|
{ |
|
"metadata": { |
|
"ParamSize": 198, |
|
"ParamBytes": 3087428608.0, |
|
"BitsPerParam": 16.0 |
|
}, |
|
"records": [ |
|
{ |
|
"dataPath": "params_shard_0.bin", |
|
"format": "raw-shard", |
|
"nbytes": 466747392, |
|
"records": [ |
|
{ |
|
"name": "model.embed_tokens.weight", |
|
"shape": [ |
|
151936, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 466747392, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "4004155c68c07080f39231f289b9c9d3" |
|
}, |
|
{ |
|
"dataPath": "params_shard_1.bin", |
|
"format": "raw-shard", |
|
"nbytes": 55050240, |
|
"records": [ |
|
{ |
|
"name": "model.layers.0.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
17920, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 55050240, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "8d9c6137ab1639c5864a3e4f0d47a945" |
|
}, |
|
{ |
|
"dataPath": "params_shard_2.bin", |
|
"format": "raw-shard", |
|
"nbytes": 27535360, |
|
"records": [ |
|
{ |
|
"name": "model.layers.0.input_layernorm.weight", |
|
"shape": [ |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3072, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.0.mlp.down_proj.weight", |
|
"shape": [ |
|
1536, |
|
8960 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 27525120, |
|
"byteOffset": 3072 |
|
}, |
|
{ |
|
"name": "model.layers.0.post_attention_layernorm.weight", |
|
"shape": [ |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3072, |
|
"byteOffset": 27528192 |
|
}, |
|
{ |
|
"name": "model.layers.0.self_attn.c_attn.bias", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 27531264 |
|
} |
|
], |
|
"md5sum": "9fd8f6531c7b68276a0e21513cf4d24c" |
|
}, |
|
{ |
|
"dataPath": "params_shard_3.bin", |
|
"format": "raw-shard", |
|
"nbytes": 27525120, |
|
"records": [ |
|
{ |
|
"name": "model.layers.1.mlp.down_proj.weight", |
|
"shape": [ |
|
1536, |
|
8960 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 27525120, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "db7e25bc89a29b9b7bbf6714baa3dc24" |
|
}, |
|
{ |
|
"dataPath": "params_shard_4.bin", |
|
"format": "raw-shard", |
|
"nbytes": 55050240, |
|
"records": [ |
|
{ |
|
"name": "model.layers.1.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
17920, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 55050240, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "13cf30b3f20ad035712c136f18f7d38d" |
|
}, |
|
{ |
|
"dataPath": "params_shard_5.bin", |
|
"format": "raw-shard", |
|
"nbytes": 27525120, |
|
"records": [ |
|
{ |
|
"name": "model.layers.10.mlp.down_proj.weight", |
|
"shape": [ |
|
1536, |
|
8960 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 27525120, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "dfd4e0fba5875fd1d7db311377b87fe5" |
|
}, |
|
{ |
|
"dataPath": "params_shard_6.bin", |
|
"format": "raw-shard", |
|
"nbytes": 55050240, |
|
"records": [ |
|
{ |
|
"name": "model.layers.10.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
17920, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 55050240, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "d3c8c121be697e30d9da502d459908dc" |
|
}, |
|
{ |
|
"dataPath": "params_shard_7.bin", |
|
"format": "raw-shard", |
|
"nbytes": 27525120, |
|
"records": [ |
|
{ |
|
"name": "model.layers.11.mlp.down_proj.weight", |
|
"shape": [ |
|
1536, |
|
8960 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 27525120, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "c303778173a91bfdc754b414416c5160" |
|
}, |
|
{ |
|
"dataPath": "params_shard_8.bin", |
|
"format": "raw-shard", |
|
"nbytes": 55050240, |
|
"records": [ |
|
{ |
|
"name": "model.layers.11.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
17920, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 55050240, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "ab163c3a0afabe864dc1dfaeae1a9908" |
|
}, |
|
{ |
|
"dataPath": "params_shard_9.bin", |
|
"format": "raw-shard", |
|
"nbytes": 33060864, |
|
"records": [ |
|
{ |
|
"name": "model.layers.0.self_attn.c_attn.weight", |
|
"shape": [ |
|
2048, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6291456, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.0.self_attn.o_proj.weight", |
|
