|
{ |
|
"metadata": { |
|
"ParamSize": 325, |
|
"ParamBytes": 3734413312.0, |
|
"BitsPerParam": 3.0339068428056057 |
|
}, |
|
"records": [ |
|
{ |
|
"dataPath": "params_shard_0.bin", |
|
"format": "raw-shard", |
|
"nbytes": 65536000, |
|
"records": [ |
|
{ |
|
"name": "lm_head.q_weight", |
|
"shape": [ |
|
32000, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 65536000, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "6268dc604af6e74676a1a41dabc690e4" |
|
}, |
|
{ |
|
"dataPath": "params_shard_1.bin", |
|
"format": "raw-shard", |
|
"nbytes": 58720256, |
|
"records": [ |
|
{ |
|
"name": "model.layers.21.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
28672, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 58720256, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "7ae97738f1339f92595390660bc84504" |
|
}, |
|
{ |
|
"dataPath": "params_shard_2.bin", |
|
"format": "raw-shard", |
|
"nbytes": 33267712, |
|
"records": [ |
|
{ |
|
"name": "lm_head.q_scale", |
|
"shape": [ |
|
32000, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2048000, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.21.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 2048000 |
|
}, |
|
{ |
|
"name": "model.layers.21.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
28672, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1835008, |
|
"byteOffset": 2056192 |
|
}, |
|
{ |
|
"name": "model.layers.21.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 3891200 |
|
}, |
|
{ |
|
"name": "model.layers.22.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 3899392 |
|
}, |
|
{ |
|
"name": "model.layers.22.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1792 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 29360128, |
|
"byteOffset": 3907584 |
|
} |
|
], |
|
"md5sum": "46e8d9203fe6fe0fc47bdb1f88e6b478" |
|
}, |
|
{ |
|
"dataPath": "params_shard_3.bin", |
|
"format": "raw-shard", |
|
"nbytes": 58720256, |
|
"records": [ |
|
{ |
|
"name": "model.layers.22.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
28672, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 58720256, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "10ce342feeac3f767a9252b4780c054a" |
|
}, |
|
{ |
|
"dataPath": "params_shard_4.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29360128, |
|
"records": [ |
|
{ |
|
"name": "model.layers.23.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1792 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 29360128, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "83fb0313953467b663220fe69521218d" |
|
}, |
|
{ |
|
"dataPath": "params_shard_5.bin", |
|
"format": "raw-shard", |
|
"nbytes": 58720256, |
|
"records": [ |
|
{ |
|
"name": "model.layers.23.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
28672, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 58720256, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "be96c7b6215f8a21867e9f9f72c0a55f" |
|
}, |
|
{ |
|
"dataPath": "params_shard_6.bin", |
|
"format": "raw-shard", |
|
"nbytes": 27156480, |
|
"records": [ |
|
{ |
|
"name": "model.layers.22.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
112 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 917504, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.22.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
28672, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1835008, |
|
"byteOffset": 917504 |
|
}, |
|
{ |
|
"name": "model.layers.22.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 2752512 |
|
}, |
|
{ |
|
"name": "model.layers.22.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
6144, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 12582912, |
|
"byteOffset": 2760704 |
|
}, |
|
{ |
|
"name": "model.layers.22.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
6144, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 393216, |
|
"byteOffset": 15343616 |
|
}, |
|
{ |
|
"name": "model.layers.22.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 15736832 |
|
}, |
|
{ |
|
"name": "model.layers.22.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 262144, |
|
"byteOffset": 24125440 |
|
}, |
|
{ |
|
"name": "model.layers.23.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 24387584 |
|
}, |
|
{ |
|
"name": "model.layers.23.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
112 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 917504, |
|
"byteOffset": 24395776 |
|
}, |
|
{ |
|
"name": "model.layers.23.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
28672, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1835008, |
|
"byteOffset": 25313280 |
|
}, |
|
{ |
|
"name": "model.layers.23.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 27148288 |
|
} |
|
], |
|
"md5sum": "da4f10934373e7d6c1e3e4a17c803e32" |
|
}, |
|
{ |
|
"dataPath": "params_shard_7.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29360128, |
|
"records": [ |
|
{ |
|
"name": "model.layers.24.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1792 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 29360128, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "fcc7648b831d441219e7ddbfb61ef237" |
|
}, |
|
{ |
|
"dataPath": "params_shard_8.bin", |
|
"format": "raw-shard", |
|
"nbytes": 58720256, |
|
"records": [ |
|
{ |
|
"name": "model.layers.24.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
28672, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 58720256, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "6a33faf795aced4ff5d70c40ca8c4ace" |
|
}, |
|
{ |
|
"dataPath": "params_shard_9.bin", |
|
"format": "raw-shard", |
|
"nbytes": 24395776, |
|
"records": [ |
|
{ |
|
"name": "model.layers.23.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
6144, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 12582912, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.23.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
6144, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 393216, |
|
"byteOffset": 12582912 |
|
}, |
|
{ |
|
"name": "model.layers.23.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 12976128 |
|
}, |
|
{ |
|
"name": "model.layers.23.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 262144, |
|
"byteOffset": 21364736 |
|
}, |
|
{ |
|
"name": "model.layers.24.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 21626880 |
|
}, |
|
{ |
|
"name": "model.layers.24.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
112 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 917504, |
|
"byteOffset": 21635072 |
|
}, |
|
{ |
|
"name": "model.layers.24.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
28672, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1835008, |
|
"byteOffset": 22552576 |
|
}, |
|
{ |
|
"name": "model.layers.24.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 24387584 |
|
} |
|
], |
|
"md5sum": "8e9277ed3b8fa26231fe227594d6af86" |
|
}, |
|
{ |
|
"dataPath": "params_shard_10.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29360128, |
|
"records": [ |
|
{ |
|
"name": "model.layers.25.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1792 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 29360128, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "751baedcba1efc26d4800efcc93ef74a" |
|
}, |
|
{ |
|
"dataPath": "params_shard_11.bin", |
|
"format": "raw-shard", |
|
"nbytes": 58720256, |
|
"records": [ |
|
{ |
|
"name": "model.layers.25.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
28672, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 58720256, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "5b4d0a194ed1e628120a7351d19ab8f0" |
|
}, |
|
{ |
|
"dataPath": "params_shard_12.bin", |
|
"format": "raw-shard", |
|
"nbytes": 24395776, |
|
"records": [ |
|
{ |
|
"name": "model.layers.24.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
6144, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 12582912, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.24.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
6144, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 393216, |
|
"byteOffset": 12582912 |
|
}, |
|
{ |
|
"name": "model.layers.24.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 12976128 |
|
}, |
|
{ |
|
"name": "model.layers.24.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 262144, |
|
"byteOffset": 21364736 |
|
}, |
|
{ |
|
"name": "model.layers.25.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 21626880 |
|
}, |
|
{ |
|
"name": "model.layers.25.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
