|
{ |
|
"metadata": { |
|
"ParamSize": 325, |
|
"ParamBytes": 3790815232.0, |
|
"BitsPerParam": 4.5004543650347415 |
|
}, |
|
"records": [ |
|
{ |
|
"dataPath": "params_shard_0.bin", |
|
"format": "raw-shard", |
|
"nbytes": 65568768, |
|
"records": [ |
|
{ |
|
"name": "lm_head.q_weight", |
|
"shape": [ |
|
32016, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 65568768, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "3be751278010110b55ac12c2e48e5d11" |
|
}, |
|
{ |
|
"dataPath": "params_shard_1.bin", |
|
"format": "raw-shard", |
|
"nbytes": 30748672, |
|
"records": [ |
|
{ |
|
"name": "lm_head.q_scale", |
|
"shape": [ |
|
32016, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8196096, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.23.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 8196096 |
|
}, |
|
{ |
|
"name": "model.layers.23.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1376 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 22544384, |
|
"byteOffset": 8204288 |
|
} |
|
], |
|
"md5sum": "8b10644cdd4bcc9c6a789726bc771bf6" |
|
}, |
|
{ |
|
"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": "9bdcc025d3ecf72cd710f947e92378c9" |
|
}, |
|
{ |
|
"dataPath": "params_shard_3.bin", |
|
"format": "raw-shard", |
|
"nbytes": 28196864, |
|
"records": [ |
|
{ |
|
"name": "model.layers.23.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
344 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2818048, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.23.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 2818048 |
|
}, |
|
{ |
|
"name": "model.layers.24.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 2826240 |
|
}, |
|
{ |
|
"name": "model.layers.24.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1376 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 22544384, |
|
"byteOffset": 2834432 |
|
}, |
|
{ |
|
"name": "model.layers.24.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
344 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2818048, |
|
"byteOffset": 25378816 |
|
} |
|
], |
|
"md5sum": "9b919dc660aaabd936377d29bb371e0b" |
|
}, |
|
{ |
|
"dataPath": "params_shard_4.bin", |
|
"format": "raw-shard", |
|
"nbytes": 30810112, |
|
"records": [ |
|
{ |
|
"name": "model.layers.24.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
22016, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5636096, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.24.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 5636096 |
|
}, |
|
{ |
|
"name": "model.layers.24.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
12288, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 25165824, |
|
"byteOffset": 5644288 |
|
} |
|
], |
|
"md5sum": "be6f50db232157d7e35b3c61e50f925f" |
|
}, |
|
{ |
|
"dataPath": "params_shard_5.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": "08752909dcacc1da352ecf5c0c338f6a" |
|
}, |
|
{ |
|
"dataPath": "params_shard_6.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": "83e32925e4839e584e46f91ff3a94222" |
|
}, |
|
{ |
|
"dataPath": "params_shard_7.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": "76e50db7606ebe7f0cd02fb21c9e2ff5" |
|
}, |
|
{ |
|
"dataPath": "params_shard_8.bin", |
|
"format": "raw-shard", |
|
"nbytes": 32587776, |
|
"records": [ |
|
{ |
|
"name": "model.layers.24.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
12288, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3145728, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.24.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 3145728 |
|
}, |
|
{ |
|
"name": "model.layers.24.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1048576, |
|
"byteOffset": 11534336 |
|
}, |
|
{ |
|
"name": "model.layers.25.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 12582912 |
|
}, |
|
{ |
|
"name": "model.layers.25.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
344 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2818048, |
|
"byteOffset": 12591104 |
|
}, |
|
{ |
|
"name": "model.layers.25.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
22016, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5636096, |
|
"byteOffset": 15409152 |
|
}, |
|
{ |
|
"name": "model.layers.25.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 21045248 |
|
}, |
|
{ |
|
"name": "model.layers.25.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
12288, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3145728, |
|
"byteOffset": 21053440 |
|
}, |
|
{ |
|
"name": "model.layers.25.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 24199168 |
|
} |
|
], |
|
"md5sum": "7782999b3e8c5cc7dc73e0255fc5dde3" |
|
}, |
|
{ |
|
"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": "29059613f7a75aa4e736a0d28b2b9081" |
|
}, |
|
{ |
|
"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": "0f0975a950dbaf64607444f64d00fa9e" |
|
}, |
|
{ |
|
"dataPath": "params_shard_11.bin", |
|
"format": "raw-shard", |
|
"nbytes": 32063488, |
|
"records": [ |
|
{ |
|
"name": "model.layers.25.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1048576, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.26.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 1048576 |
|
}, |
|
{ |
|
"name": "model.layers.26.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1376 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 22544384, |
|
"byteOffset": 1056768 |
|
}, |
|
{ |
|
"name": "model.layers.26.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
344 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2818048, |
|
"byteOffset": 23601152 |
|
}, |
|
{ |
|
"name": "model.layers.26.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
22016, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5636096, |
|
"byteOffset": 26419200 |
|
}, |
|
{ |
|
"name": "model.layers.26.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 32055296 |
|
} |
|
], |
|
"md5sum": "42708ea152c74464676d9e261338bab3" |
|
}, |
|
{ |
|
"dataPath": "params_shard_12.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": "e03f6eaf67f16cb4b92270abdda429b3" |
|
}, |
|
{ |
|
"dataPath": "params_shard_13.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": "8b79cac590be185145a4d871d51135f7" |
|
}, |
|
{ |
|
"dataPath": "params_shard_14.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": "03f4e1ad682949dd0db6e87b3307071c" |
|
}, |
|
{ |
|
"dataPath": "params_shard_15.bin", |
|
"format": "raw-shard", |
|
"nbytes": 32587776, |
|
"records": [ |
|
{ |
|
"name": "model.layers.26.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
12288, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3145728, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.26.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 3145728 |
|
}, |
|
{ |
|
"name": "model.layers.26.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1048576, |
|
"byteOffset": 11534336 |
|
}, |
|
{ |
|