"shape": [ |
|
1536, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4718592, |
|
"byteOffset": 6291456 |
|
}, |
|
{ |
|
"name": "model.layers.1.input_layernorm.weight", |
|
"shape": [ |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3072, |
|
"byteOffset": 11010048 |
|
}, |
|
{ |
|
"name": "model.layers.1.post_attention_layernorm.weight", |
|
"shape": [ |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3072, |
|
"byteOffset": 11013120 |
|
}, |
|
{ |
|
"name": "model.layers.1.self_attn.c_attn.bias", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 11016192 |
|
}, |
|
{ |
|
"name": "model.layers.1.self_attn.c_attn.weight", |
|
"shape": [ |
|
2048, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6291456, |
|
"byteOffset": 11020288 |
|
}, |
|
{ |
|
"name": "model.layers.1.self_attn.o_proj.weight", |
|
"shape": [ |
|
1536, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4718592, |
|
"byteOffset": 17311744 |
|
}, |
|
{ |
|
"name": "model.layers.10.input_layernorm.weight", |
|
"shape": [ |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3072, |
|
"byteOffset": 22030336 |
|
}, |
|
{ |
|
"name": "model.layers.10.post_attention_layernorm.weight", |
|
"shape": [ |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3072, |
|
"byteOffset": 22033408 |
|
}, |
|
{ |
|
"name": "model.layers.10.self_attn.c_attn.bias", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 22036480 |
|
}, |
|
{ |
|
"name": "model.layers.10.self_attn.c_attn.weight", |
|
"shape": [ |
|
2048, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6291456, |
|
"byteOffset": 22040576 |
|
}, |
|
{ |
|
"name": "model.layers.10.self_attn.o_proj.weight", |
|
"shape": [ |
|
1536, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4718592, |
|
"byteOffset": 28332032 |
|
}, |
|
{ |
|
"name": "model.layers.11.input_layernorm.weight", |
|
"shape": [ |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3072, |
|
"byteOffset": 33050624 |
|
}, |
|
{ |
|
"name": "model.layers.11.post_attention_layernorm.weight", |
|
"shape": [ |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3072, |
|
"byteOffset": 33053696 |
|
}, |
|
{ |
|
"name": "model.layers.11.self_attn.c_attn.bias", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 33056768 |
|
} |
|
], |
|
"md5sum": "2e9b51ed2ac487ad15028dc401beeb7d" |
|
}, |
|
{ |
|
"dataPath": "params_shard_10.bin", |
|
"format": "raw-shard", |
|
"nbytes": 27525120, |
|
"records": [ |
|
{ |
|
"name": "model.layers.12.mlp.down_proj.weight", |
|
"shape": [ |
|
1536, |
|
8960 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 27525120, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "cc304778043000c0f442d99b072b593c" |
|
}, |
|
{ |
|
"dataPath": "params_shard_11.bin", |
|
"format": "raw-shard", |
|
"nbytes": 55050240, |
|
"records": [ |
|
{ |
|
"name": "model.layers.12.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
17920, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 55050240, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "26700b8899f4d41d92f8439f3e0f1c28" |
|
}, |
|
{ |
|
"dataPath": "params_shard_12.bin", |
|
"format": "raw-shard", |
|
"nbytes": 27525120, |
|
"records": [ |
|
{ |
|
"name": "model.layers.13.mlp.down_proj.weight", |
|
"shape": [ |
|
1536, |
|
8960 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 27525120, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "2ddac3acda693d7656dc82d1cb44a5fa" |
|
}, |
|
{ |
|
"dataPath": "params_shard_13.bin", |
|
"format": "raw-shard", |
|
"nbytes": 55050240, |
|
"records": [ |
|
{ |
|
"name": "model.layers.13.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
17920, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 55050240, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "00477d2aa802e741a31ae46a2af61519" |
|
}, |
|
{ |
|
"dataPath": "params_shard_14.bin", |
|
"format": "raw-shard", |
|
"nbytes": 27525120, |
|
"records": [ |
|
{ |
|
"name": "model.layers.14.mlp.down_proj.weight", |
|
"shape": [ |
|
1536, |
|
8960 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 27525120, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "a0eb921170b36a016d3b8656caa53b8d" |
|
}, |
|
{ |
|
"dataPath": "params_shard_15.bin", |