112 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 917504, |
|
"byteOffset": 21635072 |
|
}, |
|
{ |
|
"name": "model.layers.25.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
28672, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1835008, |
|
"byteOffset": 22552576 |
|
}, |
|
{ |
|
"name": "model.layers.25.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 24387584 |
|
} |
|
], |
|
"md5sum": "5cecb20bb87f5fe9f7dc6564df161a0e" |
|
}, |
|
{ |
|
"dataPath": "params_shard_13.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29360128, |
|
"records": [ |
|
{ |
|
"name": "model.layers.26.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1792 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 29360128, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "b594acbccb04237dc30a52bfff854a0e" |
|
}, |
|
{ |
|
"dataPath": "params_shard_14.bin", |
|
"format": "raw-shard", |
|
"nbytes": 58720256, |
|
"records": [ |
|
{ |
|
"name": "model.layers.26.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
28672, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 58720256, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "99d4ef37105731ddc499e1025d37d7ed" |
|
}, |
|
{ |
|
"dataPath": "params_shard_15.bin", |
|
"format": "raw-shard", |
|
"nbytes": 24395776, |
|
"records": [ |
|
{ |
|
"name": "model.layers.25.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
6144, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 12582912, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.25.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
6144, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 393216, |
|
"byteOffset": 12582912 |
|
}, |
|
{ |
|
"name": "model.layers.25.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 12976128 |
|
}, |
|
{ |
|
"name": "model.layers.25.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 262144, |
|
"byteOffset": 21364736 |
|
}, |
|
{ |
|
"name": "model.layers.26.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 21626880 |
|
}, |
|
{ |
|
"name": "model.layers.26.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
112 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 917504, |
|
"byteOffset": 21635072 |
|
}, |
|
{ |
|
"name": "model.layers.26.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
28672, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1835008, |
|
"byteOffset": 22552576 |
|
}, |
|
{ |
|
"name": "model.layers.26.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 24387584 |
|
} |
|
], |
|
"md5sum": "30f884efd7df52486d0b89cddd645672" |
|
}, |
|
{ |
|
"dataPath": "params_shard_16.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29360128, |
|
"records": [ |
|
{ |
|
"name": "model.layers.27.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1792 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 29360128, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "6dcf3c2a336235d93ee0472293f5567e" |
|
}, |
|
{ |
|
"dataPath": "params_shard_17.bin", |
|
"format": "raw-shard", |
|
"nbytes": 58720256, |
|
"records": [ |
|
{ |
|
"name": "model.layers.27.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
28672, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 58720256, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "37bf05b36b36f929e0e56fe29d42e947" |
|
}, |
|
{ |
|
"dataPath": "params_shard_18.bin", |
|
"format": "raw-shard", |
|
"nbytes": 24395776, |
|
"records": [ |
|
{ |
|
"name": "model.layers.26.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
6144, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 12582912, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.26.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
6144, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 393216, |
|
"byteOffset": 12582912 |
|
}, |
|
{ |
|
"name": "model.layers.26.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 12976128 |
|
}, |
|
{ |
|
"name": "model.layers.26.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 262144, |
|
"byteOffset": 21364736 |
|
}, |
|
{ |
|
"name": "model.layers.27.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 21626880 |
|
}, |
|
{ |
|
"name": "model.layers.27.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
112 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 917504, |
|
"byteOffset": 21635072 |
|
}, |
|
{ |
|
"name": "model.layers.27.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
28672, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1835008, |
|
"byteOffset": 22552576 |
|
}, |
|
{ |
|
"name": "model.layers.27.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 24387584 |
|
} |
|
], |
|
"md5sum": "e92250ed4f6968d0ea6e0be6ea81810a" |
|
}, |
|
{ |
|
"dataPath": "params_shard_19.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29360128, |
|
"records": [ |
|
{ |
|
"name": "model.layers.28.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1792 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 29360128, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "d8d8303cc4cb4ead75cee189dee05fef" |
|
}, |
|
{ |
|
"dataPath": "params_shard_20.bin", |
|
"format": "raw-shard", |
|
"nbytes": 58720256, |
|
"records": [ |
|
{ |
|
"name": "model.layers.28.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
28672, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 58720256, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "e662456d33a8baecda129da1070231ba" |
|
}, |
|
{ |
|
"dataPath": "params_shard_21.bin", |
|
"format": "raw-shard", |
|
"nbytes": 24395776, |
|
"records": [ |
|
{ |
|
"name": "model.layers.27.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
6144, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 12582912, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.27.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
6144, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 393216, |
|
"byteOffset": 12582912 |
|
}, |
|
{ |
|
"name": "model.layers.27.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 12976128 |
|
}, |
|
{ |
|
"name": "model.layers.27.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 262144, |
|
"byteOffset": 21364736 |
|
}, |
|
{ |
|
"name": "model.layers.28.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 21626880 |
|
}, |
|
{ |
|
"name": "model.layers.28.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
112 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 917504, |
|
"byteOffset": 21635072 |
|
}, |
|
{ |
|
"name": "model.layers.28.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
28672, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1835008, |
|
"byteOffset": 22552576 |
|
}, |
|
{ |
|
"name": "model.layers.28.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 24387584 |
|
} |
|
], |
|
"md5sum": "cda815ab720fe4da3fd47f4577f86b7a" |
|
}, |
|
{ |
|
"dataPath": "params_shard_22.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29360128, |
|
"records": [ |
|
{ |
|
"name": "model.layers.29.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1792 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 29360128, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "0c737e68b67f42f113f0af3baabe48d1" |
|
}, |
|
{ |
|
"dataPath": "params_shard_23.bin", |
|
"format": "raw-shard", |
|
"nbytes": 58720256, |
|
"records": [ |
|
{ |
|
"name": "model.layers.29.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
28672, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 58720256, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "56f3ec4920adcb80f266cb7ee8e0d1fe" |
|
}, |
|
{ |
|
"dataPath": "params_shard_24.bin", |
|
"format": "raw-shard", |
|
"nbytes": 24395776, |
|
"records": [ |
|
{ |
|
"name": "model.layers.28.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
6144, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 12582912, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.28.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
6144, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 393216, |
|
"byteOffset": 12582912 |
|
}, |
|
{ |
|
"name": "model.layers.28.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 12976128 |
|
}, |
|
{ |
|
"name": "model.layers.28.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 262144, |
|
"byteOffset": 21364736 |
|
}, |
|
{ |
|
"name": "model.layers.29.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 21626880 |
|
}, |
|
{ |
|
"name": "model.layers.29.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
112 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 917504, |
|
"byteOffset": 21635072 |
|
}, |
|
{ |
|
"name": "model.layers.29.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