"name": "model.layers.27.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 12582912 |
|
}, |
|
{ |
|
"name": "model.layers.27.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
344 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2818048, |
|
"byteOffset": 12591104 |
|
}, |
|
{ |
|
"name": "model.layers.27.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
22016, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5636096, |
|
"byteOffset": 15409152 |
|
}, |
|
{ |
|
"name": "model.layers.27.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 21045248 |
|
}, |
|
{ |
|
"name": "model.layers.27.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
12288, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3145728, |
|
"byteOffset": 21053440 |
|
}, |
|
{ |
|
"name": "model.layers.27.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 24199168 |
|
} |
|
], |
|
"md5sum": "051aff70585d18e2e79ae02d49042512" |
|
}, |
|
{ |
|
"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": "1be5f1cde0bc61eb78af695aae2bf229" |
|
}, |
|
{ |
|
"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": "8ec21a990f127d1520312020953c0959" |
|
}, |
|
{ |
|
"dataPath": "params_shard_18.bin", |
|
"format": "raw-shard", |
|
"nbytes": 32063488, |
|
"records": [ |
|
{ |
|
"name": "model.layers.27.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1048576, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.28.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 1048576 |
|
}, |
|
{ |
|
"name": "model.layers.28.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1376 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 22544384, |
|
"byteOffset": 1056768 |
|
}, |
|
{ |
|
"name": "model.layers.28.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
344 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2818048, |
|
"byteOffset": 23601152 |
|
}, |
|
{ |
|
"name": "model.layers.28.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
22016, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5636096, |
|
"byteOffset": 26419200 |
|
}, |
|
{ |
|
"name": "model.layers.28.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 32055296 |
|
} |
|
], |
|
"md5sum": "77676cc78908325bb3341aeb7374353b" |
|
}, |
|
{ |
|
"dataPath": "params_shard_19.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": "e76942aa9d0f4c57567fc91021afc905" |
|
}, |
|
{ |
|
"dataPath": "params_shard_20.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": "3edf88a1179a4bfec0369768f5cd06e6" |
|
}, |
|
{ |
|
"dataPath": "params_shard_21.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": "16c99faf90fca435463423e672579a36" |
|
}, |
|
{ |
|
"dataPath": "params_shard_22.bin", |
|
"format": "raw-shard", |
|
"nbytes": 32587776, |
|
"records": [ |
|
{ |
|
"name": "model.layers.28.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
12288, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3145728, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.28.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 3145728 |
|
}, |
|
{ |
|
"name": "model.layers.28.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1048576, |
|
"byteOffset": 11534336 |
|
}, |
|
{ |
|
"name": "model.layers.29.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 12582912 |
|
}, |
|
{ |
|
"name": "model.layers.29.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
344 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2818048, |
|
"byteOffset": 12591104 |
|
}, |
|
{ |
|
"name": "model.layers.29.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
22016, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5636096, |
|
"byteOffset": 15409152 |
|
}, |
|
{ |
|
"name": "model.layers.29.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 21045248 |
|
}, |
|
{ |
|
"name": "model.layers.29.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
12288, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3145728, |
|
"byteOffset": 21053440 |
|
}, |
|
{ |
|
"name": "model.layers.29.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 24199168 |
|
} |
|
], |
|
"md5sum": "96b93e26d5c4e94ad71a9c74974d9a75" |
|
}, |
|
{ |
|
"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": "dcc59376997b637d40addbcc0abfd4fe" |
|
}, |
|
{ |
|
"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": "5f79a3fd75ba20489dc00935a4ce2901" |
|
}, |
|
{ |
|
"dataPath": "params_shard_25.bin", |
|
"format": "raw-shard", |
|
"nbytes": 32063488, |
|
"records": [ |
|
{ |
|
"name": "model.layers.29.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1048576, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.30.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 1048576 |
|
}, |
|
{ |
|
"name": "model.layers.30.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1376 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 22544384, |
|
"byteOffset": 1056768 |
|
}, |
|
{ |
|
"name": "model.layers.30.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
344 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2818048, |
|
"byteOffset": 23601152 |
|
}, |
|
{ |
|
"name": "model.layers.30.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
22016, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5636096, |
|
"byteOffset": 26419200 |
|
}, |
|
{ |
|
"name": "model.layers.30.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 32055296 |
|
} |
|
], |
|
"md5sum": "7078835d03c765f3d995a6aaf6c84a20" |
|
}, |
|
{ |
|
"dataPath": "params_shard_26.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": "8d3185ca0c2f9902ba49835960500a9a" |
|
}, |
|
{ |
|
"dataPath": "params_shard_27.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": "0bcfeb7ad380cc5e1336d0a95213a9bf" |
|
}, |
|
{ |
|
"dataPath": "params_shard_28.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": "247578b4c5db4e76ef7294c1124a810a" |
|
}, |
|
{ |
|
"dataPath": "params_shard_29.bin", |
|
"format": "raw-shard", |
|
"nbytes": 32587776, |
|
"records": [ |
|
{ |
|
"name": "model.layers.30.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
12288, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3145728, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.30.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 3145728 |
|
}, |
|
{ |
|
"name": "model.layers.30.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1048576, |
|
"byteOffset": 11534336 |
|
}, |
|
{ |
|
"name": "model.layers.31.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 12582912 |
|
}, |
|
{ |
|
"name": "model.layers.31.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
344 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2818048, |
|
"byteOffset": 12591104 |
|
}, |
|
{ |
|
"name": "model.layers.31.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
22016, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5636096, |
|
"byteOffset": 15409152 |
|
}, |
|
{ |
|
"name": "model.layers.31.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 21045248 |
|
