa66360f" }, { "dataPath": "params_shard_71.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": "8da309bd23173475bc7ab9939a94cd37" }, { "dataPath": "params_shard_72.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": "3880b9c30c4c691ca444dfc7248debef" }, { "dataPath": "params_shard_73.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.24.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.24.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.24.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.24.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": "90e2bdee1aaf106e38b13e30626da90d" }, { "dataPath": "params_shard_74.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": "72838ca1efce265b053b38608f9f9ee1" }, { "dataPath": "params_shard_75.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": "81aaac09c01cce4ee961676132a571a6" }, { "dataPath": "params_shard_76.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": "74ffa5c6a5e6f92f249153c8a5ee5937" }, { "dataPath": "params_shard_77.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.25.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.25.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.25.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.25.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": "4fd7e1c28c9032d19c43c79ab498ee6a" }, { "dataPath": "params_shard_78.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": "13e964f04c210c6899bad7b5adfa9bad" }, { "dataPath": "params_shard_79.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": "7124c4fb7527915d5dd7501aa1c59546" }, { "dataPath": "params_shard_80.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": "e5bb5792ff8f608e50c7990a594c67d7" }, { "dataPath": "params_shard_81.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.26.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.26.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.26.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.26.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": "dec04173c08cafd1d292fda5bcdf9ada" }, { "dataPath": "params_shard_82.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": "ac95ab90e37d02639e749e9b3ecdc6c3" }, { "dataPath": "params_shard_83.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": "9fb44ceac5ff535efbed085a48746926" }, { "dataPath": "params_shard_84.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": "6164e1bfb53c7e7b01732ca5d67da336" }, { "dataPath": "params_shard_85.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.27.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.27.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.27.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.27.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": "235bfcb4baf0cb76f75aa24bad07755e" }, { "dataPath": "params_shard_86.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": "828a3d5674282a737c354d2184e553a0" }, { "dataPath": "params_shard_87.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": "588f7f8018065a57499ad786d0fe7550" }, { "dataPath": "params_shard_88.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": "1f0fec41cb8f1750cf340d1d6ed9864c" }, { "dataPath": "params_shard_89.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.28.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.28.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.28.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.28.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": "a9a27a80e6d297d72aa07acb1374351d" }, { "dataPath": "params_shard_90.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": "2cbad330874b83655fdf1b1ccefa46ac" }, { "dataPath": "params_shard_91.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": "8aa7682a75eb82e724605957f9d6bb1b" }, { "dataPath": "params_shard_92.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": "4cd2ab52174f5858181499d8fac88037" }, { "dataPath": "params_shard_93.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.29.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.29.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.29.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.29.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": "6c0a2e12ea6f16129c6c9da7bb688a70" }, { "dataPath": "params_shard_94.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": "f93a950bd3d28c3052a4201042f3c9b1" }, { "dataPath": "params_shard_95.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": "10e1b9c0de4d179e0fd242be48edd2fc" }, { "dataPath": "params_shard_96.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": "c326cba0f5b41b27ed08e5f14f56ed00" }, { "dataPath": "params_shard_97.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.3.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.3.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.3.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": "213c7404722fd4ab580fd2d0ae0eb0da" }, { "dataPath": "params_shard_98.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": "9623379071afb5a56bd91c14900cee71" }, { "dataPath": "params_shard_99.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": "5a6eb73d85213850540eeb0b5e77f97e" }, { "dataPath": "params_shard_100.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": "ed0dc87251271e54ebb05b0ed8a105ae" }, { "dataPath": "params_shard_101.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.30.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.30.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.30.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.30.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": "a6425cc0df64e234022874f007b5d3b2" }, { "dataPath": "params_shard_102.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": "3dfcb0e3e6040f05dd1c12f1430d73bd" }, { "dataPath": "params_shard_103.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": "fff26b50e7e18d7ef210008d5f37b581" }, { "dataPath": "params_shard_104.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": "6c3f3dade283c306c6228528b5a6c422" }, { "dataPath": "params_shard_105.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.31.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.31.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.31.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.31.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": "3435690b788647cf7a22a8c897addacf" }, { "dataPath": "params_shard_106.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": "55d0453e4bf2dc2ad9e613b261df176a" }, { "dataPath": "params_shard_107.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": "fffd74b7bb7f2af5859d3707c76a1acd" }, { "dataPath": "params_shard_108.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": "53d778a64a1d4806f27b2e25f8cf52e9" }, { "dataPath": "params_shard_109.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.32.