|
{ |
|
"metadata": { |
|
"ParamSize": 325, |
|
"ParamBytes": 4213719040.0, |
|
"BitsPerParam": 5.0010664589249245 |
|
}, |
|
"records": [ |
|
{ |
|
"dataPath": "params_shard_0.bin", |
|
"format": "raw-shard", |
|
"nbytes": 66060288, |
|
"records": [ |
|
{ |
|
"name": "lm_head.q_weight", |
|
"shape": [ |
|
32256, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 66060288, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "7b6bec12079fb352588366048c90c833" |
|
}, |
|
{ |
|
"dataPath": "params_shard_1.bin", |
|
"format": "raw-shard", |
|
"nbytes": 30810112, |
|
"records": [ |
|
{ |
|
"name": "lm_head.q_scale", |
|
"shape": [ |
|
32256, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8257536, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.24.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 8257536 |
|
}, |
|
{ |
|
"name": "model.layers.24.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1376 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 22544384, |
|
"byteOffset": 8265728 |
|
} |
|
], |
|
"md5sum": "c20c62c2e3557831f55f76df8c22dd71" |
|
}, |
|
{ |
|
"dataPath": "params_shard_2.bin", |
|
"format": "raw-shard", |
|
"nbytes": 45088768, |
|
"records": [ |
|
{ |
|
"name": "model.layers.24.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
22016, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 45088768, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "3d9d46263a21b07a5b4ff9f4529a99d6" |
|
}, |
|
{ |
|
"dataPath": "params_shard_3.bin", |
|
"format": "raw-shard", |
|
"nbytes": 25165824, |
|
"records": [ |
|
{ |
|
"name": "model.layers.24.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
12288, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 25165824, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "1b69e9587d5ff16f6e839b496647acbe" |
|
}, |
|
{ |
|
"dataPath": "params_shard_4.bin", |
|
"format": "raw-shard", |
|
"nbytes": 22544384, |
|
"records": [ |
|
{ |
|
"name": "model.layers.25.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1376 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 22544384, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "b5f5ab6b96c7ecb01d31c54a2f02778a" |
|
}, |
|
{ |
|
"dataPath": "params_shard_5.bin", |
|
"format": "raw-shard", |
|
"nbytes": 45088768, |
|
"records": [ |
|
{ |
|
"name": "model.layers.25.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
22016, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 45088768, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "b051d8519aec293133d132b23d4513f8" |
|
}, |
|
{ |
|
"dataPath": "params_shard_6.bin", |
|
"format": "raw-shard", |
|
"nbytes": 25165824, |
|
"records": [ |
|
{ |
|
"name": "model.layers.25.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
12288, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 25165824, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "320e0285f9e3f891ece1b1647eae41fc" |
|
}, |
|
{ |
|
"dataPath": "params_shard_7.bin", |
|
"format": "raw-shard", |
|
"nbytes": 32661504, |
|
"records": [ |
|
{ |
|
"name": "model.layers.24.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
344 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2818048, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.24.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
22016, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5636096, |
|
"byteOffset": 2818048 |
|
}, |
|
{ |
|
"name": "model.layers.24.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 8454144 |
|
}, |
|
{ |
|
"name": "model.layers.24.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
12288, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3145728, |
|
"byteOffset": 8462336 |
|
}, |
|
{ |
|
"name": "model.layers.24.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 11608064 |
|
}, |
|
{ |
|
"name": "model.layers.24.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1048576, |
|
"byteOffset": 19996672 |
|
}, |
|
{ |
|
"name": "model.layers.25.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 21045248 |
|
}, |
|
{ |
|
"name": "model.layers.25.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
344 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2818048, |
|
"byteOffset": 21053440 |
|
}, |
|
{ |
|
"name": "model.layers.25.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
22016, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5636096, |
|
"byteOffset": 23871488 |
|
}, |
|
{ |
|
"name": "model.layers.25.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 29507584 |
|
}, |
|
{ |
|
"name": "model.layers.25.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
12288, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3145728, |
|
"byteOffset": 29515776 |
|
} |
|
], |
|
"md5sum": "1e307ac608867bc036562f4318444a60" |
|
}, |
|
{ |
|
"dataPath": "params_shard_8.bin", |
|
"format": "raw-shard", |
|
"nbytes": 31989760, |
|
"records": [ |
|
{ |
|
"name": "model.layers.25.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.25.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1048576, |
|
"byteOffset": 8388608 |
|
}, |
|
{ |
|
"name": "model.layers.26.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 9437184 |
|
}, |
|
{ |
|
"name": "model.layers.26.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1376 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 22544384, |
|
"byteOffset": 9445376 |
|
} |
|
], |
|
"md5sum": "f5421753531357f512eb805e9f98d7ae" |
|
}, |
|
{ |
|
"dataPath": "params_shard_9.bin", |
|
"format": "raw-shard", |
|
"nbytes": 45088768, |
|
"records": [ |
|
{ |
|
"name": "model.layers.26.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
22016, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 45088768, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "56861ea83c28d163e24dff3977e8df85" |
|
}, |
|
{ |
|
"dataPath": "params_shard_10.bin", |
|
"format": "raw-shard", |
|
"nbytes": 25165824, |
|
"records": [ |
|
{ |
|
"name": "model.layers.26.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
12288, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 25165824, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "bbada498955baa264d4ec489e2cc185a" |
|
}, |
|
{ |
|
"dataPath": "params_shard_11.bin", |
|
"format": "raw-shard", |
|
"nbytes": 22544384, |
|
"records": [ |
|
{ |
|
"name": "model.layers.27.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1376 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 22544384, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "9e28245d7684f8a7a74403a32f4f5371" |
|
}, |
|
{ |
|
"dataPath": "params_shard_12.bin", |
|
"format": "raw-shard", |
|
"nbytes": 45088768, |
|
"records": [ |
|
{ |
|
"name": "model.layers.27.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
22016, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 45088768, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "2d86e88d28129c342ec1230da7c18a87" |
|
}, |
|
{ |
|
"dataPath": "params_shard_13.bin", |
|
"format": "raw-shard", |
|
"nbytes": 25165824, |
|
"records": [ |
|
{ |
|
"name": "model.layers.27.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
12288, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 25165824, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "11abece5ffbf1602dd6731fb821247bb" |
|
}, |
|
{ |
|
"dataPath": "params_shard_14.bin", |
|
"format": "raw-shard", |
|
"nbytes": 32661504, |
|
"records": [ |
|
{ |
|
"name": "model.layers.26.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
344 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2818048, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.26.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
22016, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5636096, |
|
"byteOffset": 2818048 |
|
}, |
|
{ |
|
"name": "model.layers.26.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 8454144 |
|
}, |
|
{ |
|
"name": "model.layers.26.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
12288, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3145728, |
|
"byteOffset": 8462336 |
|
}, |
|
{ |
|
"name": "model.layers.26.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 11608064 |
|
}, |
|
{ |
|
"name": "model.layers.26.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1048576, |
|
"byteOffset": 19996672 |
|
}, |
|
{ |
|
"name": "model.layers.27.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 21045248 |
|
}, |
|
{ |
|
"name": "model.layers.27.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
344 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2818048, |
|
"byteOffset": 21053440 |
|
}, |
|
{ |
|
"name": "model.layers.27.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
22016, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5636096, |
|
"byteOffset": 23871488 |
|
}, |
|
{ |
|
"name": "model.layers.27.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 29507584 |
|
}, |
|
{ |