}, |
|
{ |
|
"name": "model.layers.31.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
12288, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3145728, |
|
"byteOffset": 21053440 |
|
}, |
|
{ |
|
"name": "model.layers.31.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 24199168 |
|
} |
|
], |
|
"md5sum": "cd9765105be1ced5206d7e19c242e461" |
|
}, |
|
{ |
|
"dataPath": "params_shard_30.bin", |
|
"format": "raw-shard", |
|
"nbytes": 65568768, |
|
"records": [ |
|
{ |
|
"name": "model.embed_tokens.q_weight", |
|
"shape": [ |
|
32016, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 65568768, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "433f448d37ca83e29df6e40b1f2d871e" |
|
}, |
|
{ |
|
"dataPath": "params_shard_31.bin", |
|
"format": "raw-shard", |
|
"nbytes": 31805440, |
|
"records": [ |
|
{ |
|
"name": "model.layers.31.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1048576, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.norm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 1048576 |
|
}, |
|
{ |
|
"name": "model.embed_tokens.q_scale", |
|
"shape": [ |
|
32016, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8196096, |
|
"byteOffset": 1056768 |
|
}, |
|
{ |
|
"name": "model.layers.0.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 9252864 |
|
}, |
|
{ |
|
"name": "model.layers.0.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1376 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 22544384, |
|
"byteOffset": 9261056 |
|
} |
|
], |
|
"md5sum": "08dbf81e250bcefe51774fff6f209cf0" |
|
}, |
|
{ |
|
"dataPath": "params_shard_32.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": "bde7624161b76a3f83f6e453133baad1" |
|
}, |
|
{ |
|
"dataPath": "params_shard_33.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": "67732b53d68d4f8a1e2b0a52ef4c6b9b" |
|
}, |
|
{ |
|
"dataPath": "params_shard_34.bin", |
|
"format": "raw-shard", |
|
"nbytes": 22544384, |
|
"records": [ |
|
{ |
|
"name": "model.layers.1.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1376 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 22544384, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "643d0fa528c68f56a0374b4fcec65167" |
|
}, |
|
{ |
|
"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": "8162b0a6be14c153e4e728a2355555e8" |
|
}, |
|
{ |
|
"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": "83bffdd9f8c57f68bc103775c4635219" |
|
}, |
|
{ |
|
"dataPath": "params_shard_37.bin", |
|
"format": "raw-shard", |
|
"nbytes": 32661504, |
|
"records": [ |
|
{ |
|
"name": "model.layers.0.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
344 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2818048, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.0.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
22016, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5636096, |
|
"byteOffset": 2818048 |
|
}, |
|
{ |
|
"name": "model.layers.0.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 8454144 |
|
}, |
|
{ |
|
"name": "model.layers.0.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
12288, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3145728, |
|
"byteOffset": 8462336 |
|
}, |
|
{ |
|
"name": "model.layers.0.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 11608064 |
|
}, |
|
{ |
|
"name": "model.layers.0.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1048576, |
|
"byteOffset": 19996672 |
|
}, |
|
{ |
|
"name": "model.layers.1.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 21045248 |
|
}, |
|
{ |
|
"name": "model.layers.1.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
344 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2818048, |
|
"byteOffset": 21053440 |
|
}, |
|
{ |
|
"name": "model.layers.1.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
22016, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5636096, |
|
"byteOffset": 23871488 |
|
}, |
|
{ |
|
"name": "model.layers.1.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 29507584 |
|
}, |
|
{ |
|
"name": "model.layers.1.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
12288, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3145728, |
|
"byteOffset": 29515776 |
|
} |
|
], |
|
"md5sum": "cb1e1a72a4d00606e5413a645691faba" |
|
}, |
|
{ |
|
"dataPath": "params_shard_38.bin", |
|
"format": "raw-shard", |
|
"nbytes": 31989760, |
|
"records": [ |
|
{ |
|
"name": "model.layers.1.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.1.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1048576, |
|
"byteOffset": 8388608 |
|
}, |
|
{ |
|
"name": "model.layers.10.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 9437184 |
|
}, |
|
{ |
|
"name": "model.layers.10.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1376 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 22544384, |
|
"byteOffset": 9445376 |
|
} |
|
], |
|
"md5sum": "150acfc034b997a5cf829b483cfeab1c" |
|
}, |
|
{ |
|
"dataPath": "params_shard_39.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": "60ee8ced21b7ec2fe078952e4d651f54" |
|
}, |
|
{ |
|
"dataPath": "params_shard_40.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": "a5f3c472674fda105601ed66353cf3a1" |
|
}, |
|
{ |
|
"dataPath": "params_shard_41.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": "1d92dc044b6e45b66229db9526a90783" |
|
}, |
|
{ |
|
"dataPath": "params_shard_42.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": "e08df3bf77e45d374d43fb3037c509a9" |
|
}, |
|
{ |
|
"dataPath": "params_shard_43.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29827072, |
|
"records": [ |
|
{ |
|
"name": "model.layers.10.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
344 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2818048, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.10.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
22016, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5636096, |
|
"byteOffset": 2818048 |
|
}, |
|
{ |
|
"name": "model.layers.10.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 8454144 |
|
}, |
|
{ |
|
"name": "model.layers.10.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
12288, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3145728, |
|
"byteOffset": 8462336 |
|
}, |
|
{ |
|
"name": "model.layers.10.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 11608064 |
|
}, |
|
{ |
|
"name": "model.layers.10.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1048576, |
|
"byteOffset": 19996672 |
|
}, |
|
{ |
|
"name": "model.layers.11.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
22016, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5636096, |
|
"byteOffset": 21045248 |
|
}, |
|
{ |
|
"name": "model.layers.11.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
12288, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3145728, |
|
"byteOffset": 26681344 |
|
} |
|
], |
|
"md5sum": "8d1064abf7cb7c00629a03365ff8b6d1" |