|
"format": "raw-shard", |
|
"nbytes": 55050240, |
|
"records": [ |
|
{ |
|
"name": "model.layers.14.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
17920, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 55050240, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "d80214adb8ccfa0343cf8adb0caec5a4" |
|
}, |
|
{ |
|
"dataPath": "params_shard_16.bin", |
|
"format": "raw-shard", |
|
"nbytes": 33060864, |
|
"records": [ |
|
{ |
|
"name": "model.layers.11.self_attn.c_attn.weight", |
|
"shape": [ |
|
2048, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6291456, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.11.self_attn.o_proj.weight", |
|
"shape": [ |
|
1536, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4718592, |
|
"byteOffset": 6291456 |
|
}, |
|
{ |
|
"name": "model.layers.12.input_layernorm.weight", |
|
"shape": [ |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3072, |
|
"byteOffset": 11010048 |
|
}, |
|
{ |
|
"name": "model.layers.12.post_attention_layernorm.weight", |
|
"shape": [ |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3072, |
|
"byteOffset": 11013120 |
|
}, |
|
{ |
|
"name": "model.layers.12.self_attn.c_attn.bias", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 11016192 |
|
}, |
|
{ |
|
"name": "model.layers.12.self_attn.c_attn.weight", |
|
"shape": [ |
|
2048, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6291456, |
|
"byteOffset": 11020288 |
|
}, |
|
{ |
|
"name": "model.layers.12.self_attn.o_proj.weight", |
|
"shape": [ |
|
1536, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4718592, |
|
"byteOffset": 17311744 |
|
}, |
|
{ |
|
"name": "model.layers.13.input_layernorm.weight", |
|
"shape": [ |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3072, |
|
"byteOffset": 22030336 |
|
}, |
|
{ |
|
"name": "model.layers.13.post_attention_layernorm.weight", |
|
"shape": [ |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3072, |
|
"byteOffset": 22033408 |
|
}, |
|
{ |
|
"name": "model.layers.13.self_attn.c_attn.bias", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 22036480 |
|
}, |
|
{ |
|
"name": "model.layers.13.self_attn.c_attn.weight", |
|
"shape": [ |
|
2048, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6291456, |
|
"byteOffset": 22040576 |
|
}, |
|
{ |
|
"name": "model.layers.13.self_attn.o_proj.weight", |
|
"shape": [ |
|
1536, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4718592, |
|
"byteOffset": 28332032 |
|
}, |
|
{ |
|
"name": "model.layers.14.input_layernorm.weight", |
|
"shape": [ |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3072, |
|
"byteOffset": 33050624 |
|
}, |
|
{ |
|
"name": "model.layers.14.post_attention_layernorm.weight", |
|
"shape": [ |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3072, |
|
"byteOffset": 33053696 |
|
}, |
|
{ |
|
"name": "model.layers.14.self_attn.c_attn.bias", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 33056768 |
|
} |
|
], |
|
"md5sum": "836ad76f4bf6b3ea6142a57d73863eab" |
|
}, |
|
{ |
|
"dataPath": "params_shard_17.bin", |
|
"format": "raw-shard", |
|
"nbytes": 27525120, |
|
"records": [ |
|
{ |
|
"name": "model.layers.15.mlp.down_proj.weight", |
|
"shape": [ |
|
1536, |
|
8960 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 27525120, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "69c8ebf98b69e0a7bed86b1b095d4e58" |
|
}, |
|
{ |
|
"dataPath": "params_shard_18.bin", |
|
"format": "raw-shard", |
|
"nbytes": 55050240, |
|
"records": [ |
|
{ |
|
"name": "model.layers.15.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
17920, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 55050240, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "bc5b5e85e1e1ca4a340dc0ae73d0cf70" |
|
}, |
|
{ |
|
"dataPath": "params_shard_19.bin", |
|
"format": "raw-shard", |
|
"nbytes": 27525120, |
|
"records": [ |
|
{ |
|
"name": "model.layers.16.mlp.down_proj.weight", |
|
"shape": [ |
|
1536, |
|
8960 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 27525120, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "1f0d7a92b72e8c084a47173269fabe37" |
|
}, |
|
{ |
|
"dataPath": "params_shard_20.bin", |
|
"format": "raw-shard", |
|