|
"name": "model.layers.27.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
12288, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3145728, |
|
"byteOffset": 29515776 |
|
} |
|
], |
|
"md5sum": "9bbf4c54e02b9534d5b103765ae28b41" |
|
}, |
|
{ |
|
"dataPath": "params_shard_15.bin", |
|
"format": "raw-shard", |
|
"nbytes": 31989760, |
|
"records": [ |
|
{ |
|
"name": "model.layers.27.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.27.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1048576, |
|
"byteOffset": 8388608 |
|
}, |
|
{ |
|
"name": "model.layers.28.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 9437184 |
|
}, |
|
{ |
|
"name": "model.layers.28.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1376 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 22544384, |
|
"byteOffset": 9445376 |
|
} |
|
], |
|
"md5sum": "2f020253f9a54ca0985808b7b95264f7" |
|
}, |
|
{ |
|
"dataPath": "params_shard_16.bin", |
|
"format": "raw-shard", |
|
"nbytes": 45088768, |
|
"records": [ |
|
{ |
|
"name": "model.layers.28.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
22016, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 45088768, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "3872d1ee2123bf7c1c7750a2f670c5f2" |
|
}, |
|
{ |
|
"dataPath": "params_shard_17.bin", |
|
"format": "raw-shard", |
|
"nbytes": 25165824, |
|
"records": [ |
|
{ |
|
"name": "model.layers.28.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
12288, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 25165824, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "93d66b7441f5eb1bb94a071e84e9a65a" |
|
}, |
|
{ |
|
"dataPath": "params_shard_18.bin", |
|
"format": "raw-shard", |
|
"nbytes": 22544384, |
|
"records": [ |
|
{ |
|
"name": "model.layers.29.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1376 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 22544384, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "eda53c6cbf8b3356fbbc20c05e957212" |
|
}, |
|
{ |
|
"dataPath": "params_shard_19.bin", |
|
"format": "raw-shard", |
|
"nbytes": 45088768, |
|
"records": [ |
|
{ |
|
"name": "model.layers.29.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
22016, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 45088768, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "36ede722664aeec77693e89636f77938" |
|
}, |
|
{ |
|
"dataPath": "params_shard_20.bin", |
|
"format": "raw-shard", |
|
"nbytes": 25165824, |
|
"records": [ |
|
{ |
|
"name": "model.layers.29.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
12288, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 25165824, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "8f4ee942871f1bf94cbcc208d35e7ff1" |
|
}, |
|
{ |
|
"dataPath": "params_shard_21.bin", |
|
"format": "raw-shard", |
|
"nbytes": 32661504, |
|
"records": [ |
|
{ |
|
"name": "model.layers.28.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
344 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2818048, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.28.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
22016, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5636096, |
|
"byteOffset": 2818048 |
|
}, |
|
{ |
|
"name": "model.layers.28.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 8454144 |
|
}, |
|
{ |
|
"name": "model.layers.28.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
12288, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3145728, |
|
"byteOffset": 8462336 |
|
}, |
|
{ |
|
"name": "model.layers.28.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 11608064 |
|
}, |
|
{ |
|
"name": "model.layers.28.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1048576, |
|
"byteOffset": 19996672 |
|
}, |
|
{ |
|
"name": "model.layers.29.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 21045248 |
|
}, |
|
{ |
|
"name": "model.layers.29.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
344 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2818048, |
|
"byteOffset": 21053440 |
|
}, |
|
{ |
|
"name": "model.layers.29.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
22016, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5636096, |
|
"byteOffset": 23871488 |
|
}, |
|
{ |
|
"name": "model.layers.29.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 29507584 |
|
}, |
|
{ |
|
"name": "model.layers.29.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
12288, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3145728, |
|
"byteOffset": 29515776 |
|
} |
|
], |
|
"md5sum": "8d33fc1cd467cb77bc620bf93b6b15b1" |
|
}, |
|
{ |
|
"dataPath": "params_shard_22.bin", |
|
"format": "raw-shard", |
|
"nbytes": 31989760, |
|
"records": [ |
|
{ |
|
"name": "model.layers.29.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.29.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1048576, |
|
"byteOffset": 8388608 |
|
}, |
|
{ |
|
"name": "model.layers.30.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 9437184 |
|
}, |
|
{ |
|
"name": "model.layers.30.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1376 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 22544384, |
|
"byteOffset": 9445376 |
|
} |
|
], |
|
"md5sum": "9f37b103032bb9613f7a7ad6fa63ee5a" |
|
}, |
|
{ |
|
"dataPath": "params_shard_23.bin", |
|
"format": "raw-shard", |
|
"nbytes": 45088768, |
|
"records": [ |
|
{ |
|
"name": "model.layers.30.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
22016, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 45088768, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "4b36f7325867d196db49fb5d0c5dc77c" |
|
}, |
|
{ |
|
"dataPath": "params_shard_24.bin", |
|
"format": "raw-shard", |
|
"nbytes": 25165824, |
|
"records": [ |
|
{ |
|
"name": "model.layers.30.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
12288, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 25165824, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "b7fc5fea46aba04c927abe13d900a684" |
|
}, |
|
{ |
|
"dataPath": "params_shard_25.bin", |
|
"format": "raw-shard", |
|
"nbytes": 22544384, |
|
"records": [ |
|
{ |
|
"name": "model.layers.31.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1376 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 22544384, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "9a52f75859b2b13e84100210445014f0" |
|
}, |
|
{ |
|
"dataPath": "params_shard_26.bin", |
|
"format": "raw-shard", |
|
"nbytes": 45088768, |
|
"records": [ |
|
{ |
|
"name": "model.layers.31.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
22016, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 45088768, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "5d6f91a66804e445a62fbe86b88d2151" |
|
}, |
|
{ |
|
"dataPath": "params_shard_27.bin", |
|
"format": "raw-shard", |
|
"nbytes": 25165824, |
|
"records": [ |
|
{ |
|
"name": "model.layers.31.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
12288, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 25165824, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "0b779197098086dad28c9ced18dec93c" |
|
}, |
|
{ |
|
"dataPath": "params_shard_28.bin", |
|
"format": "raw-shard", |
|
"nbytes": 32661504, |
|
"records": [ |
|
{ |
|
"name": "model.layers.30.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
344 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2818048, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.30.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
22016, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5636096, |
|
"byteOffset": 2818048 |
|
}, |
|
{ |
|
"name": "model.layers.30.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 8454144 |
|
}, |
|
{ |
|
"name": "model.layers.30.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
12288, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3145728, |
|
"byteOffset": 8462336 |
|
}, |
|
{ |
|
"name": "model.layers.30.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 11608064 |
|
}, |
|
{ |
|
"name": "model.layers.30.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1048576, |
|
"byteOffset": 19996672 |
|
}, |
|
{ |
|
"name": "model.layers.31.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 21045248 |
|
}, |
|
{ |
|
"name": "model.layers.31.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
344 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2818048, |
|
"byteOffset": 21053440 |
|
}, |
|
{ |
|
"name": "model.layers.31.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
22016, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5636096, |
|
"byteOffset": 23871488 |
|
}, |
|
{ |
|
"name": "model.layers.31.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 29507584 |
|
}, |
|
{ |
|
"name": "model.layers.31.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
12288, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3145728, |
|
"byteOffset": 29515776 |
