{ "metadata": { "ParamSize": 163, "ParamBytes": 695242752.0, "BitsPerParam": 4.500628909972241 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 131334144, "records": [ { "name": "model.embed_tokens.q_weight", "shape": [ 128256, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131334144, "byteOffset": 0 } ], "md5sum": "52e3814909f1c51c81cc5bb61a197549" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "2fbca3bfad5305393baa7b4039002755" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 31498240, "records": [ { "name": "model.embed_tokens.q_scale", "shape": [ 128256, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16416768, "byteOffset": 0 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 16416768 }, { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 16420864 }, { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 24809472 }, { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 25858048 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 27955200 }, { "name": "model.layers.0.self_attn.qkv_proj.q_weight", "shape": [ 3072, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 27959296 }, { "name": "model.layers.0.self_attn.qkv_proj.q_scale", "shape": [ 3072, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 393216, "byteOffset": 31105024 } ], "md5sum": "a1b1164e6a61b475434bf4f88aed2f01" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 30679040, "records": [ { "name": "model.layers.0.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 0 }, { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 2097152 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 2359296 }, { "name": "model.layers.1.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 2363392 }, { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 10752000 }, { "name": "model.layers.1.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 11800576 }, { "name": "model.layers.1.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 28577792 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 30674944 } ], "md5sum": "5447e7078e9caacd33799a69aa53cd19" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 32116736, "records": [ { "name": "model.layers.1.self_attn.qkv_proj.q_weight", "shape": [ 3072, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 0 }, { "name": "model.layers.1.self_attn.qkv_proj.q_scale", "shape": [ 3072, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 393216, "byteOffset": 3145728 }, { "name": "model.layers.1.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 3538944 }, { "name": "model.layers.1.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 5636096 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 5898240 }, { "name": "model.layers.10.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 5902336 }, { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 14290944 }, { "name": "model.layers.10.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 15339520 } ], "md5sum": "bedf1984a0877b8d1f85ec43bf59fa7f" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "759e202d199bb28234bb234f8c0d1b89" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 25444352, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 0 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 2097152 }, { "name": "model.layers.10.self_attn.qkv_proj.q_weight", "shape": [ 3072, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 2101248 }, { "name": "model.layers.10.self_attn.qkv_proj.q_scale", "shape": [ 3072, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 393216, "byteOffset": 5246976 }, { "name": "model.layers.10.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 5640192 }, { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 7737344 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 7999488 }, { "name": "model.layers.11.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 8003584 }, { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 16392192 }, { "name": "model.layers.11.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 17440768 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 19537920 }, { "name": "model.layers.11.self_attn.qkv_proj.q_weight", "shape": [ 3072, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 19542016 }, { "name": "model.layers.11.self_attn.qkv_proj.q_scale", "shape": [ 3072, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 393216, "byteOffset": 22687744 }, { "name": "model.layers.11.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 23080960 }, { "name": "model.layers.11.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 25178112 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 25440256 } ], "md5sum": "35c908f10feaca79d9b6a0ae8adf0ae4" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 31854592, "records": [ { "name": "model.layers.12.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.12.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.12.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 9437184 }, { "name": "model.layers.12.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 26214400 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 28311552 }, { "name": "model.layers.12.self_attn.qkv_proj.q_weight", "shape": [ 3072, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 28315648 }, { "name": "model.layers.12.self_attn.qkv_proj.q_scale", "shape": [ 3072, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 393216, "byteOffset": 31461376 } ], "md5sum": "92a82ae3fc9bf8b5dd6762f45c00ca4e" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 30679040, "records": [ { "name": "model.layers.12.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 0 }, { "name": "model.layers.12.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 2097152 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 2359296 }, { "name": "model.layers.13.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 2363392 }, { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 10752000 }, { "name": "model.layers.13.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 11800576 }, { "name": "model.layers.13.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 28577792 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 30674944 } ], "md5sum": "40fbe27d43ccf845e2531a94d985fe14" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 32116736, "records": [ { "name": "model.layers.13.self_attn.qkv_proj.q_weight", "shape": [ 3072, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 0 }, { "name": "model.layers.13.self_attn.qkv_proj.q_scale", "shape": [ 3072, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 393216, "byteOffset": 3145728 }, { "name": "model.layers.13.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 3538944 }, { "name": "model.layers.13.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 5636096 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 5898240 }, { "name": "model.layers.14.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 5902336 }, { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 14290944 }, { "name": "model.layers.14.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 15339520 } ], "md5sum": "a460e7875e02882cd6bc1abfb7fb1f41" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "3d0485395f54d1b15c8e2a9c1ce542fb" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 25444352, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 0 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 2097152 }, { "name": "model.layers.14.self_attn.qkv_proj.q_weight", "shape": [ 3072, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 2101248 }, { "name": "model.layers.14.self_attn.qkv_proj.q_scale", "shape": [ 3072, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 393216, "byteOffset": 5246976 }, { "name": "model.layers.14.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 5640192 }, { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 7737344 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 7999488 }, { "name": "model.layers.15.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 8003584 }, { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 16392192 }, { "name": "model.layers.15.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 17440768 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 19537920 }, { "name": "model.layers.15.self_attn.qkv_proj.q_weight", "shape": [ 3072, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 19542016 }, { "name": "model.layers.15.self_attn.qkv_proj.q_scale", "shape": [ 3072, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 393216, "byteOffset": 22687744 }, { "name": "model.layers.15.