28672, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1835008, |
|
"byteOffset": 22552576 |
|
}, |
|
{ |
|
"name": "model.layers.29.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 24387584 |
|
} |
|
], |
|
"md5sum": "d7413ec2aa20f2f7bb13365cfac3a559" |
|
}, |
|
{ |
|
"dataPath": "params_shard_25.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29360128, |
|
"records": [ |
|
{ |
|
"name": "model.layers.30.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1792 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 29360128, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "24de20dc3982284d71a33eb79268bc88" |
|
}, |
|
{ |
|
"dataPath": "params_shard_26.bin", |
|
"format": "raw-shard", |
|
"nbytes": 58720256, |
|
"records": [ |
|
{ |
|
"name": "model.layers.30.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
28672, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 58720256, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "c299c19665f2ea30a547d8d56a1a0328" |
|
}, |
|
{ |
|
"dataPath": "params_shard_27.bin", |
|
"format": "raw-shard", |
|
"nbytes": 24395776, |
|
"records": [ |
|
{ |
|
"name": "model.layers.29.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
6144, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 12582912, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.29.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
6144, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 393216, |
|
"byteOffset": 12582912 |
|
}, |
|
{ |
|
"name": "model.layers.29.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 12976128 |
|
}, |
|
{ |
|
"name": "model.layers.29.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 262144, |
|
"byteOffset": 21364736 |
|
}, |
|
{ |
|
"name": "model.layers.30.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 21626880 |
|
}, |
|
{ |
|
"name": "model.layers.30.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
112 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 917504, |
|
"byteOffset": 21635072 |
|
}, |
|
{ |
|
"name": "model.layers.30.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
28672, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1835008, |
|
"byteOffset": 22552576 |
|
}, |
|
{ |
|
"name": "model.layers.30.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 24387584 |
|
} |
|
], |
|
"md5sum": "003759930036b2d90011da8e0028f74f" |
|
}, |
|
{ |
|
"dataPath": "params_shard_28.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29360128, |
|
"records": [ |
|
{ |
|
"name": "model.layers.31.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1792 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 29360128, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "6e8214dd641bf0f277400e0d4ff9cde7" |
|
}, |
|
{ |
|
"dataPath": "params_shard_29.bin", |
|
"format": "raw-shard", |
|
"nbytes": 58720256, |
|
"records": [ |
|
{ |
|
"name": "model.layers.31.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
28672, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 58720256, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "b051c6f4544613a1d8faa3828856cdb6" |
|
}, |
|
{ |
|
"dataPath": "params_shard_30.bin", |
|
"format": "raw-shard", |
|
"nbytes": 24395776, |
|
"records": [ |
|
{ |
|
"name": "model.layers.30.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
6144, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 12582912, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.30.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
6144, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 393216, |
|
"byteOffset": 12582912 |
|
}, |
|
{ |
|
"name": "model.layers.30.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 12976128 |
|
}, |
|
{ |
|
"name": "model.layers.30.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 262144, |
|
"byteOffset": 21364736 |
|
}, |
|
{ |
|
"name": "model.layers.31.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 21626880 |
|
}, |
|
{ |
|
"name": "model.layers.31.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
112 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 917504, |
|
"byteOffset": 21635072 |
|
}, |
|
{ |
|
"name": "model.layers.31.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
28672, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1835008, |
|
"byteOffset": 22552576 |
|
}, |
|
{ |
|
"name": "model.layers.31.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 24387584 |
|
} |
|
], |
|
"md5sum": "0e89f967d16e44db2c25996c11536ca2" |
|
}, |
|
{ |
|
"dataPath": "params_shard_31.bin", |
|
"format": "raw-shard", |
|
"nbytes": 65536000, |
|
"records": [ |
|
{ |
|
"name": "model.embed_tokens.q_weight", |
|
"shape": [ |
|
32000, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 65536000, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "6d8a3d0dacd54e347a5c19a25e133dd6" |
|
}, |
|
{ |
|
"dataPath": "params_shard_32.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29360128, |
|
"records": [ |
|
{ |
|
"name": "model.layers.0.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1792 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 29360128, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "be92ed72b7b03cc732640fbfab4645af" |
|
}, |
|
{ |
|
"dataPath": "params_shard_33.bin", |
|
"format": "raw-shard", |
|
"nbytes": 58720256, |
|
"records": [ |
|
{ |
|
"name": "model.layers.0.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
28672, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 58720256, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "fca26c713d088f19998f622764f84af4" |
|
}, |
|
{ |
|
"dataPath": "params_shard_34.bin", |
|
"format": "raw-shard", |
|
"nbytes": 26451968, |
|
"records": [ |
|
{ |
|
"name": "model.layers.31.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
6144, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 12582912, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.31.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
6144, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 393216, |
|
"byteOffset": 12582912 |
|
}, |
|
{ |
|
"name": "model.layers.31.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 12976128 |
|
}, |
|
{ |
|
"name": "model.layers.31.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 262144, |
|
"byteOffset": 21364736 |
|
}, |
|
{ |
|
"name": "model.norm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 21626880 |
|
}, |
|
{ |
|
"name": "model.embed_tokens.q_scale", |
|
"shape": [ |
|
32000, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2048000, |
|
"byteOffset": 21635072 |
|
}, |
|
{ |
|
"name": "model.layers.0.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 23683072 |
|
}, |
|
{ |
|
"name": "model.layers.0.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
112 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 917504, |
|
"byteOffset": 23691264 |
|
}, |
|
{ |
|
"name": "model.layers.0.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
28672, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1835008, |
|
"byteOffset": 24608768 |
|
}, |
|
{ |
|
"name": "model.layers.0.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 26443776 |
|
} |
|
], |
|
"md5sum": "6ea6798a28ab3854c0244be3244eee2a" |
|
}, |
|
{ |
|
"dataPath": "params_shard_35.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29360128, |
|
"records": [ |
|
{ |
|
"name": "model.layers.1.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1792 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 29360128, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "8b8d492a5e99b5a1bc110fc3649aa84d" |
|
}, |
|
{ |
|
"dataPath": "params_shard_36.bin", |
|
"format": "raw-shard", |
|
"nbytes": 58720256, |
|
"records": [ |
|
{ |
|
"name": "model.layers.1.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
28672, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 58720256, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "6132bddf9c045afbcfa3aea44a9a463f" |
|
}, |
|
{ |
|
"dataPath": "params_shard_37.bin", |
|
"format": "raw-shard", |
|
"nbytes": 24395776, |
|
"records": [ |
|
{ |
|
"name": "model.layers.0.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
6144, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 12582912, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.0.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
6144, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 393216, |
|
"byteOffset": 12582912 |
|
}, |
|
{ |
|
"name": "model.layers.0.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 12976128 |
|
}, |
|
{ |
|