|
} |
|
], |
|
"md5sum": "70e09b562aa26a6e40c7f9301b6801d1" |
|
}, |
|
{ |
|
"dataPath": "params_shard_29.bin", |
|
"format": "raw-shard", |
|
"nbytes": 66060288, |
|
"records": [ |
|
{ |
|
"name": "model.embed_tokens.q_weight", |
|
"shape": [ |
|
32256, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 66060288, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "4c292bafabb0bc4cd5dfdbf9a84c7f1b" |
|
}, |
|
{ |
|
"dataPath": "params_shard_30.bin", |
|
"format": "raw-shard", |
|
"nbytes": 22544384, |
|
"records": [ |
|
{ |
|
"name": "model.layers.0.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1376 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 22544384, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "fba8c19b8c466083207d774aad5ea640" |
|
}, |
|
{ |
|
"dataPath": "params_shard_31.bin", |
|
"format": "raw-shard", |
|
"nbytes": 45088768, |
|
"records": [ |
|
{ |
|
"name": "model.layers.0.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
22016, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 45088768, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "b8cb19279ada345b8f17eed9dbe8dfe4" |
|
}, |
|
{ |
|
"dataPath": "params_shard_32.bin", |
|
"format": "raw-shard", |
|
"nbytes": 25165824, |
|
"records": [ |
|
{ |
|
"name": "model.layers.0.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
12288, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 25165824, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "947a4e99e42235aa3693392d4d307cf5" |
|
}, |
|
{ |
|
"dataPath": "params_shard_33.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29319168, |
|
"records": [ |
|
{ |
|
"name": "model.layers.31.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.31.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1048576, |
|
"byteOffset": 8388608 |
|
}, |
|
{ |
|
"name": "model.norm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 9437184 |
|
}, |
|
{ |
|
"name": "model.embed_tokens.q_scale", |
|
"shape": [ |
|
32256, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8257536, |
|
"byteOffset": 9445376 |
|
}, |
|
{ |
|
"name": "model.layers.0.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 17702912 |
|
}, |
|
{ |
|
"name": "model.layers.0.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
344 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2818048, |
|
"byteOffset": 17711104 |
|
}, |
|
{ |
|
"name": "model.layers.0.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
22016, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5636096, |
|
"byteOffset": 20529152 |
|
}, |
|
{ |
|
"name": "model.layers.0.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 26165248 |
|
}, |
|
{ |
|
"name": "model.layers.0.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
12288, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3145728, |
|
"byteOffset": 26173440 |
|
} |
|
], |
|
"md5sum": "91821f1452e68e554e2f6390362932ea" |
|
}, |
|
{ |
|
"dataPath": "params_shard_34.bin", |
|
"format": "raw-shard", |
|
"nbytes": 31989760, |
|
"records": [ |
|
{ |
|
"name": "model.layers.0.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.0.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1048576, |
|
"byteOffset": 8388608 |
|
}, |
|
{ |
|
"name": "model.layers.1.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 9437184 |
|
}, |
|
{ |
|
"name": "model.layers.1.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1376 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 22544384, |
|
"byteOffset": 9445376 |
|
} |
|
], |
|
"md5sum": "a9ec18987206b1f60db741eb139d8ddd" |
|
}, |
|
{ |
|
"dataPath": "params_shard_35.bin", |
|
"format": "raw-shard", |
|
"nbytes": 45088768, |
|
"records": [ |
|
{ |
|
"name": "model.layers.1.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
22016, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 45088768, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "862064bcad7a15039c3f77f90f9233cb" |
|
}, |
|
{ |
|
"dataPath": "params_shard_36.bin", |
|
"format": "raw-shard", |
|
"nbytes": 25165824, |
|
"records": [ |
|
{ |
|
"name": "model.layers.1.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
12288, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 25165824, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "d1c8c6f914a92b62a67246f0735d6ef7" |
|
}, |
|
{ |
|
"dataPath": "params_shard_37.bin", |
|
"format": "raw-shard", |
|
"nbytes": 22544384, |
|
"records": [ |
|
{ |
|
"name": "model.layers.10.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1376 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 22544384, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "722bc8bb423a987d4a6fea186c5397ac" |
|
}, |
|
{ |
|
"dataPath": "params_shard_38.bin", |
|
"format": "raw-shard", |
|
"nbytes": 45088768, |
|
"records": [ |
|
{ |
|
"name": "model.layers.10.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
22016, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 45088768, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "64036fc4503fa6e946166105b19fc9fd" |
|
}, |
|
{ |
|
"dataPath": "params_shard_39.bin", |
|
"format": "raw-shard", |
|
"nbytes": 25165824, |
|
"records": [ |
|
{ |
|
"name": "model.layers.10.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
12288, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 25165824, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "1cb2cacd73a58ce801ddcdcad96adba2" |
|
}, |
|
{ |
|
"dataPath": "params_shard_40.bin", |
|
"format": "raw-shard", |
|
"nbytes": 32661504, |
|
"records": [ |
|
{ |
|
"name": "model.layers.1.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
344 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2818048, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.1.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
22016, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5636096, |
|
"byteOffset": 2818048 |
|
}, |
|
{ |
|
"name": "model.layers.1.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 8454144 |
|
}, |
|
{ |
|
"name": "model.layers.1.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
12288, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3145728, |
|
"byteOffset": 8462336 |
|
}, |
|
{ |
|
"name": "model.layers.1.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 11608064 |
|
}, |
|
{ |
|
"name": "model.layers.1.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1048576, |
|
"byteOffset": 19996672 |
|
}, |
|
{ |
|
"name": "model.layers.10.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 21045248 |
|
}, |
|
{ |
|
"name": "model.layers.10.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
344 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2818048, |
|
"byteOffset": 21053440 |
|
}, |
|
{ |
|
"name": "model.layers.10.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
22016, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5636096, |
|
"byteOffset": 23871488 |
|
}, |
|
{ |
|
"name": "model.layers.10.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 29507584 |
|
}, |
|
{ |
|
"name": "model.layers.10.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
12288, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3145728, |
|
"byteOffset": 29515776 |
|
} |
|
], |
|
"md5sum": "c6b193fc8257867deb30939deb5816e8" |
|
}, |
|
{ |
|
"dataPath": "params_shard_41.bin", |
|
"format": "raw-shard", |
|
"nbytes": 31989760, |
|
"records": [ |
|
{ |
|
"name": "model.layers.10.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.10.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1048576, |
|
"byteOffset": 8388608 |
|
}, |
|
{ |
|
"name": "model.layers.11.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 9437184 |
|
}, |
|
{ |
|
"name": "model.layers.11.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1376 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 22544384, |
|
"byteOffset": 9445376 |
|
} |
|
], |
|
"md5sum": "9de0abed91b053d42f6461b3807ba9ff" |
|
}, |
|
{ |
|
"dataPath": "params_shard_42.bin", |
|
"format": "raw-shard", |
|
"nbytes": 45088768, |
|
"records": [ |
|
{ |
|
"name": "model.layers.11.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
22016, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 45088768, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "feaf7271e3b61cdd7b1152fef5cfb5d7" |
|
}, |
|
{ |
|
"dataPath": "params_shard_43.bin", |
|
"format": "raw-shard", |
|
"nbytes": 25165824, |
|
"records": [ |
|
{ |
|
"name": "model.layers.11.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
12288, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 25165824, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "e9e4f7ef01dea09c2a3c82be96795bb8" |
|
}, |
|
{ |
|
"dataPath": "params_shard_44.bin", |
|
"format": "raw-shard", |
|
"nbytes": 22544384, |
|
"records": [ |
|
{ |
|