"nbytes": 55050240, |
|
"records": [ |
|
{ |
|
"name": "model.layers.16.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
17920, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 55050240, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "7868afb9efef145589b5d006eaa1d2cb" |
|
}, |
|
{ |
|
"dataPath": "params_shard_21.bin", |
|
"format": "raw-shard", |
|
"nbytes": 27525120, |
|
"records": [ |
|
{ |
|
"name": "model.layers.17.mlp.down_proj.weight", |
|
"shape": [ |
|
1536, |
|
8960 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 27525120, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "64dd36a133277b89ecb7b753fa45a053" |
|
}, |
|
{ |
|
"dataPath": "params_shard_22.bin", |
|
"format": "raw-shard", |
|
"nbytes": 55050240, |
|
"records": [ |
|
{ |
|
"name": "model.layers.17.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
17920, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 55050240, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "9ed20f54aebad5411cce28791db1bd4f" |
|
}, |
|
{ |
|
"dataPath": "params_shard_23.bin", |
|
"format": "raw-shard", |
|
"nbytes": 33060864, |
|
"records": [ |
|
{ |
|
"name": "model.layers.14.self_attn.c_attn.weight", |
|
"shape": [ |
|
2048, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6291456, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.14.self_attn.o_proj.weight", |
|
"shape": [ |
|
1536, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4718592, |
|
"byteOffset": 6291456 |
|
}, |
|
{ |
|
"name": "model.layers.15.input_layernorm.weight", |
|
"shape": [ |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3072, |
|
"byteOffset": 11010048 |
|
}, |
|
{ |
|
"name": "model.layers.15.post_attention_layernorm.weight", |
|
"shape": [ |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3072, |
|
"byteOffset": 11013120 |
|
}, |
|
{ |
|
"name": "model.layers.15.self_attn.c_attn.bias", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 11016192 |
|
}, |
|
{ |
|
"name": "model.layers.15.self_attn.c_attn.weight", |
|
"shape": [ |
|
2048, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6291456, |
|
"byteOffset": 11020288 |
|
}, |
|
{ |
|
"name": "model.layers.15.self_attn.o_proj.weight", |
|
"shape": [ |
|
1536, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4718592, |
|
"byteOffset": 17311744 |
|
}, |
|
{ |
|
"name": "model.layers.16.input_layernorm.weight", |
|
"shape": [ |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3072, |
|
"byteOffset": 22030336 |
|
}, |
|
{ |
|
"name": "model.layers.16.post_attention_layernorm.weight", |
|
"shape": [ |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3072, |
|
"byteOffset": 22033408 |
|
}, |
|
{ |
|
"name": "model.layers.16.self_attn.c_attn.bias", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 22036480 |
|
}, |
|
{ |
|
"name": "model.layers.16.self_attn.c_attn.weight", |
|
"shape": [ |
|
2048, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6291456, |
|
"byteOffset": 22040576 |
|
}, |
|
{ |
|
"name": "model.layers.16.self_attn.o_proj.weight", |
|
"shape": [ |
|
1536, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4718592, |
|
"byteOffset": 28332032 |
|
}, |
|
{ |
|
"name": "model.layers.17.input_layernorm.weight", |
|
"shape": [ |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3072, |
|
"byteOffset": 33050624 |
|
}, |
|
{ |
|
"name": "model.layers.17.post_attention_layernorm.weight", |
|
"shape": [ |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3072, |
|
"byteOffset": 33053696 |
|
}, |
|
{ |
|
"name": "model.layers.17.self_attn.c_attn.bias", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 33056768 |
|
} |
|
], |
|
"md5sum": "d3ca8d87d2da5c44ba5209a2791736da" |
|
}, |
|
{ |
|
"dataPath": "params_shard_24.bin", |
|
"format": "raw-shard", |
|
"nbytes": 27525120, |
|
"records": [ |
|
{ |
|
"name": "model.layers.18.mlp.down_proj.weight", |
|
"shape": [ |
|
1536, |
|
8960 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 27525120, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "3dd39a6d6ad6ed3ea7b684810336118a" |
|
}, |
|
{ |
|
"dataPath": "params_shard_25.bin", |
|
"format": "raw-shard", |
|
"nbytes": 55050240, |
|
"records": [ |
|
{ |
|