|
}, |
|
{ |
|
"dataPath": "params_shard_44.bin", |
|
"format": "raw-shard", |
|
"nbytes": 31989760, |
|
"records": [ |
|
{ |
|
"name": "model.layers.11.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.11.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1048576, |
|
"byteOffset": 8388608 |
|
}, |
|
{ |
|
"name": "model.layers.2.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 9437184 |
|
}, |
|
{ |
|
"name": "model.layers.2.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1376 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 22544384, |
|
"byteOffset": 9445376 |
|
} |
|
], |
|
"md5sum": "3ac09c7b0d2d9ba708ce6c9a6faa6bc7" |
|
}, |
|
{ |
|
"dataPath": "params_shard_45.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": "59b2f1d329b35dde87dae9f6dd09e9bf" |
|
}, |
|
{ |
|
"dataPath": "params_shard_46.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": "6871f768e999c7b109d525031b25f9b9" |
|
}, |
|
{ |
|
"dataPath": "params_shard_47.bin", |
|
"format": "raw-shard", |
|
"nbytes": 22544384, |
|
"records": [ |
|
{ |
|
"name": "model.layers.3.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1376 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 22544384, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "cccff3c5c7c0be586898240b1bcd0864" |
|
}, |
|
{ |
|
"dataPath": "params_shard_48.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": "37951e2ab9a6b1700acf8f4db70cc714" |
|
}, |
|
{ |
|
"dataPath": "params_shard_49.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": "0113ec13fa90fdfd742994386174116b" |
|
}, |
|
{ |
|
"dataPath": "params_shard_50.bin", |
|
"format": "raw-shard", |
|
"nbytes": 32661504, |
|
"records": [ |
|
{ |
|
"name": "model.layers.2.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
344 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2818048, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.2.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
22016, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5636096, |
|
"byteOffset": 2818048 |
|
}, |
|
{ |
|
"name": "model.layers.2.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 8454144 |
|
}, |
|
{ |
|
"name": "model.layers.2.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
12288, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3145728, |
|
"byteOffset": 8462336 |
|
}, |
|
{ |
|
"name": "model.layers.2.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 11608064 |
|
}, |
|
{ |
|
"name": "model.layers.2.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1048576, |
|
"byteOffset": 19996672 |
|
}, |
|
{ |
|
"name": "model.layers.3.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 21045248 |
|
}, |
|
{ |
|
"name": "model.layers.3.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
344 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2818048, |
|
"byteOffset": 21053440 |
|
}, |
|
{ |
|
"name": "model.layers.3.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
22016, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5636096, |
|
"byteOffset": 23871488 |
|
}, |
|
{ |
|
"name": "model.layers.3.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 29507584 |
|
}, |
|
{ |
|
"name": "model.layers.3.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
12288, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3145728, |
|
"byteOffset": 29515776 |
|
} |
|
], |
|
"md5sum": "ab87074077d4b9cc401ae646eb6bf2f4" |
|
}, |
|
{ |
|
"dataPath": "params_shard_51.bin", |
|
"format": "raw-shard", |
|
"nbytes": 31989760, |
|
"records": [ |
|
{ |
|
"name": "model.layers.3.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.3.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1048576, |
|
"byteOffset": 8388608 |
|
}, |
|
{ |
|
"name": "model.layers.4.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 9437184 |
|
}, |
|
{ |
|
"name": "model.layers.4.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1376 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 22544384, |
|
"byteOffset": 9445376 |
|
} |
|
], |
|
"md5sum": "30824909697d00d147c0420c18146d5a" |
|
}, |
|
{ |
|
"dataPath": "params_shard_52.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": "29b80655449a8c16c569667aedde189d" |
|
}, |
|
{ |
|
"dataPath": "params_shard_53.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": "f135ef46889467f10d8d07899263a61b" |
|
}, |
|
{ |
|
"dataPath": "params_shard_54.bin", |
|
"format": "raw-shard", |
|
"nbytes": 22544384, |
|
"records": [ |
|
{ |
|
"name": "model.layers.5.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1376 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 22544384, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "7714b21759c2d012980529523eb6e3ad" |
|
}, |
|
{ |
|
"dataPath": "params_shard_55.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": "f70b51a2e7035527c167e867b2997616" |
|
}, |
|
{ |
|
"dataPath": "params_shard_56.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": "e6186ec8bb6c1c8c238e1383332264e9" |
|
}, |
|
{ |
|
"dataPath": "params_shard_57.bin", |
|
"format": "raw-shard", |
|
"nbytes": 32661504, |
|
"records": [ |
|
{ |
|
"name": "model.layers.4.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
344 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2818048, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.4.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
22016, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5636096, |
|
"byteOffset": 2818048 |
|
}, |
|
{ |
|
"name": "model.layers.4.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 8454144 |
|
}, |
|
{ |
|
"name": "model.layers.4.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
12288, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3145728, |
|
"byteOffset": 8462336 |
|
}, |
|
{ |
|
"name": "model.layers.4.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 11608064 |
|
}, |
|
{ |
|
"name": "model.layers.4.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1048576, |
|
"byteOffset": 19996672 |
|
}, |
|
{ |
|
"name": "model.layers.5.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 21045248 |
|
}, |
|
{ |
|
"name": "model.layers.5.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
344 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2818048, |
|
"byteOffset": 21053440 |
|
}, |
|
{ |
|
"name": "model.layers.5.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
22016, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5636096, |
|
"byteOffset": 23871488 |
|
}, |
|
{ |
|
"name": "model.layers.5.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 29507584 |
|
}, |
|
{ |
|
"name": "model.layers.5.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
12288, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3145728, |
|
"byteOffset": 29515776 |
|
} |
|
], |
|
"md5sum": "7e9c8fd20b29bd8485e2b46fd5eead3c" |
|
}, |
|
{ |
|
"dataPath": "params_shard_58.bin", |
|
"format": "raw-shard", |
|
"nbytes": 31989760, |