"name": "model.layers.12.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1376 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 22544384, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "cf24da9bb0e6d1dc50f255e9f9e78ad8" |
|
}, |
|
{ |
|
"dataPath": "params_shard_45.bin", |
|
"format": "raw-shard", |
|
"nbytes": 45088768, |
|
"records": [ |
|
{ |
|
"name": "model.layers.12.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
22016, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 45088768, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "bccc6658ebf36faf23d01b6708355193" |
|
}, |
|
{ |
|
"dataPath": "params_shard_46.bin", |
|
"format": "raw-shard", |
|
"nbytes": 25165824, |
|
"records": [ |
|
{ |
|
"name": "model.layers.12.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
12288, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 25165824, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "671653b9c083a2e699b2baee99acddbc" |
|
}, |
|
{ |
|
"dataPath": "params_shard_47.bin", |
|
"format": "raw-shard", |
|
"nbytes": 32661504, |
|
"records": [ |
|
{ |
|
"name": "model.layers.11.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
344 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2818048, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.11.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
22016, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5636096, |
|
"byteOffset": 2818048 |
|
}, |
|
{ |
|
"name": "model.layers.11.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 8454144 |
|
}, |
|
{ |
|
"name": "model.layers.11.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
12288, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3145728, |
|
"byteOffset": 8462336 |
|
}, |
|
{ |
|
"name": "model.layers.11.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 11608064 |
|
}, |
|
{ |
|
"name": "model.layers.11.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1048576, |
|
"byteOffset": 19996672 |
|
}, |
|
{ |
|
"name": "model.layers.12.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 21045248 |
|
}, |
|
{ |
|
"name": "model.layers.12.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
344 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2818048, |
|
"byteOffset": 21053440 |
|
}, |
|
{ |
|
"name": "model.layers.12.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
22016, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5636096, |
|
"byteOffset": 23871488 |
|
}, |
|
{ |
|
"name": "model.layers.12.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 29507584 |
|
}, |
|
{ |
|
"name": "model.layers.12.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
12288, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3145728, |
|
"byteOffset": 29515776 |
|
} |
|
], |
|
"md5sum": "f1d3b8b319ed34ccdb439d5c119bb7b1" |
|
}, |
|
{ |
|
"dataPath": "params_shard_48.bin", |
|
"format": "raw-shard", |
|
"nbytes": 31989760, |
|
"records": [ |
|
{ |
|
"name": "model.layers.12.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.12.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1048576, |
|
"byteOffset": 8388608 |
|
}, |
|
{ |
|
"name": "model.layers.13.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 9437184 |
|
}, |
|
{ |
|
"name": "model.layers.13.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1376 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 22544384, |
|
"byteOffset": 9445376 |
|
} |
|
], |
|
"md5sum": "ae01af0e100ba3260909824d5a9c558b" |
|
}, |
|
{ |
|
"dataPath": "params_shard_49.bin", |
|
"format": "raw-shard", |
|
"nbytes": 45088768, |
|
"records": [ |
|
{ |
|
"name": "model.layers.13.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
22016, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 45088768, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "01eb2728e2501939438db1cfcfc019b6" |
|
}, |
|
{ |
|
"dataPath": "params_shard_50.bin", |
|
"format": "raw-shard", |
|
"nbytes": 25165824, |
|
"records": [ |
|
{ |
|
"name": "model.layers.13.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
12288, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 25165824, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "ddbd0a76a91c0717741a8fce4e5601ff" |
|
}, |
|
{ |
|
"dataPath": "params_shard_51.bin", |
|
"format": "raw-shard", |
|
"nbytes": 22544384, |
|
"records": [ |
|
{ |
|
"name": "model.layers.14.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1376 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 22544384, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "31f31fe91fac28fa8a9cf41c170a203c" |
|
}, |
|
{ |
|
"dataPath": "params_shard_52.bin", |
|
"format": "raw-shard", |
|
"nbytes": 45088768, |
|
"records": [ |
|
{ |
|
"name": "model.layers.14.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
22016, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 45088768, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "7652b35174a57733ea8414e4663f507c" |
|
}, |
|
{ |
|
"dataPath": "params_shard_53.bin", |
|
"format": "raw-shard", |
|
"nbytes": 25165824, |
|
"records": [ |
|
{ |
|
"name": "model.layers.14.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
12288, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 25165824, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "7e3c99d418ca74e25172403c59f3cc07" |
|
}, |
|
{ |
|
"dataPath": "params_shard_54.bin", |
|
"format": "raw-shard", |
|
"nbytes": 32661504, |
|
"records": [ |
|
{ |
|
"name": "model.layers.13.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
344 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2818048, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.13.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
22016, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5636096, |
|
"byteOffset": 2818048 |
|
}, |
|
{ |
|
"name": "model.layers.13.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 8454144 |
|
}, |
|
{ |
|
"name": "model.layers.13.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
12288, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3145728, |
|
"byteOffset": 8462336 |
|
}, |
|
{ |
|
"name": "model.layers.13.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 11608064 |
|
}, |
|
{ |
|
"name": "model.layers.13.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1048576, |
|
"byteOffset": 19996672 |
|
}, |
|
{ |
|
"name": "model.layers.14.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 21045248 |
|
}, |
|
{ |
|
"name": "model.layers.14.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
344 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2818048, |
|
"byteOffset": 21053440 |
|
}, |
|
{ |
|
"name": "model.layers.14.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
22016, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5636096, |
|
"byteOffset": 23871488 |
|
}, |
|
{ |
|
"name": "model.layers.14.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 29507584 |
|
}, |
|
{ |
|
"name": "model.layers.14.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
12288, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3145728, |
|
"byteOffset": 29515776 |
|
} |
|
], |
|
"md5sum": "4812eff80f5e6b05f82ec9f300d6f6d1" |
|
}, |
|
{ |
|
"dataPath": "params_shard_55.bin", |
|
"format": "raw-shard", |
|
"nbytes": 31989760, |
|
"records": [ |
|
{ |
|
"name": "model.layers.14.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.14.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1048576, |
|
"byteOffset": 8388608 |
|
}, |
|
{ |
|
"name": "model.layers.15.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 9437184 |
|
}, |
|
{ |
|
"name": "model.layers.15.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1376 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 22544384, |
|
"byteOffset": 9445376 |
|
} |
|
], |
|
"md5sum": "12e6b28ee2d3161a19b30bf976f503cf" |
|
}, |
|
{ |
|
"dataPath": "params_shard_56.bin", |
|
"format": "raw-shard", |
|
"nbytes": 45088768, |
|
"records": [ |
|
{ |
|
"name": "model.layers.15.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
22016, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 45088768, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "92cb4992a85221c6ce795703bdf48bbc" |
|
}, |
|
{ |
|
"dataPath": "params_shard_57.bin", |
|
"format": "raw-shard", |
|
"nbytes": 25165824, |
|
"records": [ |
|
{ |
|
"name": "model.layers.15.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
12288, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 25165824, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "c86545c65b101279606838696649499b" |
|
}, |
|
{ |
|
"dataPath": "params_shard_58.bin", |
|
"format": "raw-shard", |
|
"nbytes": 22544384, |
|
"records": [ |
|
{ |
|
"name": "model.layers.16.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1376 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 22544384, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "b8b7fb64e43708a5fe5e8e4b7f01f6db" |
|
}, |
|
{ |
|
"dataPath": "params_shard_59.bin", |