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.32.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.32.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.32.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": "c5d01e9ad249b3e2400c635500323b28" }, { "dataPath": "params_shard_110.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": "633fe2e4dd7b2cc3ba3104f7d693120a" }, { "dataPath": "params_shard_111.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": "dadaf5b4f17b21ff01803894df64c3e6" }, { "dataPath": "params_shard_112.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": "6d1ecff8bfc7d59ee842ae591c8ca39c" }, { "dataPath": "params_shard_113.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.33.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.33.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.33.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.33.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": "fd70fc08fd9a7c36a1f842ceecae2292" }, { "dataPath": "params_shard_114.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": "9cc9190cd4517b5d727e59c977ae1671" }, { "dataPath": "params_shard_115.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": "33b96f0a90e7de7cb3cee8136875df1b" }, { "dataPath": "params_shard_116.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": "70e87a6886a9a179983c450e4b3d34f2" }, { "dataPath": "params_shard_117.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.34.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.34.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.34.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.34.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": "8662e0442fe6709eda1068cc35feb61a" }, { "dataPath": "params_shard_118.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": "d8dbc267b2361240dbffae9cf0c98df6" }, { "dataPath": "params_shard_119.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": "f4575e2d9703230e49041ecfae0c1ece" }, { "dataPath": "params_shard_120.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": "d1e631142200c317045dc54fb8eb1098" }, { "dataPath": "params_shard_121.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.35.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.35.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.35.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.35.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": "8a3a7e469f4f9706cff4c3f8d9054762" }, { "dataPath": "params_shard_122.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": "dbd979dc01ae0116100d677927d494fd" }, { "dataPath": "params_shard_123.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": "a105a417c96646f092b09ad13f66c5c0" }, { "dataPath": "params_shard_124.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": "987861d2cd9a76a340fd6d84071b30c8" }, { "dataPath": "params_shard_125.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.36.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.36.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.36.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.36.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": "b6cef9ea47a7d5a2aea87a24d9969eec" }, { "dataPath": "params_shard_126.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": "43c54d0acdbd9f90f2ca5d676ef75227" }, { "dataPath": "params_shard_127.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": "6dcb27eb9c4c47eddb26d11152b8c6f3" }, { "dataPath": "params_shard_128.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": "31e6db4b7d2ed24a5ff5ed08f7026c49" }, { "dataPath": "params_shard_129.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.37.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.37.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.37.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.37.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": "46e8c4ca3e7b53fbe4d340c5901252c1" }, { "dataPath": "params_shard_130.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": "f195698dc3dbb4a0a5df03aaf6015ee8" }, { "dataPath": "params_shard_131.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": "e556fbdfe6fa39b5576ee6757bf8ee5c" }, { "dataPath": "params_shard_132.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": "615061220e62d67d9dc5d3f6bc854830" }, { "dataPath": "params_shard_133.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.38.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.38.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.38.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.38.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": "6fa78a645efba4983e8e931e54428b51" }, { "dataPath": "params_shard_134.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": "5a84c2ea31d886315d80ead7fa37684d" }, { "dataPath": "params_shard_135.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": "0c86d27835c962054b0ea13a54e29f44" }, { "dataPath": "params_shard_136.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": "8dca2d313911170c1b03bd3905c77869" }, { "dataPath": "params_shard_137.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.39.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.39.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.39.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.39.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": "6afdbbbf395fa105cd3105ab42bfec33" }, { "dataPath": "params_shard_138.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": "12e8229e94b6ea632832bc5e01052a33" }, { "dataPath": "params_shard_139.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": "9c64e4be3b125d4b68bd2d7a2621d4ba" }, { "dataPath": "params_shard_140.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": "77f5469b3e85a109f8ed6293fe2f98b0" }, { "dataPath": "params_shard_141.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.4.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.4.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.4.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.4.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": "9b2fed524429a21074aaa65d47b4f029" }, { "dataPath": "params_shard_142.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": "dc0f1d7b326608c9c5c0accc057ba7f5" }, { "dataPath": "params_shard_143.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": "8bd11a566294007f5a47aa69066ae8c5" }, { "dataPath": "params_shard_144.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": "0e9424e9f2e585a8c78527f4f46da032" }, { "dataPath": "params_shard_145.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.40.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.40.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.40.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.40.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": "49d59055fa03c6720b17235aa4cd1341" }, { "dataPath": "params_shard_146.