|
"records": [ |
|
{ |
|
"name": "model.layers.5.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.5.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1048576, |
|
"byteOffset": 8388608 |
|
}, |
|
{ |
|
"name": "model.layers.6.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 9437184 |
|
}, |
|
{ |
|
"name": "model.layers.6.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1376 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 22544384, |
|
"byteOffset": 9445376 |
|
} |
|
], |
|
"md5sum": "6419777ddfea52b7e92a26d6bb1f877a" |
|
}, |
|
{ |
|
"dataPath": "params_shard_59.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": "5961841d137e58c1698ef29f0377b816" |
|
}, |
|
{ |
|
"dataPath": "params_shard_60.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": "5181edfe1e1d3bb9092bf78d98a96efc" |
|
}, |
|
{ |
|
"dataPath": "params_shard_61.bin", |
|
"format": "raw-shard", |
|
"nbytes": 22544384, |
|
"records": [ |
|
{ |
|
"name": "model.layers.7.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1376 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 22544384, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "abf58d125f584dd78692b250d3e39b22" |
|
}, |
|
{ |
|
"dataPath": "params_shard_62.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": "1458b7d58f57f64971ba0ec8c699dbe4" |
|
}, |
|
{ |
|
"dataPath": "params_shard_63.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": "0510b1e777e3b0289db1f09eed7e7fd1" |
|
}, |
|
{ |
|
"dataPath": "params_shard_64.bin", |
|
"format": "raw-shard", |
|
"nbytes": 32661504, |
|
"records": [ |
|
{ |
|
"name": "model.layers.6.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
344 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2818048, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.6.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
22016, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5636096, |
|
"byteOffset": 2818048 |
|
}, |
|
{ |
|
"name": "model.layers.6.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 8454144 |
|
}, |
|
{ |
|
"name": "model.layers.6.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
12288, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3145728, |
|
"byteOffset": 8462336 |
|
}, |
|
{ |
|
"name": "model.layers.6.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 11608064 |
|
}, |
|
{ |
|
"name": "model.layers.6.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1048576, |
|
"byteOffset": 19996672 |
|
}, |
|
{ |
|
"name": "model.layers.7.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 21045248 |
|
}, |
|
{ |
|
"name": "model.layers.7.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
344 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2818048, |
|
"byteOffset": 21053440 |
|
}, |
|
{ |
|
"name": "model.layers.7.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
22016, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5636096, |
|
"byteOffset": 23871488 |
|
}, |
|
{ |
|
"name": "model.layers.7.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 29507584 |
|
}, |
|
{ |
|
"name": "model.layers.7.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
12288, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3145728, |
|
"byteOffset": 29515776 |
|
} |
|
], |
|
"md5sum": "e76191e183a6a32dadebc87367048272" |
|
}, |
|
{ |
|
"dataPath": "params_shard_65.bin", |
|
"format": "raw-shard", |
|
"nbytes": 31989760, |
|
"records": [ |
|
{ |
|
"name": "model.layers.7.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.7.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1048576, |
|
"byteOffset": 8388608 |
|
}, |
|
{ |
|
"name": "model.layers.8.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 9437184 |
|
}, |
|
{ |
|
"name": "model.layers.8.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1376 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 22544384, |
|
"byteOffset": 9445376 |
|
} |
|
], |
|
"md5sum": "c9bc79c33d0a832d0f74e95dc0847f70" |
|
}, |
|
{ |
|
"dataPath": "params_shard_66.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": "3ac295a2e18dbe4d0f13e616e25b2bf2" |
|
}, |
|
{ |
|
"dataPath": "params_shard_67.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": "7707dacb517306b97646aa77bf1cd577" |
|
}, |
|
{ |
|
"dataPath": "params_shard_68.bin", |
|
"format": "raw-shard", |
|
"nbytes": 22544384, |
|
"records": [ |
|
{ |
|
"name": "model.layers.9.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1376 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 22544384, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "65b97719b2e69a2d0ef34c39dc3f96bb" |
|
}, |
|
{ |
|
"dataPath": "params_shard_69.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": "e9957d81dc57d5f7852c735396b05f90" |
|
}, |
|
{ |
|
"dataPath": "params_shard_70.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": "a7685eb987a502d2627bd27e7df40b7b" |
|
}, |
|
{ |
|
"dataPath": "params_shard_71.bin", |
|
"format": "raw-shard", |
|
"nbytes": 32661504, |
|
"records": [ |
|
{ |
|
"name": "model.layers.8.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
344 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2818048, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.8.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
22016, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5636096, |
|
"byteOffset": 2818048 |
|
}, |
|
{ |
|
"name": "model.layers.8.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 8454144 |
|
}, |
|
{ |
|
"name": "model.layers.8.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
12288, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3145728, |
|
"byteOffset": 8462336 |
|
}, |
|
{ |
|
"name": "model.layers.8.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 11608064 |
|
}, |
|
{ |
|
"name": "model.layers.8.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1048576, |
|
"byteOffset": 19996672 |
|
}, |
|
{ |
|
"name": "model.layers.9.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 21045248 |
|
}, |
|
{ |
|
"name": "model.layers.9.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
344 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2818048, |
|
"byteOffset": 21053440 |
|
}, |
|
{ |
|
"name": "model.layers.9.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
22016, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5636096, |
|
"byteOffset": 23871488 |
|
}, |
|
{ |
|
"name": "model.layers.9.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 29507584 |
|
}, |
|
{ |
|
"name": "model.layers.9.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
12288, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3145728, |
|
"byteOffset": 29515776 |
|
} |
|
], |
|
"md5sum": "e4bde8f0247dc75b061f6eab4797d127" |
|
}, |
|
{ |
|
"dataPath": "params_shard_72.bin", |
|
"format": "raw-shard", |
|
"nbytes": 31989760, |
|
"records": [ |
|
{ |
|
"name": "model.layers.9.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.9.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1048576, |