|
"format": "raw-shard", |
|
"nbytes": 45088768, |
|
"records": [ |
|
{ |
|
"name": "model.layers.16.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
22016, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 45088768, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "75820895be275c2ee7aa290283095cd3" |
|
}, |
|
{ |
|
"dataPath": "params_shard_60.bin", |
|
"format": "raw-shard", |
|
"nbytes": 25165824, |
|
"records": [ |
|
{ |
|
"name": "model.layers.16.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
12288, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 25165824, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "86225fa864e63dcd3b7f31edd2db7340" |
|
}, |
|
{ |
|
"dataPath": "params_shard_61.bin", |
|
"format": "raw-shard", |
|
"nbytes": 32661504, |
|
"records": [ |
|
{ |
|
"name": "model.layers.15.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
344 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2818048, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.15.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
22016, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5636096, |
|
"byteOffset": 2818048 |
|
}, |
|
{ |
|
"name": "model.layers.15.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 8454144 |
|
}, |
|
{ |
|
"name": "model.layers.15.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
12288, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3145728, |
|
"byteOffset": 8462336 |
|
}, |
|
{ |
|
"name": "model.layers.15.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 11608064 |
|
}, |
|
{ |
|
"name": "model.layers.15.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1048576, |
|
"byteOffset": 19996672 |
|
}, |
|
{ |
|
"name": "model.layers.16.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 21045248 |
|
}, |
|
{ |
|
"name": "model.layers.16.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
344 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2818048, |
|
"byteOffset": 21053440 |
|
}, |
|
{ |
|
"name": "model.layers.16.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
22016, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5636096, |
|
"byteOffset": 23871488 |
|
}, |
|
{ |
|
"name": "model.layers.16.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 29507584 |
|
}, |
|
{ |
|
"name": "model.layers.16.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
12288, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3145728, |
|
"byteOffset": 29515776 |
|
} |
|
], |
|
"md5sum": "102e40988714d0efb63c4a5aa0d8adb0" |
|
}, |
|
{ |
|
"dataPath": "params_shard_62.bin", |
|
"format": "raw-shard", |
|
"nbytes": 31989760, |
|
"records": [ |
|
{ |
|
"name": "model.layers.16.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.16.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1048576, |
|
"byteOffset": 8388608 |
|
}, |
|
{ |
|
"name": "model.layers.17.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 9437184 |
|
}, |
|
{ |
|
"name": "model.layers.17.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1376 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 22544384, |
|
"byteOffset": 9445376 |
|
} |
|
], |
|
"md5sum": "badcd9397e6d6a0ace4d47de12e04eed" |
|
}, |
|
{ |
|
"dataPath": "params_shard_63.bin", |
|
"format": "raw-shard", |
|
"nbytes": 45088768, |
|
"records": [ |
|
{ |
|
"name": "model.layers.17.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
22016, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 45088768, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "0a14eb99cfedb3e94e7c2d7ab4ee12b3" |
|
}, |
|
{ |
|
"dataPath": "params_shard_64.bin", |
|
"format": "raw-shard", |
|
"nbytes": 25165824, |
|
"records": [ |
|
{ |
|
"name": "model.layers.17.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
12288, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 25165824, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "2de043c9ab5b583b34201c50fc1a0a26" |
|
}, |
|
{ |
|
"dataPath": "params_shard_65.bin", |
|
"format": "raw-shard", |
|
"nbytes": 22544384, |
|
"records": [ |
|
{ |
|
"name": "model.layers.18.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1376 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 22544384, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "d81b33c161e53cf59e288582b8c3a9a3" |
|
}, |
|
{ |
|
"dataPath": "params_shard_66.bin", |
|
"format": "raw-shard", |
|
"nbytes": 45088768, |
|
"records": [ |
|
{ |
|
"name": "model.layers.18.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
22016, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 45088768, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "324acedb27d14f180f8fb0f5d086a5da" |
|
}, |
|
{ |
|
"dataPath": "params_shard_67.bin", |
|
"format": "raw-shard", |
|
"nbytes": 25165824, |
|
"records": [ |
|
{ |
|
"name": "model.layers.18.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
12288, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 25165824, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "f7cf5bb45bad4554bbe3dd0b41365137" |
|
}, |
|
{ |
|
"dataPath": "params_shard_68.bin", |
|
"format": "raw-shard", |
|
"nbytes": 32661504, |
|
"records": [ |
|
{ |
|
"name": "model.layers.17.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
344 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2818048, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.17.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
22016, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5636096, |
|
"byteOffset": 2818048 |
|
}, |
|
{ |
|
"name": "model.layers.17.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 8454144 |
|
}, |
|
{ |
|
"name": "model.layers.17.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
12288, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3145728, |
|
"byteOffset": 8462336 |
|
}, |
|
{ |
|
"name": "model.layers.17.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 11608064 |
|
}, |
|
{ |
|
"name": "model.layers.17.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1048576, |
|
"byteOffset": 19996672 |
|
}, |
|
{ |
|
"name": "model.layers.18.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 21045248 |
|
}, |
|
{ |
|
"name": "model.layers.18.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
344 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2818048, |
|
"byteOffset": 21053440 |
|
}, |
|
{ |
|
"name": "model.layers.18.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
22016, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5636096, |
|
"byteOffset": 23871488 |
|
}, |
|
{ |
|
"name": "model.layers.18.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 29507584 |
|
}, |
|
{ |
|
"name": "model.layers.18.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
12288, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3145728, |
|
"byteOffset": 29515776 |
|
} |
|
], |
|
"md5sum": "2ddcaa192eddbbfa79257d5b84a82a86" |
|
}, |
|
{ |
|
"dataPath": "params_shard_69.bin", |
|
"format": "raw-shard", |
|
"nbytes": 31989760, |
|
"records": [ |
|
{ |
|
"name": "model.layers.18.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.18.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1048576, |
|
"byteOffset": 8388608 |
|
}, |
|
{ |
|
"name": "model.layers.19.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 9437184 |
|
}, |
|
{ |
|
"name": "model.layers.19.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1376 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 22544384, |
|
"byteOffset": 9445376 |
|
} |
|
], |
|
"md5sum": "a4ef2eb96edc2b4496785b004d539607" |
|
}, |
|
{ |
|
"dataPath": "params_shard_70.bin", |
|
"format": "raw-shard", |
|
"nbytes": 45088768, |
|
"records": [ |
|
{ |
|
"name": "model.layers.19.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
22016, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 45088768, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "3b5586c252aec02c8644e8001a70a7f5" |
|
}, |
|
{ |
|
"dataPath": "params_shard_71.bin", |
|
"format": "raw-shard", |
|
"nbytes": 25165824, |
|
"records": [ |
|
{ |
|
"name": "model.layers.19.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
12288, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 25165824, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "9dc7775fb0fa7763037fba4116652444" |
|
}, |
|
{ |
|
"dataPath": "params_shard_72.bin", |
|
"format": "raw-shard", |
|
"nbytes": 22544384, |
|
"records": [ |
|
{ |
|
"name": "model.layers.2.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1376 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 22544384, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "102ecdc04664240c031b5ab5db475e6b" |
|
}, |
|
{ |
|
"dataPath": "params_shard_73.bin", |
|
"format": "raw-shard", |
|
"nbytes": 45088768, |
|
"records": [ |
|
{ |
|
"name": "model.layers.2.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