"name": "model.layers.0.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 262144, |
|
"byteOffset": 21364736 |
|
}, |
|
{ |
|
"name": "model.layers.1.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 21626880 |
|
}, |
|
{ |
|
"name": "model.layers.1.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
112 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 917504, |
|
"byteOffset": 21635072 |
|
}, |
|
{ |
|
"name": "model.layers.1.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
28672, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1835008, |
|
"byteOffset": 22552576 |
|
}, |
|
{ |
|
"name": "model.layers.1.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 24387584 |
|
} |
|
], |
|
"md5sum": "c817fc34548303af378b0df9da564f51" |
|
}, |
|
{ |
|
"dataPath": "params_shard_38.bin", |
|
"format": "raw-shard", |
|
"nbytes": 58720256, |
|
"records": [ |
|
{ |
|
"name": "model.layers.10.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
28672, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 58720256, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "e440ca29d6d1988c5e41ea86de3904c1" |
|
}, |
|
{ |
|
"dataPath": "params_shard_39.bin", |
|
"format": "raw-shard", |
|
"nbytes": 23461888, |
|
"records": [ |
|
{ |
|
"name": "model.layers.1.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
6144, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 12582912, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.1.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
6144, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 393216, |
|
"byteOffset": 12582912 |
|
}, |
|
{ |
|
"name": "model.layers.1.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 12976128 |
|
}, |
|
{ |
|
"name": "model.layers.1.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 262144, |
|
"byteOffset": 21364736 |
|
}, |
|
{ |
|
"name": "model.layers.10.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
28672, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1835008, |
|
"byteOffset": 21626880 |
|
} |
|
], |
|
"md5sum": "686eff344c7be97cf1e27605d1c0a49a" |
|
}, |
|
{ |
|
"dataPath": "params_shard_40.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29360128, |
|
"records": [ |
|
{ |
|
"name": "model.layers.2.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1792 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 29360128, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "141c634ca83aa6f5ce59d31359b614a3" |
|
}, |
|
{ |
|
"dataPath": "params_shard_41.bin", |
|
"format": "raw-shard", |
|
"nbytes": 58720256, |
|
"records": [ |
|
{ |
|
"name": "model.layers.2.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
28672, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 58720256, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "6c9d6dc6afce6cdf53900a7610a550e8" |
|
}, |
|
{ |
|
"dataPath": "params_shard_42.bin", |
|
"format": "raw-shard", |
|
"nbytes": 24395776, |
|
"records": [ |
|
{ |
|
"name": "model.layers.10.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
6144, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 12582912, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.10.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
6144, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 393216, |
|
"byteOffset": 12582912 |
|
}, |
|
{ |
|
"name": "model.layers.10.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 12976128 |
|
}, |
|
{ |
|
"name": "model.layers.10.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 262144, |
|
"byteOffset": 21364736 |
|
}, |
|
{ |
|
"name": "model.layers.2.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 21626880 |
|
}, |
|
{ |
|
"name": "model.layers.2.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
112 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 917504, |
|
"byteOffset": 21635072 |
|
}, |
|
{ |
|
"name": "model.layers.2.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
28672, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1835008, |
|
"byteOffset": 22552576 |
|
}, |
|
{ |
|
"name": "model.layers.2.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 24387584 |
|
} |
|
], |
|
"md5sum": "fb04ad7a13e3f494ee3c9776e7ea6ee4" |
|
}, |
|
{ |
|
"dataPath": "params_shard_43.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29360128, |
|
"records": [ |
|
{ |
|
"name": "model.layers.3.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1792 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 29360128, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "ee42ad97aae0a2488c799cc8f6eb6e10" |
|
}, |
|
{ |
|
"dataPath": "params_shard_44.bin", |
|
"format": "raw-shard", |
|
"nbytes": 58720256, |
|
"records": [ |
|
{ |
|
"name": "model.layers.3.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
28672, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 58720256, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "63c5b5e695462179d7c713aa6c7f2c83" |
|
}, |
|
{ |
|
"dataPath": "params_shard_45.bin", |
|
"format": "raw-shard", |
|
"nbytes": 24395776, |
|
"records": [ |
|
{ |
|
"name": "model.layers.2.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
6144, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 12582912, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.2.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
6144, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 393216, |
|
"byteOffset": 12582912 |
|
}, |
|
{ |
|
"name": "model.layers.2.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 12976128 |
|
}, |
|
{ |
|
"name": "model.layers.2.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 262144, |
|
"byteOffset": 21364736 |
|
}, |
|
{ |
|
"name": "model.layers.3.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 21626880 |
|
}, |
|
{ |
|
"name": "model.layers.3.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
112 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 917504, |
|
"byteOffset": 21635072 |
|
}, |
|
{ |
|
"name": "model.layers.3.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
28672, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1835008, |
|
"byteOffset": 22552576 |
|
}, |
|
{ |
|
"name": "model.layers.3.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 24387584 |
|
} |
|
], |
|
"md5sum": "545db3dbc0918b66acc18619e6af8f1e" |
|
}, |
|
{ |
|
"dataPath": "params_shard_46.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29360128, |
|
"records": [ |
|
{ |
|
"name": "model.layers.4.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1792 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 29360128, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "06bb991f5d6d081af33f4146dc61f2df" |
|
}, |
|
{ |
|
"dataPath": "params_shard_47.bin", |
|
"format": "raw-shard", |
|
"nbytes": 58720256, |
|
"records": [ |
|
{ |
|
"name": "model.layers.4.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
28672, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 58720256, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "49f2059ef185adebab3fbebc27f86bc1" |
|
}, |
|
{ |
|
"dataPath": "params_shard_48.bin", |
|
"format": "raw-shard", |
|
"nbytes": 24395776, |
|
"records": [ |
|
{ |
|
"name": "model.layers.3.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
6144, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 12582912, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.3.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
6144, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 393216, |
|
"byteOffset": 12582912 |
|
}, |
|
{ |
|
"name": "model.layers.3.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 12976128 |
|
}, |
|
{ |
|
"name": "model.layers.3.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 262144, |
|
"byteOffset": 21364736 |
|
}, |
|
{ |
|
"name": "model.layers.4.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 21626880 |
|
}, |
|
{ |
|
"name": "model.layers.4.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
112 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 917504, |
|
"byteOffset": 21635072 |
|
}, |
|
{ |
|
"name": "model.layers.4.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
28672, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1835008, |
|
"byteOffset": 22552576 |
|
}, |
|
{ |
|
"name": "model.layers.4.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 24387584 |
|
} |
|
], |
|
"md5sum": "cb9da8de7cb77ec0bdaebb94a2a264e7" |
|
}, |
|
{ |
|
"dataPath": "params_shard_49.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29360128, |
|
"records": [ |
|
{ |
|