|
"byteOffset": 8388608 |
|
}, |
|
{ |
|
"name": "model.layers.11.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"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": "deca602a90f98aba1bfc8faf0ea9e035" |
|
}, |
|
{ |
|
"dataPath": "params_shard_73.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": "d5665cad95b1bd91b128dc4ecab5b0c4" |
|
}, |
|
{ |
|
"dataPath": "params_shard_74.bin", |
|
"format": "raw-shard", |
|
"nbytes": 28196864, |
|
"records": [ |
|
{ |
|
"name": "model.layers.11.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
344 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2818048, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.11.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 2818048 |
|
}, |
|
{ |
|
"name": "model.layers.12.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 2826240 |
|
}, |
|
{ |
|
"name": "model.layers.12.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1376 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 22544384, |
|
"byteOffset": 2834432 |
|
}, |
|
{ |
|
"name": "model.layers.12.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
344 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2818048, |
|
"byteOffset": 25378816 |
|
} |
|
], |
|
"md5sum": "498a82bcd42199732947005541520882" |
|
}, |
|
{ |
|
"dataPath": "params_shard_75.bin", |
|
"format": "raw-shard", |
|
"nbytes": 30810112, |
|
"records": [ |
|
{ |
|
"name": "model.layers.12.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
22016, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5636096, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.12.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 5636096 |
|
}, |
|
{ |
|
"name": "model.layers.12.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
12288, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 25165824, |
|
"byteOffset": 5644288 |
|
} |
|
], |
|
"md5sum": "bd1f7587542e00a40475c5e23b4b9f5d" |
|
}, |
|
{ |
|
"dataPath": "params_shard_76.bin", |
|
"format": "raw-shard", |
|
"nbytes": 22544384, |
|
"records": [ |
|
{ |
|
"name": "model.layers.13.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1376 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 22544384, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "de525dbe33190495145934c3c37e1b22" |
|
}, |
|
{ |
|
"dataPath": "params_shard_77.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": "21ea57ead272b6844cebad200206174b" |
|
}, |
|
{ |
|
"dataPath": "params_shard_78.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": "358306092b3317a361fde3979b4d3288" |
|
}, |
|
{ |
|
"dataPath": "params_shard_79.bin", |
|
"format": "raw-shard", |
|
"nbytes": 32587776, |
|
"records": [ |
|
{ |
|
"name": "model.layers.12.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
12288, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3145728, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.12.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 3145728 |
|
}, |
|
{ |
|
"name": "model.layers.12.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1048576, |
|
"byteOffset": 11534336 |
|
}, |
|
{ |
|
"name": "model.layers.13.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 12582912 |
|
}, |
|
{ |
|
"name": "model.layers.13.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
344 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2818048, |
|
"byteOffset": 12591104 |
|
}, |
|
{ |
|
"name": "model.layers.13.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
22016, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5636096, |
|
"byteOffset": 15409152 |
|
}, |
|
{ |
|
"name": "model.layers.13.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 21045248 |
|
}, |
|
{ |
|
"name": "model.layers.13.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
12288, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3145728, |
|
"byteOffset": 21053440 |
|
}, |
|
{ |
|
"name": "model.layers.13.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 24199168 |
|
} |
|
], |
|
"md5sum": "8ef66d81af5b071fc18a9b428a363f30" |
|
}, |
|
{ |
|
"dataPath": "params_shard_80.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": "3ae02c339030f0d4f1dbed23eaefb571" |
|
}, |
|
{ |
|
"dataPath": "params_shard_81.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": "1e0cff6ddecd2fb5fd29ea40b6c44092" |
|
}, |
|
{ |
|
"dataPath": "params_shard_82.bin", |
|
"format": "raw-shard", |
|
"nbytes": 32063488, |
|
"records": [ |
|
{ |
|
"name": "model.layers.13.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1048576, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.14.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 1048576 |
|
}, |
|
{ |
|
"name": "model.layers.14.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1376 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 22544384, |
|
"byteOffset": 1056768 |
|
}, |
|
{ |
|
"name": "model.layers.14.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
344 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2818048, |
|
"byteOffset": 23601152 |
|
}, |
|
{ |
|
"name": "model.layers.14.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
22016, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5636096, |
|
"byteOffset": 26419200 |
|
}, |
|
{ |
|
"name": "model.layers.14.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 32055296 |
|
} |
|
], |
|
"md5sum": "dbd9188e74e76183e68bedc2b1af7434" |
|
}, |
|
{ |
|
"dataPath": "params_shard_83.bin", |
|
"format": "raw-shard", |
|
"nbytes": 22544384, |
|
"records": [ |
|
{ |
|
"name": "model.layers.15.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1376 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 22544384, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "1635865f515b18fcebf07239a346471f" |
|
}, |
|
{ |
|
"dataPath": "params_shard_84.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": "5c35758bcb3e02a7827086626b7bdd33" |
|
}, |
|
{ |
|
"dataPath": "params_shard_85.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": "46d30e5585392f282c2379f4ef0bf1dd" |
|
}, |
|
{ |
|
"dataPath": "params_shard_86.bin", |
|
"format": "raw-shard", |
|
"nbytes": 32587776, |
|
"records": [ |
|
{ |
|
"name": "model.layers.14.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
12288, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3145728, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.14.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 3145728 |
|
}, |
|
{ |
|
"name": "model.layers.14.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1048576, |
|
"byteOffset": 11534336 |
|
}, |
|
{ |
|
"name": "model.layers.15.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 12582912 |
|
}, |
|
{ |
|
"name": "model.layers.15.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
344 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2818048, |
|
"byteOffset": 12591104 |