22016, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 45088768, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "5278860f4edced75579985c142ea452d" |
|
}, |
|
{ |
|
"dataPath": "params_shard_74.bin", |
|
"format": "raw-shard", |
|
"nbytes": 25165824, |
|
"records": [ |
|
{ |
|
"name": "model.layers.2.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
12288, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 25165824, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "e3249c826e2c33bf6849eaea9a25cb21" |
|
}, |
|
{ |
|
"dataPath": "params_shard_75.bin", |
|
"format": "raw-shard", |
|
"nbytes": 32661504, |
|
"records": [ |
|
{ |
|
"name": "model.layers.19.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
344 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2818048, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.19.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
22016, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5636096, |
|
"byteOffset": 2818048 |
|
}, |
|
{ |
|
"name": "model.layers.19.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 8454144 |
|
}, |
|
{ |
|
"name": "model.layers.19.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
12288, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3145728, |
|
"byteOffset": 8462336 |
|
}, |
|
{ |
|
"name": "model.layers.19.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 11608064 |
|
}, |
|
{ |
|
"name": "model.layers.19.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1048576, |
|
"byteOffset": 19996672 |
|
}, |
|
{ |
|
"name": "model.layers.2.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 21045248 |
|
}, |
|
{ |
|
"name": "model.layers.2.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
344 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2818048, |
|
"byteOffset": 21053440 |
|
}, |
|
{ |
|
"name": "model.layers.2.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
22016, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5636096, |
|
"byteOffset": 23871488 |
|
}, |
|
{ |
|
"name": "model.layers.2.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 29507584 |
|
}, |
|
{ |
|
"name": "model.layers.2.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
12288, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3145728, |
|
"byteOffset": 29515776 |
|
} |
|
], |
|
"md5sum": "03a61ef7af11c47166de6098bbfb6259" |
|
}, |
|
{ |
|
"dataPath": "params_shard_76.bin", |
|
"format": "raw-shard", |
|
"nbytes": 31989760, |
|
"records": [ |
|
{ |
|
"name": "model.layers.2.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.2.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1048576, |
|
"byteOffset": 8388608 |
|
}, |
|
{ |
|
"name": "model.layers.20.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 9437184 |
|
}, |
|
{ |
|
"name": "model.layers.20.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1376 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 22544384, |
|
"byteOffset": 9445376 |
|
} |
|
], |
|
"md5sum": "9269cc1f7ebc1809114b1c820fc30e16" |
|
}, |
|
{ |
|
"dataPath": "params_shard_77.bin", |
|
"format": "raw-shard", |
|
"nbytes": 45088768, |
|
"records": [ |
|
{ |
|
"name": "model.layers.20.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
22016, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 45088768, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "a5eb968a0ee79f802b9f4a8c90538ab7" |
|
}, |
|
{ |
|
"dataPath": "params_shard_78.bin", |
|
"format": "raw-shard", |
|
"nbytes": 25165824, |
|
"records": [ |
|
{ |
|
"name": "model.layers.20.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
12288, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 25165824, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "3660ef86266b4aaf388045cf903a58bc" |
|
}, |
|
{ |
|
"dataPath": "params_shard_79.bin", |
|
"format": "raw-shard", |
|
"nbytes": 22544384, |
|
"records": [ |
|
{ |
|
"name": "model.layers.21.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1376 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 22544384, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "2c7a5d0ffd817c66bc958511e401a2ec" |
|
}, |
|
{ |
|
"dataPath": "params_shard_80.bin", |
|
"format": "raw-shard", |
|
"nbytes": 45088768, |
|
"records": [ |
|
{ |
|
"name": "model.layers.21.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
22016, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 45088768, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "40b68ab74dbb2613715ae48a7cf82bd7" |
|
}, |
|
{ |
|
"dataPath": "params_shard_81.bin", |
|
"format": "raw-shard", |
|
"nbytes": 25165824, |
|
"records": [ |
|
{ |
|
"name": "model.layers.21.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
12288, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 25165824, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "cfbb7649989f9cb07d25013cc5f1a2a5" |
|
}, |
|
{ |
|
"dataPath": "params_shard_82.bin", |
|
"format": "raw-shard", |
|
"nbytes": 32661504, |
|
"records": [ |
|
{ |
|
"name": "model.layers.20.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
344 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2818048, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.20.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
22016, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5636096, |
|
"byteOffset": 2818048 |
|
}, |
|
{ |
|
"name": "model.layers.20.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 8454144 |
|
}, |
|
{ |
|
"name": "model.layers.20.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
12288, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3145728, |
|
"byteOffset": 8462336 |
|
}, |
|
{ |
|
"name": "model.layers.20.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 11608064 |
|
}, |
|
{ |
|
"name": "model.layers.20.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1048576, |
|
"byteOffset": 19996672 |
|
}, |
|
{ |
|
"name": "model.layers.21.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 21045248 |
|
}, |
|
{ |
|
"name": "model.layers.21.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
344 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2818048, |
|
"byteOffset": 21053440 |
|
}, |
|
{ |
|
"name": "model.layers.21.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
22016, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5636096, |
|
"byteOffset": 23871488 |
|
}, |
|
{ |
|
"name": "model.layers.21.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 29507584 |
|
}, |
|
{ |
|
"name": "model.layers.21.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
12288, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3145728, |
|
"byteOffset": 29515776 |
|
} |
|
], |
|
"md5sum": "08bcf02f1eb206f6ac2fdba2310c1c13" |
|
}, |
|
{ |
|
"dataPath": "params_shard_83.bin", |
|
"format": "raw-shard", |
|
"nbytes": 31989760, |
|
"records": [ |
|
{ |
|
"name": "model.layers.21.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.21.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1048576, |
|
"byteOffset": 8388608 |
|
}, |
|
{ |
|
"name": "model.layers.22.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 9437184 |
|
}, |
|
{ |
|
"name": "model.layers.22.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1376 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 22544384, |
|
"byteOffset": 9445376 |
|
} |
|
], |
|
"md5sum": "ca5991068cc24a7ae18de3f7abbaca19" |
|
}, |
|
{ |
|
"dataPath": "params_shard_84.bin", |
|
"format": "raw-shard", |
|
"nbytes": 45088768, |
|
"records": [ |
|
{ |
|
"name": "model.layers.22.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
22016, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 45088768, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "3d6a966f1178ff78c5114a0cbf0b00be" |
|
}, |
|
{ |
|
"dataPath": "params_shard_85.bin", |
|
"format": "raw-shard", |
|
"nbytes": 25165824, |
|
"records": [ |
|
{ |
|
"name": "model.layers.22.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
12288, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 25165824, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "3d57198ddc7b35b2c93722dba46ecdeb" |
|
}, |
|
{ |
|
"dataPath": "params_shard_86.bin", |
|
"format": "raw-shard", |
|
"nbytes": 22544384, |
|
"records": [ |
|
{ |
|
"name": "model.layers.23.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1376 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 22544384, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "fa40cdb8320df600547fa6e5f3c88669" |
|
}, |
|
{ |
|
"dataPath": "params_shard_87.bin", |
|
"format": "raw-shard", |
|
"nbytes": 45088768, |
|
"records": [ |
|
{ |
|
"name": "model.layers.23.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
22016, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 45088768, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "c4767700ff2ca49127367d957752af0f" |
|
}, |
|
{ |
|
"dataPath": "params_shard_88.bin", |