"name": "model.layers.5.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1792 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 29360128, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "f27839f986de72a3c77d0e3db9992810" |
|
}, |
|
{ |
|
"dataPath": "params_shard_50.bin", |
|
"format": "raw-shard", |
|
"nbytes": 58720256, |
|
"records": [ |
|
{ |
|
"name": "model.layers.5.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
28672, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 58720256, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "646aded590da7b45af2223c1e43ca4a7" |
|
}, |
|
{ |
|
"dataPath": "params_shard_51.bin", |
|
"format": "raw-shard", |
|
"nbytes": 24395776, |
|
"records": [ |
|
{ |
|
"name": "model.layers.4.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
6144, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 12582912, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.4.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
6144, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 393216, |
|
"byteOffset": 12582912 |
|
}, |
|
{ |
|
"name": "model.layers.4.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 12976128 |
|
}, |
|
{ |
|
"name": "model.layers.4.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 262144, |
|
"byteOffset": 21364736 |
|
}, |
|
{ |
|
"name": "model.layers.5.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 21626880 |
|
}, |
|
{ |
|
"name": "model.layers.5.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
112 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 917504, |
|
"byteOffset": 21635072 |
|
}, |
|
{ |
|
"name": "model.layers.5.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
28672, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1835008, |
|
"byteOffset": 22552576 |
|
}, |
|
{ |
|
"name": "model.layers.5.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 24387584 |
|
} |
|
], |
|
"md5sum": "4beabf0b41aafa4233fc0d389824911d" |
|
}, |
|
{ |
|
"dataPath": "params_shard_52.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29360128, |
|
"records": [ |
|
{ |
|
"name": "model.layers.6.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1792 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 29360128, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "d9fae465b632d1e5c40e728fe5a6c58d" |
|
}, |
|
{ |
|
"dataPath": "params_shard_53.bin", |
|
"format": "raw-shard", |
|
"nbytes": 58720256, |
|
"records": [ |
|
{ |
|
"name": "model.layers.6.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
28672, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 58720256, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "f1e70f00556481fd7ebcb982a96733ad" |
|
}, |
|
{ |
|
"dataPath": "params_shard_54.bin", |
|
"format": "raw-shard", |
|
"nbytes": 24395776, |
|
"records": [ |
|
{ |
|
"name": "model.layers.5.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
6144, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 12582912, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.5.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
6144, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 393216, |
|
"byteOffset": 12582912 |
|
}, |
|
{ |
|
"name": "model.layers.5.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 12976128 |
|
}, |
|
{ |
|
"name": "model.layers.5.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 262144, |
|
"byteOffset": 21364736 |
|
}, |
|
{ |
|
"name": "model.layers.6.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 21626880 |
|
}, |
|
{ |
|
"name": "model.layers.6.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
112 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 917504, |
|
"byteOffset": 21635072 |
|
}, |
|
{ |
|
"name": "model.layers.6.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
28672, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1835008, |
|
"byteOffset": 22552576 |
|
}, |
|
{ |
|
"name": "model.layers.6.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 24387584 |
|
} |
|
], |
|
"md5sum": "ad577372be6aadd2c66574870c34574a" |
|
}, |
|
{ |
|
"dataPath": "params_shard_55.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29360128, |
|
"records": [ |
|
{ |
|
"name": "model.layers.7.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1792 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 29360128, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "462fe5f7a95de2baa34595658225fb53" |
|
}, |
|
{ |
|
"dataPath": "params_shard_56.bin", |
|
"format": "raw-shard", |
|
"nbytes": 58720256, |
|
"records": [ |
|
{ |
|
"name": "model.layers.7.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
28672, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 58720256, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "f4db8bbf97609fdf861cc9217ab805a2" |
|
}, |
|
{ |
|
"dataPath": "params_shard_57.bin", |
|
"format": "raw-shard", |
|
"nbytes": 24395776, |
|
"records": [ |
|
{ |
|
"name": "model.layers.6.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
6144, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 12582912, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.6.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
6144, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 393216, |
|
"byteOffset": 12582912 |
|
}, |
|
{ |
|
"name": "model.layers.6.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 12976128 |
|
}, |
|
{ |
|
"name": "model.layers.6.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 262144, |
|
"byteOffset": 21364736 |
|
}, |
|
{ |
|
"name": "model.layers.7.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 21626880 |
|
}, |
|
{ |
|
"name": "model.layers.7.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
112 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 917504, |
|
"byteOffset": 21635072 |
|
}, |
|
{ |
|
"name": "model.layers.7.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
28672, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1835008, |
|
"byteOffset": 22552576 |
|
}, |
|
{ |
|
"name": "model.layers.7.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 24387584 |
|
} |
|
], |
|
"md5sum": "548800aed35c4ef7864046b92b1e44e8" |
|
}, |
|
{ |
|
"dataPath": "params_shard_58.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29360128, |
|
"records": [ |
|
{ |
|
"name": "model.layers.8.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1792 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 29360128, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "d403abacda56f5900fc374eb351a1083" |
|
}, |
|
{ |
|
"dataPath": "params_shard_59.bin", |
|
"format": "raw-shard", |
|
"nbytes": 58720256, |
|
"records": [ |
|
{ |
|
"name": "model.layers.8.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
28672, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 58720256, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "74c3d6dfa6cecc1d971b9dc66da6e569" |
|
}, |
|
{ |
|
"dataPath": "params_shard_60.bin", |
|
"format": "raw-shard", |
|
"nbytes": 24395776, |
|
"records": [ |
|
{ |
|
"name": "model.layers.7.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
6144, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 12582912, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.7.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
6144, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 393216, |
|
"byteOffset": 12582912 |
|
}, |
|
{ |
|
"name": "model.layers.7.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 12976128 |
|
}, |
|
{ |
|
"name": "model.layers.7.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 262144, |
|
"byteOffset": 21364736 |
|
}, |
|
{ |
|
"name": "model.layers.8.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 21626880 |
|
}, |
|
{ |
|
"name": "model.layers.8.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
112 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 917504, |
|
"byteOffset": 21635072 |
|
}, |
|
{ |
|
"name": "model.layers.8.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
28672, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1835008, |
|
"byteOffset": 22552576 |
|
}, |
|
{ |
|
"name": "model.layers.8.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 24387584 |
|
} |
|
], |
|
"md5sum": "c07a4370ce61e4df8fe6f089c619a50a" |
|
}, |
|
{ |
|
"dataPath": "params_shard_61.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29360128, |
|
"records": [ |
|
{ |
|
"name": "model.layers.9.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1792 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 29360128, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "51f48858f547d6001c2a101195f73e07" |
|
}, |
|
{ |
|