|
}, |
|
{ |
|
"name": "model.layers.15.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
22016, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5636096, |
|
"byteOffset": 15409152 |
|
}, |
|
{ |
|
"name": "model.layers.15.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 21045248 |
|
}, |
|
{ |
|
"name": "model.layers.15.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
12288, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3145728, |
|
"byteOffset": 21053440 |
|
}, |
|
{ |
|
"name": "model.layers.15.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 24199168 |
|
} |
|
], |
|
"md5sum": "5d8c30b5cb142139059aea68d3821b3f" |
|
}, |
|
{ |
|
"dataPath": "params_shard_87.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": "68c81ceb689d649889a38147047a3b35" |
|
}, |
|
{ |
|
"dataPath": "params_shard_88.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": "26d4b42858378192175bc5605444cdcf" |
|
}, |
|
{ |
|
"dataPath": "params_shard_89.bin", |
|
"format": "raw-shard", |
|
"nbytes": 32063488, |
|
"records": [ |
|
{ |
|
"name": "model.layers.15.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1048576, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.16.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 1048576 |
|
}, |
|
{ |
|
"name": "model.layers.16.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1376 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 22544384, |
|
"byteOffset": 1056768 |
|
}, |
|
{ |
|
"name": "model.layers.16.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
344 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2818048, |
|
"byteOffset": 23601152 |
|
}, |
|
{ |
|
"name": "model.layers.16.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
22016, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5636096, |
|
"byteOffset": 26419200 |
|
}, |
|
{ |
|
"name": "model.layers.16.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 32055296 |
|
} |
|
], |
|
"md5sum": "0dc9567d0fb700d3582fa147b92bd483" |
|
}, |
|
{ |
|
"dataPath": "params_shard_90.bin", |
|
"format": "raw-shard", |
|
"nbytes": 22544384, |
|
"records": [ |
|
{ |
|
"name": "model.layers.17.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1376 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 22544384, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "7ccfc5814a9281170af138d2df41578b" |
|
}, |
|
{ |
|
"dataPath": "params_shard_91.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": "63f6c75eb9b4b8de35fa40fd5e398afb" |
|
}, |
|
{ |
|
"dataPath": "params_shard_92.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": "92eda6cc982d35ffbfdf7cb73c782706" |
|
}, |
|
{ |
|
"dataPath": "params_shard_93.bin", |
|
"format": "raw-shard", |
|
"nbytes": 32587776, |
|
"records": [ |
|
{ |
|
"name": "model.layers.16.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
12288, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3145728, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.16.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 3145728 |
|
}, |
|
{ |
|
"name": "model.layers.16.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1048576, |
|
"byteOffset": 11534336 |
|
}, |
|
{ |
|
"name": "model.layers.17.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 12582912 |
|
}, |
|
{ |
|
"name": "model.layers.17.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
344 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2818048, |
|
"byteOffset": 12591104 |
|
}, |
|
{ |
|
"name": "model.layers.17.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
22016, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5636096, |
|
"byteOffset": 15409152 |
|
}, |
|
{ |
|
"name": "model.layers.17.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 21045248 |
|
}, |
|
{ |
|
"name": "model.layers.17.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
12288, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3145728, |
|
"byteOffset": 21053440 |
|
}, |
|
{ |
|
"name": "model.layers.17.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 24199168 |
|
} |
|
], |
|
"md5sum": "4e0e8a2fec3d85a885d3332b40b9cfe5" |
|
}, |
|
{ |
|
"dataPath": "params_shard_94.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": "c4e169ce90e104188e0da620b37b81c8" |
|
}, |
|
{ |
|
"dataPath": "params_shard_95.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": "81a6d6994039c6d00d4f06345c45cd4d" |
|
}, |
|
{ |
|
"dataPath": "params_shard_96.bin", |
|
"format": "raw-shard", |
|
"nbytes": 32063488, |
|
"records": [ |
|
{ |
|
"name": "model.layers.17.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1048576, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.18.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 1048576 |
|
}, |
|
{ |
|
"name": "model.layers.18.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1376 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 22544384, |
|
"byteOffset": 1056768 |
|
}, |
|
{ |
|
"name": "model.layers.18.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
344 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2818048, |
|
"byteOffset": 23601152 |
|
}, |
|
{ |
|
"name": "model.layers.18.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
22016, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5636096, |
|
"byteOffset": 26419200 |
|
}, |
|
{ |
|
"name": "model.layers.18.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 32055296 |
|
} |
|
], |
|
"md5sum": "21b285f78a386d3fef94bfa5bb18d828" |
|
}, |
|
{ |
|
"dataPath": "params_shard_97.bin", |
|
"format": "raw-shard", |
|
"nbytes": 22544384, |
|
"records": [ |
|
{ |
|
"name": "model.layers.19.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1376 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 22544384, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "df6aed5f74dbc118cafd2a121c3273d3" |
|
}, |
|
{ |
|
"dataPath": "params_shard_98.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": "e02508f82b77fe9d1c3f5f9b5757b50a" |
|
}, |
|
{ |
|
"dataPath": "params_shard_99.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": "7c89d3526d03f7eb4f3662af03d6c6ce" |
|
}, |
|
{ |
|
"dataPath": "params_shard_100.bin", |
|
"format": "raw-shard", |
|
"nbytes": 32587776, |
|
"records": [ |
|
{ |
|
"name": "model.layers.18.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
12288, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3145728, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.18.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 3145728 |
|
}, |
|
{ |
|
"name": "model.layers.18.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1048576, |
|
"byteOffset": 11534336 |
|
}, |
|
{ |
|
"name": "model.layers.19.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 12582912 |
|
}, |
|
{ |
|
"name": "model.layers.19.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
344 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2818048, |
|
"byteOffset": 12591104 |