|
"format": "raw-shard", |
|
"nbytes": 25165824, |
|
"records": [ |
|
{ |
|
"name": "model.layers.23.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
12288, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 25165824, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "afd648a9d0deb79ec10438b13ab60ce1" |
|
}, |
|
{ |
|
"dataPath": "params_shard_89.bin", |
|
"format": "raw-shard", |
|
"nbytes": 32661504, |
|
"records": [ |
|
{ |
|
"name": "model.layers.22.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
344 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2818048, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.22.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
22016, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5636096, |
|
"byteOffset": 2818048 |
|
}, |
|
{ |
|
"name": "model.layers.22.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 8454144 |
|
}, |
|
{ |
|
"name": "model.layers.22.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
12288, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3145728, |
|
"byteOffset": 8462336 |
|
}, |
|
{ |
|
"name": "model.layers.22.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 11608064 |
|
}, |
|
{ |
|
"name": "model.layers.22.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1048576, |
|
"byteOffset": 19996672 |
|
}, |
|
{ |
|
"name": "model.layers.23.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 21045248 |
|
}, |
|
{ |
|
"name": "model.layers.23.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
344 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2818048, |
|
"byteOffset": 21053440 |
|
}, |
|
{ |
|
"name": "model.layers.23.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
22016, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5636096, |
|
"byteOffset": 23871488 |
|
}, |
|
{ |
|
"name": "model.layers.23.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 29507584 |
|
}, |
|
{ |
|
"name": "model.layers.23.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
12288, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3145728, |
|
"byteOffset": 29515776 |
|
} |
|
], |
|
"md5sum": "79664e2386031b2301ce970b124b075c" |
|
}, |
|
{ |
|
"dataPath": "params_shard_90.bin", |
|
"format": "raw-shard", |
|
"nbytes": 31989760, |
|
"records": [ |
|
{ |
|
"name": "model.layers.23.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.23.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1048576, |
|
"byteOffset": 8388608 |
|
}, |
|
{ |
|
"name": "model.layers.3.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 9437184 |
|
}, |
|
{ |
|
"name": "model.layers.3.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1376 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 22544384, |
|
"byteOffset": 9445376 |
|
} |
|
], |
|
"md5sum": "bb6ef361af0074b67ab76d3917969691" |
|
}, |
|
{ |
|
"dataPath": "params_shard_91.bin", |
|
"format": "raw-shard", |
|
"nbytes": 45088768, |
|
"records": [ |
|
{ |
|
"name": "model.layers.3.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
22016, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 45088768, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "f5e51e5cfb4c47e178caf150df283c89" |
|
}, |
|
{ |
|
"dataPath": "params_shard_92.bin", |
|
"format": "raw-shard", |
|
"nbytes": 25165824, |
|
"records": [ |
|
{ |
|
"name": "model.layers.3.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
12288, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 25165824, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "76c2493e4efcab98511dd5745a9e1c8f" |
|
}, |
|
{ |
|
"dataPath": "params_shard_93.bin", |
|
"format": "raw-shard", |
|
"nbytes": 22544384, |
|
"records": [ |
|
{ |
|
"name": "model.layers.4.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1376 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 22544384, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "2aeab8e58980996e0ddb33fc2642afda" |
|
}, |
|
{ |
|
"dataPath": "params_shard_94.bin", |
|
"format": "raw-shard", |
|
"nbytes": 45088768, |
|
"records": [ |
|
{ |
|
"name": "model.layers.4.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
22016, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 45088768, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "99ac69f764366150251b9415ee419c1d" |
|
}, |
|
{ |
|
"dataPath": "params_shard_95.bin", |
|
"format": "raw-shard", |
|
"nbytes": 25165824, |
|
"records": [ |
|
{ |
|
"name": "model.layers.4.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
12288, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 25165824, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "0e8f679d3d4b6fc1d434164e1aebd3af" |
|
}, |
|
{ |
|
"dataPath": "params_shard_96.bin", |
|
"format": "raw-shard", |
|
"nbytes": 32661504, |
|
"records": [ |
|
{ |
|
"name": "model.layers.3.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
344 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2818048, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.3.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
22016, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5636096, |
|
"byteOffset": 2818048 |
|
}, |
|
{ |
|
"name": "model.layers.3.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 8454144 |
|
}, |
|
{ |
|
"name": "model.layers.3.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
12288, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3145728, |
|
"byteOffset": 8462336 |
|
}, |
|
{ |
|
"name": "model.layers.3.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 11608064 |
|
}, |
|
{ |
|
"name": "model.layers.3.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1048576, |
|
"byteOffset": 19996672 |
|
}, |
|
{ |
|
"name": "model.layers.4.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 21045248 |
|
}, |
|
{ |
|
"name": "model.layers.4.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
344 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2818048, |
|
"byteOffset": 21053440 |
|
}, |
|
{ |
|
"name": "model.layers.4.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
22016, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5636096, |
|
"byteOffset": 23871488 |
|
}, |
|
{ |
|
"name": "model.layers.4.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 29507584 |
|
}, |
|
{ |
|
"name": "model.layers.4.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
12288, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3145728, |
|
"byteOffset": 29515776 |
|
} |
|
], |
|
"md5sum": "7c81666c4dea3b4c9be6400d636b2ba4" |
|
}, |
|
{ |
|
"dataPath": "params_shard_97.bin", |
|
"format": "raw-shard", |
|
"nbytes": 31989760, |
|
"records": [ |
|
{ |
|
"name": "model.layers.4.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.4.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1048576, |
|
"byteOffset": 8388608 |
|
}, |
|
{ |
|
"name": "model.layers.5.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 9437184 |
|
}, |
|
{ |
|
"name": "model.layers.5.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1376 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 22544384, |
|
"byteOffset": 9445376 |
|
} |
|
], |
|
"md5sum": "da6ee1a07ce89ea4e0681ea7eea2f60f" |
|
}, |
|
{ |
|
"dataPath": "params_shard_98.bin", |
|
"format": "raw-shard", |
|
"nbytes": 45088768, |
|
"records": [ |
|
{ |
|
"name": "model.layers.5.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
22016, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 45088768, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "938bc711ef1a3ba549b63a3de7f0bc05" |
|
}, |
|
{ |
|
"dataPath": "params_shard_99.bin", |
|
"format": "raw-shard", |
|
"nbytes": 25165824, |
|
"records": [ |
|
{ |
|
"name": "model.layers.5.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
12288, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 25165824, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "df92995ada17209397b9b757027f44e2" |
|
}, |
|
{ |
|
"dataPath": "params_shard_100.bin", |
|
"format": "raw-shard", |
|
"nbytes": 22544384, |
|
"records": [ |
|
{ |
|
"name": "model.layers.6.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1376 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 22544384, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "a5f6bef9b7c5349c2e39ac7a78aada33" |
|
}, |
|
{ |
|
"dataPath": "params_shard_101.bin", |
|
"format": "raw-shard", |
|
"nbytes": 45088768, |
|
"records": [ |
|
{ |
|
"name": "model.layers.6.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
22016, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 45088768, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "31bffb24356063e719dd7a62320f28d4" |
|
}, |
|
{ |
|
"dataPath": "params_shard_102.bin", |
|
"format": "raw-shard", |
|
"nbytes": 25165824, |
|
"records": [ |
|
{ |
|
"name": "model.layers.6.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
