{ "metadata": { "ParamSize": 163, "ParamBytes": 772612096.0, "BitsPerParam": 5.001476571239176 }, "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": "c4b02155a26438cabaf913f2ba7b126f" }, { "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": "c86cb3842a29237cdba1dc373b78b3b7" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 31498240, "records": [ { "name": "model.embed_tokens.q_scale", "shape": [ 128256, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16416768, "byteOffset": 0 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 24809472 }, { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2097152, "byteOffset": 25858048 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 393216, "byteOffset": 31105024 } ], "md5sum": "8b1b78616f0a26e500880d6da113fff7" }, { "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": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 2097152 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 2097152, "byteOffset": 28577792 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 30674944 } ], "md5sum": "fe861c8dea627b8872c506bd32041ceb" }, { "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": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 5636096 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "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": "7e06ec88d3df685c9c584afff753485f" }, { "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": "dfc4b7fd2f1f3d10149f65211ffd4345" }, { "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": "bfloat16", "format": "raw", "nbytes": 2097152, "byteOffset": 0 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 7737344 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 16392192 }, { "name": "model.layers.11.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2097152, "byteOffset": 17440768 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 25178112 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 25440256 } ], "md5sum": "d30c444d80d3393ec27a93fa730d5d9b" }, { "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": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 2097152, "byteOffset": 26214400 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 393216, "byteOffset": 31461376 } ], "md5sum": "f8ebdf1fdbfd306d29787abdf17d973a" }, { "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": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 2097152 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 2097152, "byteOffset": 28577792 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 30674944 } ], "md5sum": "12d4141ced1db03f23667dba4079b4e9" }, { "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": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 5636096 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "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": "3a5b70f90e93fa1ec77af6f2ebac7a6e" }, { "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": "9cf02ddf37dd87c7deb832c9faeb1a88" }, { "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": "bfloat16", "format": "raw", "nbytes": 2097152, "byteOffset": 0 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 7737344 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 16392192 }, { "name": "model.layers.15.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2097152, "byteOffset": 17440768 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 25178112 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 25440256 } ], "md5sum": "cafc16f22e34efdefda314bfb5b1904a" }, { "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": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 2097152, "byteOffset": 26214400 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 393216, "byteOffset": 31461376 } ], "md5sum": "7be48f4a52836f213bd4650e8bada27e" }, { "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": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 2097152 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 2097152, "byteOffset": 28577792 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 30674944 } ], "md5sum": "9ec9f43021fca5430fe7d90a61bbe081" }, { "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": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 5636096 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "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": "f8f38b21fe0b6ce9cc4a8195635b073b" }, { "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": "6b3ca5be729c96d884611497465cf9cf" }, { "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": "bfloat16", "format": "raw", "nbytes": 2097152, "byteOffset": 0 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 7737344 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 16392192 }, { "name": "model.layers.5.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2097152, "byteOffset": 17440768 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 25178112 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 25440256 } ], "md5sum": "7bfbc2f1a22c93cc6fe23ff187674b45" }, { "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": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 2097152, "byteOffset": 26214400 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 393216, "byteOffset": 31461376 } ], "md5sum": "03dc788d306ff9cd93aceaed94dc72b3" }, { "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": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 2097152 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 2097152, "byteOffset": 28577792 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 30674944 } ], "md5sum": "505909b9ed26c82c7ec5b64bd3cea8f8" }, { "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": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 5636096 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "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": "15660046fbafedf9f570110ff3b3d6c4" }, { "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": "5a2bd5e0a68d768fd4afcbc382834154" }, { "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": "bfloat16", "format": "raw", "nbytes": 2097152, "byteOffset": 0 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 7737344 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 16392192 }, { "name": "model.layers.9.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2097152, "byteOffset": 17440768 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 25178112 }, { "name": "model.norm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 25440256 } ], "md5sum": "5317654acd9ce53606003c0da799efb0" } ] }