"dataPath": "params_shard_62.bin", |
|
"format": "raw-shard", |
|
"nbytes": 58720256, |
|
"records": [ |
|
{ |
|
"name": "model.layers.9.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
28672, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 58720256, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "bf14aad99f787528911a2825abb3e6a1" |
|
}, |
|
{ |
|
"dataPath": "params_shard_63.bin", |
|
"format": "raw-shard", |
|
"nbytes": 24395776, |
|
"records": [ |
|
{ |
|
"name": "model.layers.8.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
6144, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 12582912, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.8.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
6144, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 393216, |
|
"byteOffset": 12582912 |
|
}, |
|
{ |
|
"name": "model.layers.8.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 12976128 |
|
}, |
|
{ |
|
"name": "model.layers.8.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 262144, |
|
"byteOffset": 21364736 |
|
}, |
|
{ |
|
"name": "model.layers.9.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 21626880 |
|
}, |
|
{ |
|
"name": "model.layers.9.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
112 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 917504, |
|
"byteOffset": 21635072 |
|
}, |
|
{ |
|
"name": "model.layers.9.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
28672, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1835008, |
|
"byteOffset": 22552576 |
|
}, |
|
{ |
|
"name": "model.layers.9.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 24387584 |
|
} |
|
], |
|
"md5sum": "ebb8876363bc9356f524688691da1d5d" |
|
}, |
|
{ |
|
"dataPath": "params_shard_64.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29360128, |
|
"records": [ |
|
{ |
|
"name": "model.layers.10.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1792 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 29360128, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "ec2137397257426774b07a14b436d51e" |
|
}, |
|
{ |
|
"dataPath": "params_shard_65.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29360128, |
|
"records": [ |
|
{ |
|
"name": "model.layers.11.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1792 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 29360128, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "0b8f07575ca363e6be50525645048b56" |
|
}, |
|
{ |
|
"dataPath": "params_shard_66.bin", |
|
"format": "raw-shard", |
|
"nbytes": 58720256, |
|
"records": [ |
|
{ |
|
"name": "model.layers.11.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
28672, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 58720256, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "bb36ec5ecf28a80d08a3e3785911ea9b" |
|
}, |
|
{ |
|
"dataPath": "params_shard_67.bin", |
|
"format": "raw-shard", |
|
"nbytes": 25329664, |
|
"records": [ |
|
{ |
|
"name": "model.layers.9.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
6144, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 12582912, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.9.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
6144, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 393216, |
|
"byteOffset": 12582912 |
|
}, |
|
{ |
|
"name": "model.layers.9.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 12976128 |
|
}, |
|
{ |
|
"name": "model.layers.9.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 262144, |
|
"byteOffset": 21364736 |
|
}, |
|
{ |
|
"name": "model.layers.10.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 21626880 |
|
}, |
|
{ |
|
"name": "model.layers.10.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
112 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 917504, |
|
"byteOffset": 21635072 |
|
}, |
|
{ |
|
"name": "model.layers.10.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 22552576 |
|
}, |
|
{ |
|
"name": "model.layers.11.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 22560768 |
|
}, |
|
{ |
|
"name": "model.layers.11.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
112 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 917504, |
|
"byteOffset": 22568960 |
|
}, |
|
{ |
|
"name": "model.layers.11.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
28672, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1835008, |
|
"byteOffset": 23486464 |
|
}, |
|
{ |
|
"name": "model.layers.11.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 25321472 |
|
} |
|
], |
|
"md5sum": "15e6b7b74bd788cf7eaf0cac686171c3" |
|
}, |
|
{ |
|
"dataPath": "params_shard_68.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29360128, |
|
"records": [ |
|
{ |
|
"name": "model.layers.12.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1792 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 29360128, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "bb8e21788a8f68648a5449b6a4c4675c" |
|
}, |
|
{ |
|
"dataPath": "params_shard_69.bin", |
|
"format": "raw-shard", |
|
"nbytes": 58720256, |
|
"records": [ |
|
{ |
|
"name": "model.layers.12.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
28672, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 58720256, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "e61586168a2e2b1b6e6dd36dc6a815f5" |
|
}, |
|
{ |
|
"dataPath": "params_shard_70.bin", |
|
"format": "raw-shard", |
|
"nbytes": 24395776, |
|
"records": [ |
|
{ |
|
"name": "model.layers.11.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
6144, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 12582912, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.11.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
6144, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 393216, |
|
"byteOffset": 12582912 |
|
}, |
|
{ |
|
"name": "model.layers.11.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 12976128 |
|
}, |
|
{ |
|
"name": "model.layers.11.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 262144, |
|
"byteOffset": 21364736 |
|
}, |
|
{ |
|
"name": "model.layers.12.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 21626880 |
|
}, |
|
{ |
|
"name": "model.layers.12.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
112 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 917504, |
|
"byteOffset": 21635072 |
|
}, |
|
{ |
|
"name": "model.layers.12.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
28672, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1835008, |
|
"byteOffset": 22552576 |
|
}, |
|
{ |
|
"name": "model.layers.12.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 24387584 |
|
} |
|
], |
|
"md5sum": "40592627a85996a7014dc04d067ec5f7" |
|
}, |
|
{ |
|
"dataPath": "params_shard_71.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29360128, |
|
"records": [ |
|
{ |
|
"name": "model.layers.13.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1792 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 29360128, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "c1f3f3dea2118aaf60ded2dd81f6aec2" |
|
}, |
|
{ |
|
"dataPath": "params_shard_72.bin", |
|
"format": "raw-shard", |
|
"nbytes": 58720256, |
|
"records": [ |
|
{ |
|
"name": "model.layers.13.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
28672, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 58720256, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "4ece41c47f2c36c3a1d27e4e78332fac" |
|
}, |
|
{ |
|
"dataPath": "params_shard_73.bin", |
|
"format": "raw-shard", |
|
"nbytes": 24395776, |
|
"records": [ |
|
{ |
|
"name": "model.layers.12.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
6144, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 12582912, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.12.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
6144, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 393216, |
|
"byteOffset": 12582912 |
|
}, |
|
{ |
|
"name": "model.layers.12.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 12976128 |
|
}, |
|
{ |
|
"name": "model.layers.12.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 262144, |
|
"byteOffset": 21364736 |
|
}, |
|
{ |
|
"name": "model.layers.13.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 21626880 |
|
}, |
|
{ |
|
"name": "model.layers.13.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
112 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 917504, |
|
"byteOffset": 21635072 |
|
}, |
|
{ |
|
"name": "model.layers.13.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
28672, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1835008, |