12288, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 25165824, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "ee599d56cd2ca1b58b09a0c2f5443785" |
|
}, |
|
{ |
|
"dataPath": "params_shard_103.bin", |
|
"format": "raw-shard", |
|
"nbytes": 32661504, |
|
"records": [ |
|
{ |
|
"name": "model.layers.5.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
344 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2818048, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.5.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
22016, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5636096, |
|
"byteOffset": 2818048 |
|
}, |
|
{ |
|
"name": "model.layers.5.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 8454144 |
|
}, |
|
{ |
|
"name": "model.layers.5.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
12288, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3145728, |
|
"byteOffset": 8462336 |
|
}, |
|
{ |
|
"name": "model.layers.5.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 11608064 |
|
}, |
|
{ |
|
"name": "model.layers.5.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1048576, |
|
"byteOffset": 19996672 |
|
}, |
|
{ |
|
"name": "model.layers.6.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 21045248 |
|
}, |
|
{ |
|
"name": "model.layers.6.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
344 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2818048, |
|
"byteOffset": 21053440 |
|
}, |
|
{ |
|
"name": "model.layers.6.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
22016, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5636096, |
|
"byteOffset": 23871488 |
|
}, |
|
{ |
|
"name": "model.layers.6.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 29507584 |
|
}, |
|
{ |
|
"name": "model.layers.6.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
12288, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3145728, |
|
"byteOffset": 29515776 |
|
} |
|
], |
|
"md5sum": "0706dce4960df51157dc6e788a3e8ba5" |
|
}, |
|
{ |
|
"dataPath": "params_shard_104.bin", |
|
"format": "raw-shard", |
|
"nbytes": 31989760, |
|
"records": [ |
|
{ |
|
"name": "model.layers.6.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.6.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1048576, |
|
"byteOffset": 8388608 |
|
}, |
|
{ |
|
"name": "model.layers.7.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 9437184 |
|
}, |
|
{ |
|
"name": "model.layers.7.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1376 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 22544384, |
|
"byteOffset": 9445376 |
|
} |
|
], |
|
"md5sum": "f4138808fb4761e244381936d246a188" |
|
}, |
|
{ |
|
"dataPath": "params_shard_105.bin", |
|
"format": "raw-shard", |
|
"nbytes": 45088768, |
|
"records": [ |
|
{ |
|
"name": "model.layers.7.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
22016, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 45088768, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "0daf10cb6b4a2d238f5d073a926e85a5" |
|
}, |
|
{ |
|
"dataPath": "params_shard_106.bin", |
|
"format": "raw-shard", |
|
"nbytes": 25165824, |
|
"records": [ |
|
{ |
|
"name": "model.layers.7.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
12288, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 25165824, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "d8a03ea6e14a686af36f02c3dd9dfbcd" |
|
}, |
|
{ |
|
"dataPath": "params_shard_107.bin", |
|
"format": "raw-shard", |
|
"nbytes": 22544384, |
|
"records": [ |
|
{ |
|
"name": "model.layers.8.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1376 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 22544384, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "8c16c14753d159d898f115f0afcefd7f" |
|
}, |
|
{ |
|
"dataPath": "params_shard_108.bin", |
|
"format": "raw-shard", |
|
"nbytes": 45088768, |
|
"records": [ |
|
{ |
|
"name": "model.layers.8.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
22016, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 45088768, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "ce9af16fec25346a3acfef7cfe49ab00" |
|
}, |
|
{ |
|
"dataPath": "params_shard_109.bin", |
|
"format": "raw-shard", |
|
"nbytes": 25165824, |
|
"records": [ |
|
{ |
|
"name": "model.layers.8.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
12288, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 25165824, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "7226e901578632708a82530e3c5b8240" |
|
}, |
|
{ |
|
"dataPath": "params_shard_110.bin", |
|
"format": "raw-shard", |
|
"nbytes": 32661504, |
|
"records": [ |
|
{ |
|
"name": "model.layers.7.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
344 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2818048, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.7.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
22016, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5636096, |
|
"byteOffset": 2818048 |
|
}, |
|
{ |
|
"name": "model.layers.7.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 8454144 |
|
}, |
|
{ |
|
"name": "model.layers.7.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
12288, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3145728, |
|
"byteOffset": 8462336 |
|
}, |
|
{ |
|
"name": "model.layers.7.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 11608064 |
|
}, |
|
{ |
|
"name": "model.layers.7.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1048576, |
|
"byteOffset": 19996672 |
|
}, |
|
{ |
|
"name": "model.layers.8.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 21045248 |
|
}, |
|
{ |
|
"name": "model.layers.8.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
344 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2818048, |
|
"byteOffset": 21053440 |
|
}, |
|
{ |
|
"name": "model.layers.8.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
22016, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5636096, |
|
"byteOffset": 23871488 |
|
}, |
|
{ |
|
"name": "model.layers.8.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 29507584 |
|
}, |
|
{ |
|
"name": "model.layers.8.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
12288, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3145728, |
|
"byteOffset": 29515776 |
|
} |
|
], |
|
"md5sum": "0e6602d959830665d0ec0c183a6b9b9f" |
|
}, |
|
{ |
|
"dataPath": "params_shard_111.bin", |
|
"format": "raw-shard", |
|
"nbytes": 31989760, |
|
"records": [ |
|
{ |
|
"name": "model.layers.8.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.8.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1048576, |
|
"byteOffset": 8388608 |
|
}, |
|
{ |
|
"name": "model.layers.9.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 9437184 |
|
}, |
|
{ |
|
"name": "model.layers.9.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1376 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 22544384, |
|
"byteOffset": 9445376 |
|
} |
|
], |
|
"md5sum": "4743a20edf03a185b4dc1a620a69e629" |
|
}, |
|
{ |
|
"dataPath": "params_shard_112.bin", |
|
"format": "raw-shard", |
|
"nbytes": 45088768, |
|
"records": [ |
|
{ |
|
"name": "model.layers.9.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
22016, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 45088768, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "2966412e577043b579e06ab124fb5ac2" |
|
}, |
|
{ |
|
"dataPath": "params_shard_113.bin", |
|
"format": "raw-shard", |
|
"nbytes": 25165824, |
|
"records": [ |
|
{ |
|
"name": "model.layers.9.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
12288, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 25165824, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "b2cbb3fcdad45dfbfc42b6f2d22742f4" |
|
}, |
|
{ |
|
"dataPath": "params_shard_114.bin", |
|
"format": "raw-shard", |
|
"nbytes": 21045248, |
|
"records": [ |
|
{ |
|
"name": "model.layers.9.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
344 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2818048, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.9.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
22016, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5636096, |
|
"byteOffset": 2818048 |
|
}, |
|
{ |
|
"name": "model.layers.9.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 8454144 |
|
}, |
|
{ |
|
"name": "model.layers.9.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
12288, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3145728, |
|
"byteOffset": 8462336 |
|
}, |
|
{ |
|
"name": "model.layers.9.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 11608064 |
|
}, |
|
{ |
|
"name": "model.layers.9.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
128 |
|
], |
|
"dtype": "float32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1048576, |
|
"byteOffset": 19996672 |
|
} |
|
], |
|
"md5sum": "3b0a3035616078d1afd46a94ecb157b9" |
|
} |
|
] |
|
} |