|
}, |
|
{ |
|
"name": "model.layers.19.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
22016, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5636096, |
|
"byteOffset": 15409152 |
|
}, |
|
{ |
|
"name": "model.layers.19.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 21045248 |
|
}, |
|
{ |
|
"name": "model.layers.19.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
12288, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3145728, |
|
"byteOffset": 21053440 |
|
}, |
|
{ |
|
"name": "model.layers.19.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 24199168 |
|
} |
|
], |
|
"md5sum": "d8c8ad4a676a783a3f0c22fce7b0acd6" |
|
}, |
|
{ |
|
"dataPath": "params_shard_101.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": "49f60e734d8cd0107a8a16a87962a0a3" |
|
}, |
|
{ |
|
"dataPath": "params_shard_102.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": "8f4be813c96075351a59b47b03d6f574" |
|
}, |
|
{ |
|
"dataPath": "params_shard_103.bin", |
|
"format": "raw-shard", |
|
"nbytes": 32063488, |
|
"records": [ |
|
{ |
|
"name": "model.layers.19.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1048576, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.20.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 1048576 |
|
}, |
|
{ |
|
"name": "model.layers.20.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1376 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 22544384, |
|
"byteOffset": 1056768 |
|
}, |
|
{ |
|
"name": "model.layers.20.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
344 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2818048, |
|
"byteOffset": 23601152 |
|
}, |
|
{ |
|
"name": "model.layers.20.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
22016, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5636096, |
|
"byteOffset": 26419200 |
|
}, |
|
{ |
|
"name": "model.layers.20.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 32055296 |
|
} |
|
], |
|
"md5sum": "93d24cf677ccb1ea9fe9c190048fb508" |
|
}, |
|
{ |
|
"dataPath": "params_shard_104.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": "c5d4c39b5275d0c1908aba34bf32760f" |
|
}, |
|
{ |
|
"dataPath": "params_shard_105.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": "3b663b07d57eaba90d714513ba080d09" |
|
}, |
|
{ |
|
"dataPath": "params_shard_106.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": "c69e343f84b10d3e2c2f8972120623c9" |
|
}, |
|
{ |
|
"dataPath": "params_shard_107.bin", |
|
"format": "raw-shard", |
|
"nbytes": 32587776, |
|
"records": [ |
|
{ |
|
"name": "model.layers.20.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
12288, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3145728, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.20.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 3145728 |
|
}, |
|
{ |
|
"name": "model.layers.20.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1048576, |
|
"byteOffset": 11534336 |
|
}, |
|
{ |
|
"name": "model.layers.21.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 12582912 |
|
}, |
|
{ |
|
"name": "model.layers.21.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
344 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2818048, |
|
"byteOffset": 12591104 |
|
}, |
|
{ |
|
"name": "model.layers.21.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
22016, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5636096, |
|
"byteOffset": 15409152 |
|
}, |
|
{ |
|
"name": "model.layers.21.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 21045248 |
|
}, |
|
{ |
|
"name": "model.layers.21.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
12288, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3145728, |
|
"byteOffset": 21053440 |
|
}, |
|
{ |
|
"name": "model.layers.21.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 24199168 |
|
} |
|
], |
|
"md5sum": "1454f4c992fe8f5d09524f0126f6f042" |
|
}, |
|
{ |
|
"dataPath": "params_shard_108.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": "57341094795d91ec5d9f0e02ed9aec5b" |
|
}, |
|
{ |
|
"dataPath": "params_shard_109.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": "e4b3e6e069f90c72f9878b08bdeb8d92" |
|
}, |
|
{ |
|
"dataPath": "params_shard_110.bin", |
|
"format": "raw-shard", |
|
"nbytes": 32063488, |
|
"records": [ |
|
{ |
|
"name": "model.layers.21.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1048576, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.22.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 1048576 |
|
}, |
|
{ |
|
"name": "model.layers.22.mlp.down_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
1376 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 22544384, |
|
"byteOffset": 1056768 |
|
}, |
|
{ |
|
"name": "model.layers.22.mlp.down_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
344 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2818048, |
|
"byteOffset": 23601152 |
|
}, |
|
{ |
|
"name": "model.layers.22.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
22016, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5636096, |
|
"byteOffset": 26419200 |
|
}, |
|
{ |
|
"name": "model.layers.22.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 32055296 |
|
} |
|
], |
|
"md5sum": "cd85fc777c440aa2f51e4fc55ecbb9a8" |
|
}, |
|
{ |
|
"dataPath": "params_shard_111.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": "9a76357255b68a7def5c34b22763d770" |
|
}, |
|
{ |
|
"dataPath": "params_shard_112.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": "96129e37231c0dfbaf0e2f2e4501ab5a" |
|
}, |
|
{ |
|
"dataPath": "params_shard_113.bin", |
|
"format": "raw-shard", |
|
"nbytes": 30801920, |
|
"records": [ |
|
{ |
|
"name": "model.layers.22.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
12288, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3145728, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.22.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 3145728 |
|
}, |
|
{ |
|
"name": "model.layers.22.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1048576, |
|
"byteOffset": 11534336 |
|
}, |
|
{ |
|
"name": "model.layers.23.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
22016, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5636096, |
|
"byteOffset": 12582912 |
|
}, |
|
{ |
|
"name": "model.layers.23.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
12288, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3145728, |
|
"byteOffset": 18219008 |
|
}, |
|
{ |
|
"name": "model.layers.23.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
512 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8388608, |
|
"byteOffset": 21364736 |
|
}, |
|
{ |
|
"name": "model.layers.23.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
128 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1048576, |
|
"byteOffset": 29753344 |
|
} |
|
], |
|
"md5sum": "2501f572daea973a047e2a4914483d1c" |
|
} |
|
] |
|
} |