|
"byteOffset": 22552576 |
|
}, |
|
{ |
|
"name": "model.layers.13.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 24387584 |
|
} |
|
], |
|
"md5sum": "d6d7eb51eb883337611e4b0371304737" |
|
}, |
|
{ |
|
"dataPath": "params_shard_74.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29360128, |
|
"records": [ |
|
{ |
|
"name": "model.layers.14.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1792 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 29360128, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "18ab2c545499b5d7ff1d466c1ab91862" |
|
}, |
|
{ |
|
"dataPath": "params_shard_75.bin", |
|
"format": "raw-shard", |
|
"nbytes": 58720256, |
|
"records": [ |
|
{ |
|
"name": "model.layers.14.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
28672, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 58720256, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "4c31ef559582804f8b3744038bdf9151" |
|
}, |
|
{ |
|
"dataPath": "params_shard_76.bin", |
|
"format": "raw-shard", |
|
"nbytes": 24395776, |
|
"records": [ |
|
{ |
|
"name": "model.layers.13.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
6144, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 12582912, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.13.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
6144, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 393216, |
|
"byteOffset": 12582912 |
|
}, |
|
{ |
|
"name": "model.layers.13.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 12976128 |
|
}, |
|
{ |
|
"name": "model.layers.13.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 262144, |
|
"byteOffset": 21364736 |
|
}, |
|
{ |
|
"name": "model.layers.14.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 21626880 |
|
}, |
|
{ |
|
"name": "model.layers.14.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
112 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 917504, |
|
"byteOffset": 21635072 |
|
}, |
|
{ |
|
"name": "model.layers.14.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
28672, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1835008, |
|
"byteOffset": 22552576 |
|
}, |
|
{ |
|
"name": "model.layers.14.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 24387584 |
|
} |
|
], |
|
"md5sum": "43fefba5b25d7579d6a053667911f798" |
|
}, |
|
{ |
|
"dataPath": "params_shard_77.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29360128, |
|
"records": [ |
|
{ |
|
"name": "model.layers.15.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1792 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 29360128, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "8b5837ff80bb9cb01c84a8cb9646c8b4" |
|
}, |
|
{ |
|
"dataPath": "params_shard_78.bin", |
|
"format": "raw-shard", |
|
"nbytes": 58720256, |
|
"records": [ |
|
{ |
|
"name": "model.layers.15.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
28672, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 58720256, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "fdd56baeaab896335210297e9092e497" |
|
}, |
|
{ |
|
"dataPath": "params_shard_79.bin", |
|
"format": "raw-shard", |
|
"nbytes": 24395776, |
|
"records": [ |
|
{ |
|
"name": "model.layers.14.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
6144, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 12582912, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.14.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
6144, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 393216, |
|
"byteOffset": 12582912 |
|
}, |
|
{ |
|
"name": "model.layers.14.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 12976128 |
|
}, |
|
{ |
|
"name": "model.layers.14.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 262144, |
|
"byteOffset": 21364736 |
|
}, |
|
{ |
|
"name": "model.layers.15.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 21626880 |
|
}, |
|
{ |
|
"name": "model.layers.15.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
112 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 917504, |
|
"byteOffset": 21635072 |
|
}, |
|
{ |
|
"name": "model.layers.15.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
28672, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1835008, |
|
"byteOffset": 22552576 |
|
}, |
|
{ |
|
"name": "model.layers.15.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 24387584 |
|
} |
|
], |
|
"md5sum": "c54a351d7bc70c4965030b5a9fa29dc4" |
|
}, |
|
{ |
|
"dataPath": "params_shard_80.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29360128, |
|
"records": [ |
|
{ |
|
"name": "model.layers.16.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1792 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 29360128, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "98876cb6f6f95d4c671fd46406be6fa9" |
|
}, |
|
{ |
|
"dataPath": "params_shard_81.bin", |
|
"format": "raw-shard", |
|
"nbytes": 58720256, |
|
"records": [ |
|
{ |
|
"name": "model.layers.16.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
28672, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 58720256, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "7668c72a0e21224a921f8074e6eedb7a" |
|
}, |
|
{ |
|
"dataPath": "params_shard_82.bin", |
|
"format": "raw-shard", |
|
"nbytes": 24395776, |
|
"records": [ |
|
{ |
|
"name": "model.layers.15.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
6144, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 12582912, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.15.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
6144, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 393216, |
|
"byteOffset": 12582912 |
|
}, |
|
{ |
|
"name": "model.layers.15.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 12976128 |
|
}, |
|
{ |
|
"name": "model.layers.15.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 262144, |
|
"byteOffset": 21364736 |
|
}, |
|
{ |
|
"name": "model.layers.16.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 21626880 |
|
}, |
|
{ |
|
"name": "model.layers.16.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
112 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 917504, |
|
"byteOffset": 21635072 |
|
}, |
|
{ |
|
"name": "model.layers.16.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
28672, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1835008, |
|
"byteOffset": 22552576 |
|
}, |
|
{ |
|
"name": "model.layers.16.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 24387584 |
|
} |
|
], |
|
"md5sum": "6d954a47c79bcb3f0bc375c0985dac6d" |
|
}, |
|
{ |
|
"dataPath": "params_shard_83.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29360128, |
|
"records": [ |
|
{ |
|
"name": "model.layers.17.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1792 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 29360128, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "2bf98226bf61bad9253ec822e579ff1e" |
|
}, |
|
{ |
|
"dataPath": "params_shard_84.bin", |
|
"format": "raw-shard", |
|
"nbytes": 58720256, |
|
"records": [ |
|
{ |
|
"name": "model.layers.17.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
28672, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 58720256, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "61f17ad371e8c5379ed92d27a5546aaf" |
|
}, |
|
{ |
|
"dataPath": "params_shard_85.bin", |
|
"format": "raw-shard", |
|
"nbytes": 24395776, |
|
"records": [ |
|
{ |
|
"name": "model.layers.16.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
6144, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 12582912, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.16.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
6144, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 393216, |
|
"byteOffset": 12582912 |
|
}, |
|
{ |
|
"name": "model.layers.16.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 12976128 |
|
}, |
|
{ |
|
"name": "model.layers.16.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 262144, |
|
"byteOffset": 21364736 |
|
}, |
|
{ |
|
"name": "model.layers.17.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 21626880 |
|
}, |
|
{ |
|
"name": "model.layers.17.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
112 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 917504, |
|
"byteOffset": 21635072 |
|
}, |
|
{ |
|
"name": "model.layers.17.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
28672, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1835008, |
|
"byteOffset": 22552576 |
|
}, |
|
{ |
|
"name": "model.layers.17.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 24387584 |
|