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 23080960 }, { "name": "model.layers.15.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 25178112 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 25440256 } ], "md5sum": "c024f40917346b6ed6ed3c69a3bbc65e" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 31854592, "records": [ { "name": "model.layers.2.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.2.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 9437184 }, { "name": "model.layers.2.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 26214400 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 28311552 }, { "name": "model.layers.2.self_attn.qkv_proj.q_weight", "shape": [ 3072, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 28315648 }, { "name": "model.layers.2.self_attn.qkv_proj.q_scale", "shape": [ 3072, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 393216, "byteOffset": 31461376 } ], "md5sum": "cad4c069c923c368cdaff2866118e774" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 30679040, "records": [ { "name": "model.layers.2.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 0 }, { "name": "model.layers.2.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 2097152 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 2359296 }, { "name": "model.layers.3.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 2363392 }, { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 10752000 }, { "name": "model.layers.3.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 11800576 }, { "name": "model.layers.3.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 28577792 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 30674944 } ], "md5sum": "729666368216d32a744b74ec61dc6ffa" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 32116736, "records": [ { "name": "model.layers.3.self_attn.qkv_proj.q_weight", "shape": [ 3072, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 0 }, { "name": "model.layers.3.self_attn.qkv_proj.q_scale", "shape": [ 3072, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 393216, "byteOffset": 3145728 }, { "name": "model.layers.3.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 3538944 }, { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 5636096 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 5898240 }, { "name": "model.layers.4.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 5902336 }, { "name": "model.layers.4.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 14290944 }, { "name": "model.layers.4.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 15339520 } ], "md5sum": "312da379d71a840b31a6e9e91cbb3dd3" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "295466658d69efc34a6ae7e7b1369f59" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 25444352, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 0 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 2097152 }, { "name": "model.layers.4.self_attn.qkv_proj.q_weight", "shape": [ 3072, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 2101248 }, { "name": "model.layers.4.self_attn.qkv_proj.q_scale", "shape": [ 3072, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 393216, "byteOffset": 5246976 }, { "name": "model.layers.4.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 5640192 }, { "name": "model.layers.4.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 7737344 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 7999488 }, { "name": "model.layers.5.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 8003584 }, { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 16392192 }, { "name": "model.layers.5.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 17440768 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 19537920 }, { "name": "model.layers.5.self_attn.qkv_proj.q_weight", "shape": [ 3072, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 19542016 }, { "name": "model.layers.5.self_attn.qkv_proj.q_scale", "shape": [ 3072, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 393216, "byteOffset": 22687744 }, { "name": "model.layers.5.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 23080960 }, { "name": "model.layers.5.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 25178112 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 25440256 } ], "md5sum": "512c79b7371adc917942e366252d652d" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 31854592, "records": [ { "name": "model.layers.6.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.6.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.6.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 9437184 }, { "name": "model.layers.6.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 26214400 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 28311552 }, { "name": "model.layers.6.self_attn.qkv_proj.q_weight", "shape": [ 3072, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 28315648 }, { "name": "model.layers.6.self_attn.qkv_proj.q_scale", "shape": [ 3072, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 393216, "byteOffset": 31461376 } ], "md5sum": "a54f030bcc4170a8be9ab8afdd9f6258" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 30679040, "records": [ { "name": "model.layers.6.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 0 }, { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 2097152 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 2359296 }, { "name": "model.layers.7.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 2363392 }, { "name": "model.layers.7.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 10752000 }, { "name": "model.layers.7.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 11800576 }, { "name": "model.layers.7.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 28577792 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 30674944 } ], "md5sum": "d012835ff4c50e448cdbc368e0355852" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 32116736, "records": [ { "name": "model.layers.7.self_attn.qkv_proj.q_weight", "shape": [ 3072, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 0 }, { "name": "model.layers.7.self_attn.qkv_proj.q_scale", "shape": [ 3072, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 393216, "byteOffset": 3145728 }, { "name": "model.layers.7.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 3538944 }, { "name": "model.layers.7.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 5636096 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 5898240 }, { "name": "model.layers.8.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 5902336 }, { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 14290944 }, { "name": "model.layers.8.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 15339520 } ], "md5sum": "a9d6ab1c7c8cafa656e9e50de403c127" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "454bc283931428d2a814d1208f2b0aff" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 25444352, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 0 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 2097152 }, { "name": "model.layers.8.self_attn.qkv_proj.q_weight", "shape": [ 3072, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 2101248 }, { "name": "model.layers.8.self_attn.qkv_proj.q_scale", "shape": [ 3072, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 393216, "byteOffset": 5246976 }, { "name": "model.layers.8.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 5640192 }, { "name": "model.layers.8.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 7737344 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 7999488 }, { "name": "model.layers.9.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 8003584 }, { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 16392192 }, { "name": "model.layers.9.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 17440768 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 19537920 }, { "name": "model.layers.9.self_attn.qkv_proj.q_weight", "shape": [ 3072, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 19542016 }, { "name": "model.layers.9.self_attn.qkv_proj.q_scale", "shape": [ 3072, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 393216, "byteOffset": 22687744 }, { "name": "model.layers.9.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 23080960 }, { "name": "model.layers.9.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 25178112 }, { "name": "model.norm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 25440256 } ], "md5sum": "260bdd770469e8090538f2aaedecfcf9" } ] }