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": "ce6cb548ab5d65c1d05d208a7c1a8562" }, { "dataPath": "params_shard_147.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": "431a0c935a1c838656d0d360abaf87c8" }, { "dataPath": "params_shard_148.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": "c0345d1f97de80d6880d0255f742db7a" }, { "dataPath": "params_shard_149.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.41.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.41.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.41.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.41.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": "c5c702d10795154ebf6c5d69203f6cc7" }, { "dataPath": "params_shard_150.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": "599412788af765dee563f897941219a5" }, { "dataPath": "params_shard_151.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": "3d5b8027dba42fede295c2641904b230" }, { "dataPath": "params_shard_152.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": "7ddea37b42a84bd48c244fe9107b6623" }, { "dataPath": "params_shard_153.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.42.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.42.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.42.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.42.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": "806ef2c337c7833db9c7d042bc20bf95" }, { "dataPath": "params_shard_154.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": "19d802b134d75061059d26195083793f" }, { "dataPath": "params_shard_155.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": "b1bcb7c6f6c29ea7f091dfdf317187b0" }, { "dataPath": "params_shard_156.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": "9807ab49bdccdd6953d8d0635832150c" }, { "dataPath": "params_shard_157.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.43.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.43.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.43.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.43.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": "02cc7d5baee3ac110fe0c29736a1eb9a" }, { "dataPath": "params_shard_158.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": "50ee534f865bcde45f309baa1c201d05" }, { "dataPath": "params_shard_159.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": "fb851f8fa85e6f54ce8757dd20677e33" }, { "dataPath": "params_shard_160.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": "359951516bb3f550113a8b6ed986a128" }, { "dataPath": "params_shard_161.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.44.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.44.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.44.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.44.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": "b7bdbc15c70ae333411056e5f66389e0" }, { "dataPath": "params_shard_162.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": "5526d31d0140de9c501187345ef85b5f" }, { "dataPath": "params_shard_163.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": "8806ede0ccfcd419ecd854d717b63d84" }, { "dataPath": "params_shard_164.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": "c946cb01bf428d17ff5ab70017d03b8f" }, { "dataPath": "params_shard_165.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.45.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.45.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.45.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.45.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": "f16f7248d3669b07d918662885a23f8b" }, { "dataPath": "params_shard_166.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": "cb61d7cff6cd74cf5798a42d5b79c7eb" }, { "dataPath": "params_shard_167.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": "1d89dfce6a7b922786d239bdc34ef1b7" }, { "dataPath": "params_shard_168.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": "c182aec014c9302c79a8c286dcb9354b" }, { "dataPath": "params_shard_169.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.46.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.46.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.46.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.46.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": "75ef3548cb6cf46fb1e021e92815002b" }, { "dataPath": "params_shard_170.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": "eee68bcdccca20f727515612b5f143dd" }, { "dataPath": "params_shard_171.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": "c10ee56c9482ac631e0c049b80802af2" }, { "dataPath": "params_shard_172.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": "862b2afa6eadff71c2ecd682b9b8969b" }, { "dataPath": "params_shard_173.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.47.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.47.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.47.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.47.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": "00adb009a237138dc72b9ff3e62aa1f7" }, { "dataPath": "params_shard_174.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": "7b45b1f271c8a13cc0d355c8dd589cc0" }, { "dataPath": "params_shard_175.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": "f916cee980962dbe0cf51e79d73c900d" }, { "dataPath": "params_shard_176.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": "045ce4c39b12a8f24bf65e5c0b7ae3af" }, { "dataPath": "params_shard_177.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.48.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.48.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.48.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.48.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": "0c71d311a8ee6d9e2c257692ea5dcf12" }, { "dataPath": "params_shard_178.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": "b23fc22e29c37f64bf4b9499a89413b8" }, { "dataPath": "params_shard_179.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": "04662b979a713f05b50419f2f49fdff7" }, { "dataPath": "params_shard_180.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": "ace809b959a5c997118d1311ad18b379" }, { "dataPath": "params_shard_181.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.49.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.49.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.49.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.49.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": "ba0c89f1f3d2452f1c7ff09fe7f82889" }, { "dataPath": "params_shard_182.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": "09da40d803df8f54b101b099389e760d" }, { "dataPath": "params_shard_183.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": "5bc9d4f6b0d5ed95450b387e693631fe" }, { "dataPath": "params_shard_184.