} |
|
], |
|
"md5sum": "fbc5dd29d92d82ac600ee9d9875cbcd2" |
|
}, |
|
{ |
|
"dataPath": "params_shard_86.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29360128, |
|
"records": [ |
|
{ |
|
"name": "model.layers.18.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1792 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 29360128, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "59af96bc2b7498fc3f14fc6f6f2cbbf5" |
|
}, |
|
{ |
|
"dataPath": "params_shard_87.bin", |
|
"format": "raw-shard", |
|
"nbytes": 58720256, |
|
"records": [ |
|
{ |
|
"name": "model.layers.18.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
28672, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 58720256, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "aef78833bac2de3472a80222e098eef5" |
|
}, |
|
{ |
|
"dataPath": "params_shard_88.bin", |
|
"format": "raw-shard", |
|
"nbytes": 24395776, |
|
"records": [ |
|
{ |
|
"name": "model.layers.17.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
6144, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 12582912, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.17.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
6144, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 393216, |
|
"byteOffset": 12582912 |
|
}, |
|
{ |
|
"name": "model.layers.17.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 12976128 |
|
}, |
|
{ |
|
"name": "model.layers.17.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 262144, |
|
"byteOffset": 21364736 |
|
}, |
|
{ |
|
"name": "model.layers.18.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 21626880 |
|
}, |
|
{ |
|
"name": "model.layers.18.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
112 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 917504, |
|
"byteOffset": 21635072 |
|
}, |
|
{ |
|
"name": "model.layers.18.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
28672, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1835008, |
|
"byteOffset": 22552576 |
|
}, |
|
{ |
|
"name": "model.layers.18.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 24387584 |
|
} |
|
], |
|
"md5sum": "245bbf36e5657da08827180eff9060c1" |
|
}, |
|
{ |
|
"dataPath": "params_shard_89.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29360128, |
|
"records": [ |
|
{ |
|
"name": "model.layers.19.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1792 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 29360128, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "390b8d38cf1f473c4faf9573ac342220" |
|
}, |
|
{ |
|
"dataPath": "params_shard_90.bin", |
|
"format": "raw-shard", |
|
"nbytes": 58720256, |
|
"records": [ |
|
{ |
|
"name": "model.layers.19.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
28672, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 58720256, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "34b3d2489245ab78c01b2dd75eacbac7" |
|
}, |
|
{ |
|
"dataPath": "params_shard_91.bin", |
|
"format": "raw-shard", |
|
"nbytes": 24395776, |
|
"records": [ |
|
{ |
|
"name": "model.layers.18.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
6144, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 12582912, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.18.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
6144, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 393216, |
|
"byteOffset": 12582912 |
|
}, |
|
{ |
|
"name": "model.layers.18.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 12976128 |
|
}, |
|
{ |
|
"name": "model.layers.18.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 262144, |
|
"byteOffset": 21364736 |
|
}, |
|
{ |
|
"name": "model.layers.19.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 21626880 |
|
}, |
|
{ |
|
"name": "model.layers.19.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
112 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 917504, |
|
"byteOffset": 21635072 |
|
}, |
|
{ |
|
"name": "model.layers.19.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
28672, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1835008, |
|
"byteOffset": 22552576 |
|
}, |
|
{ |
|
"name": "model.layers.19.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 24387584 |
|
} |
|
], |
|
"md5sum": "44c639cb804ee5fb77c2ce30f62061bf" |
|
}, |
|
{ |
|
"dataPath": "params_shard_92.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29360128, |
|
"records": [ |
|
{ |
|
"name": "model.layers.20.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1792 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 29360128, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "e4eca06e08b5ff44461aa98841d70e64" |
|
}, |
|
{ |
|
"dataPath": "params_shard_93.bin", |
|
"format": "raw-shard", |
|
"nbytes": 58720256, |
|
"records": [ |
|
{ |
|
"name": "model.layers.20.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
28672, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 58720256, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "03dab12956f8ba14ebe39097bccc92e8" |
|
}, |
|
{ |
|
"dataPath": "params_shard_94.bin", |
|
"format": "raw-shard", |
|
"nbytes": 24395776, |
|
"records": [ |
|
{ |
|
"name": "model.layers.19.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
6144, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 12582912, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.19.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
6144, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 393216, |
|
"byteOffset": 12582912 |
|
}, |
|
{ |
|
"name": "model.layers.19.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 12976128 |
|
}, |
|
{ |
|
"name": "model.layers.19.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 262144, |
|
"byteOffset": 21364736 |
|
}, |
|
{ |
|
"name": "model.layers.20.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 21626880 |
|
}, |
|
{ |
|
"name": "model.layers.20.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
112 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 917504, |
|
"byteOffset": 21635072 |
|
}, |
|
{ |
|
"name": "model.layers.20.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
28672, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1835008, |
|
"byteOffset": 22552576 |
|
}, |
|
{ |
|
"name": "model.layers.20.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 24387584 |
|
} |
|
], |
|
"md5sum": "ad463cb9aa71aa12615992a1020ae14a" |
|
}, |
|
{ |
|
"dataPath": "params_shard_95.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29360128, |
|
"records": [ |
|
{ |
|
"name": "model.layers.21.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1792 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 29360128, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "c913cd675558f25f5aae0c9211121695" |
|
}, |
|
{ |
|
"dataPath": "params_shard_96.bin", |
|
"format": "raw-shard", |
|
"nbytes": 22544384, |
|
"records": [ |
|
{ |
|
"name": "model.layers.20.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
6144, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 12582912, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.20.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
6144, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 393216, |
|
"byteOffset": 12582912 |
|
}, |
|
{ |
|
"name": "model.layers.20.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 12976128 |
|
}, |
|
{ |
|
"name": "model.layers.20.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 262144, |
|
"byteOffset": 21364736 |
|
}, |
|
{ |
|
"name": "model.layers.21.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
112 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 917504, |
|
"byteOffset": 21626880 |
|
} |
|
], |
|
"md5sum": "eaed3f4cc556a12cf2872dcee9d64093" |
|
}, |
|
{ |
|
"dataPath": "params_shard_97.bin", |
|
"format": "raw-shard", |
|
"nbytes": 21626880, |
|
"records": [ |
|
{ |
|
"name": "model.layers.21.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
6144, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 12582912, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.21.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
6144, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 393216, |
|
"byteOffset": 12582912 |
|
}, |
|
{ |
|
"name": "model.layers.21.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 12976128 |
|
}, |
|
{ |
|
"name": "model.layers.21.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
32 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 262144, |
|
"byteOffset": 21364736 |
|
} |
|
], |
|
"md5sum": "333eec9294809297a31d98474588fe3d" |
|
} |
|
] |
|
} |