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": "b891c12458722f2cc4a685b309466170" }, { "dataPath": "params_shard_185.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.5.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.5.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.5.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": "d7c6363c45ece7eea1469cb45dccbd23" }, { "dataPath": "params_shard_186.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": "4ee5d6495635f48349e165545a209ee2" }, { "dataPath": "params_shard_187.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": "ee8f2d76b32964b4dc2da2a44a6d7fc8" }, { "dataPath": "params_shard_188.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": "eeb4c680c8a58c346b00ed57761972b8" }, { "dataPath": "params_shard_189.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.50.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.50.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.50.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.50.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": "52434c08787f2c83e7cabde2574c8538" }, { "dataPath": "params_shard_190.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": "20756e3ce960846d21e2432aee3587dc" }, { "dataPath": "params_shard_191.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": "b926c78a1d37ca2a46daec17f36748ff" }, { "dataPath": "params_shard_192.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": "f55a8c78ad798072c1051a2aacd45e0a" }, { "dataPath": "params_shard_193.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.51.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.51.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.51.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.51.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": "4c386cf1333fc61c960da93e564fbaa0" }, { "dataPath": "params_shard_194.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": "1d306303a25e1191baa3c1d78cf575a8" }, { "dataPath": "params_shard_195.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": "5b641e3859382fd2fc5088a537a06d1f" }, { "dataPath": "params_shard_196.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": "f7368b3e411b445433d1ef9489d6e55f" }, { "dataPath": "params_shard_197.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.52.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.52.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.52.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.52.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": "c1aeb519a2e3e1dfdc894b355c8aaa6e" }, { "dataPath": "params_shard_198.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": "4fc3d783504b165cc7055462ff6e587f" }, { "dataPath": "params_shard_199.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": "f0fba927f9e8a03c455c5b2fae1d0f16" }, { "dataPath": "params_shard_200.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": "30e70dab5c13562bf2f8b9cdbd3e0cda" }, { "dataPath": "params_shard_201.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.53.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.53.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.53.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.53.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": "d17ae76071b741bbbe655cfc4670b057" }, { "dataPath": "params_shard_202.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": "ebce8236d32cfee5ae4d7ec6eb80c35f" }, { "dataPath": "params_shard_203.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": "064ee6cd2552d54f45623850da28ef17" }, { "dataPath": "params_shard_204.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": "0688d5f50da1b03c8a25256707e1e164" }, { "dataPath": "params_shard_205.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.54.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.54.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.54.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.54.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": "37390a00a29408430d26c235380cbc3a" }, { "dataPath": "params_shard_206.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": "8a3b63861b992488063ccf314b93ceab" }, { "dataPath": "params_shard_207.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": "d6f5696f2f23aea879441e51ef5905fc" }, { "dataPath": "params_shard_208.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": "cd2d34ab39509bab7cece90490069d70" }, { "dataPath": "params_shard_209.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.55.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.55.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.55.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.55.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": "f48e5931bf5c52d0d2ec1fa97e68b071" }, { "dataPath": "params_shard_210.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": "e2289b575146ec5892dbc9b9e3e2bcb4" }, { "dataPath": "params_shard_211.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": "632801adfa2f42376a05d3dcb1ae591b" }, { "dataPath": "params_shard_212.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": "7019450869b27bffd264f012e0e4f7a6" }, { "dataPath": "params_shard_213.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.56.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.56.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.56.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.56.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": "a43a889872faa60671a623150ee2cb31" }, { "dataPath": "params_shard_214.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": "8052cbd948e6333825c67494356f6f6a" }, { "dataPath": "params_shard_215.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": "f428916e79cdea1c5a05770782a532be" }, { "dataPath": "params_shard_216.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": "41a9d9dd2b461e87fc1dfc99df416f67" }, { "dataPath": "params_shard_217.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.57.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.57.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.57.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.57.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": "72c4f9fb3f5fa146404b7ace5a47a667" }, { "dataPath": "params_shard_218.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": "b9939fff6aa0e4eac26f7c38b0fc1391" }, { "dataPath": "params_shard_219.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": "115e4ca8a8d367d30369455afa28eb57" }, { "dataPath": "params_shard_220.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": "66e5c5d64654e198345797af054ec119" }, { "dataPath": "params_shard_221.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.58.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.58.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.58.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.58.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": "68f38229593a7817f8bc06bba0c9f5c6" }, { "dataPath": "params_shard_222.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": "4f9acb2337bd126fa0c893f94ce0a745" }, { "dataPath": "params_shard_223.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": "43c1c0da3c36d0005d80962299394dd0" }, { "dataPath": "params_shard_224.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": "62f230c958e25a4ed90413affca41d72" }, { "dataPath": "params_shard_225.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.59.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.59.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.59.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.59.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": "80da5196abf5d6060cda97bb08438abc" }, { "dataPath": "params_shard_226.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": "c147afb13b4d00a922d7c835a09a8c49" }, { "dataPath": "params_shard_227.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": "f2e972074c113d65b6e84972300bc14e" }, { "dataPath": "params_shard_228.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": "3011fbca4c282a1b698e882da230c4da" }, { "dataPath": "params_shard_229.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.6.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.6.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.6.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.6.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": "429d637ec66f0000d675c7e93a0f64df" }, { "dataPath": "params_shard_230.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": "f09a8fb57115ce2ef0ee8b52aca69401" }, { "dataPath": "params_shard_231.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": "e79cf5927aa78b4a58f558562c627f69" }, { "dataPath": "params_shard_232.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": "6600da09bbcdd9e03ab8eee2eaec9f6d" }, { "dataPath": "params_shard_233.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.60.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.60.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.60.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.60.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": "5dc508b2f74f02360e536e24700863cf" }, { "dataPath": "params_shard_234.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": "224484ac6fa25f5d529b314995b913a3" }, { "dataPath": "params_shard_235.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": "f0b0268f6e4f311eaac7211c8c3e2756" }, { "dataPath": "params_shard_236.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": "a97dbfa6a3294a7f85736ebdaf6e4a19" }, { "dataPath": "params_shard_237.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.61.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.61.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.61.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.61.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": "489f688276e5e7751cee2288d4f02a25" }, { "dataPath": "params_shard_238.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": "3222e6f9405ee0717a05e1a9cd22f6e8" }, { "dataPath": "params_shard_239.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": "b38d17d3162c14631de219e0d6f36ed5" }, { "dataPath": "params_shard_240.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": "cf8e6f72723b4c60ad25ae84a6489b70" }, { "dataPath": "params_shard_241.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.62.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.62.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.62.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.62.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": "e7a409ef6716b3dfc2d118acc2b9852b" }, { "dataPath": "params_shard_242.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": "ecc407247e8ea6fc0999195aaff060d7" }, { "dataPath": "params_shard_243.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": "d99e70926ab570954322da7965bdfbb0" }, { "dataPath": "params_shard_244.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": "7a788f9f21e8f8f12aaf6f5ad1b64152" }, { "dataPath": "params_shard_245.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.63.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.63.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.63.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.63.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": "7c05d6157ed5292c7f7d11ba79e99c45" }, { "dataPath": "params_shard_246.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": "f608ffd2f30678a4cc7754b6503f0a32" }, { "dataPath": "params_shard_247.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": "ce65e55d2eb19cbfa5f8274039493698" }, { "dataPath": "params_shard_248.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": "19d4d93de13892f83a826649199a3e52" }, { "dataPath": "params_shard_249.bin", "format": "raw-shard", "nbytes": 20760576, "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.7.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.7.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.7.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.7.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": "5097b3dda17322d492bcf138a5c76755" }, { "dataPath": "params_shard_250.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": "cdf1d32e815807d32c10ff6879d9e01e" }, { "dataPath": "params_shard_251.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": "6fab47a5c535a74d81e51912cac5ed88" }, { "dataPath": "params_shard_252.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": "587ca97d5182d02d5234709509f810c6" }, { "dataPath": "params_shard_253.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.8.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.8.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.8.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": "4b16da2148ddb4013727bb1f2153e79f" }, { "dataPath": "params_shard_254.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": "97e4e1600c287f6f986ecbcc3e05c45c" }, { "dataPath": "params_shard_255.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": "617f3891306e9b788cc367415ef711b5" }, { "dataPath": "params_shard_256.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": "5eefe89c5b5bb196400f60fd381b6dbf" }, { "dataPath": "params_shard_257.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.9.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.9.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.9.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": "5a623715713a91e8d78e482cc1dc1fb4" }, { "dataPath": "params_shard_258.bin", "format": "raw-shard", "nbytes": 13527040, "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.norm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 } ], "md5sum": "afa707485eecce27b71c4baba9711db8" } ] }