"name": "model.layers.18.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
17920, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 55050240, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "3a8f050e1c81d9c21bd78dc7df0d4bc4" |
|
}, |
|
{ |
|
"dataPath": "params_shard_26.bin", |
|
"format": "raw-shard", |
|
"nbytes": 27525120, |
|
"records": [ |
|
{ |
|
"name": "model.layers.19.mlp.down_proj.weight", |
|
"shape": [ |
|
1536, |
|
8960 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 27525120, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "36ca71a16ca2834d3164b92c97a170ab" |
|
}, |
|
{ |
|
"dataPath": "params_shard_27.bin", |
|
"format": "raw-shard", |
|
"nbytes": 55050240, |
|
"records": [ |
|
{ |
|
"name": "model.layers.19.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
17920, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 55050240, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "9f22ca095f2021608fae9bc98136d252" |
|
}, |
|
{ |
|
"dataPath": "params_shard_28.bin", |
|
"format": "raw-shard", |
|
"nbytes": 27525120, |
|
"records": [ |
|
{ |
|
"name": "model.layers.2.mlp.down_proj.weight", |
|
"shape": [ |
|
1536, |
|
8960 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 27525120, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "fab4a0e7de9cca7058251ee57a4a9742" |
|
}, |
|
{ |
|
"dataPath": "params_shard_29.bin", |
|
"format": "raw-shard", |
|
"nbytes": 55050240, |
|
"records": [ |
|
{ |
|
"name": "model.layers.2.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
17920, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 55050240, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "e6b441ea46b5d4ba144d0ede689da1a2" |
|
}, |
|
{ |
|
"dataPath": "params_shard_30.bin", |
|
"format": "raw-shard", |
|
"nbytes": 33060864, |
|
"records": [ |
|
{ |
|
"name": "model.layers.17.self_attn.c_attn.weight", |
|
"shape": [ |
|
2048, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6291456, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.17.self_attn.o_proj.weight", |
|
"shape": [ |
|
1536, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4718592, |
|
"byteOffset": 6291456 |
|
}, |
|
{ |
|
"name": "model.layers.18.input_layernorm.weight", |
|
"shape": [ |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3072, |
|
"byteOffset": 11010048 |
|
}, |
|
{ |
|
"name": "model.layers.18.post_attention_layernorm.weight", |
|
"shape": [ |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3072, |
|
"byteOffset": 11013120 |
|
}, |
|
{ |
|
"name": "model.layers.18.self_attn.c_attn.bias", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 11016192 |
|
}, |
|
{ |
|
"name": "model.layers.18.self_attn.c_attn.weight", |
|
"shape": [ |
|
2048, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6291456, |
|
"byteOffset": 11020288 |
|
}, |
|
{ |
|
"name": "model.layers.18.self_attn.o_proj.weight", |
|
"shape": [ |
|
1536, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4718592, |
|
"byteOffset": 17311744 |
|
}, |
|
{ |
|
"name": "model.layers.19.input_layernorm.weight", |
|
"shape": [ |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3072, |
|
"byteOffset": 22030336 |
|
}, |
|
{ |
|
"name": "model.layers.19.post_attention_layernorm.weight", |
|
"shape": [ |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3072, |
|
"byteOffset": 22033408 |
|
}, |
|
{ |
|
"name": "model.layers.19.self_attn.c_attn.bias", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 22036480 |
|
}, |
|
{ |
|
"name": "model.layers.19.self_attn.c_attn.weight", |
|
"shape": [ |
|
2048, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6291456, |
|
"byteOffset": 22040576 |
|
}, |
|
{ |
|
"name": "model.layers.19.self_attn.o_proj.weight", |
|
"shape": [ |
|
1536, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4718592, |
|
"byteOffset": 28332032 |
|
}, |
|
{ |
|
"name": "model.layers.2.input_layernorm.weight", |
|
"shape": [ |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3072, |
|
"byteOffset": 33050624 |
|
}, |
|
{ |
|
"name": "model.layers.2.post_attention_layernorm.weight", |
|
"shape": [ |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3072, |
|
"byteOffset": 33053696 |
|
}, |
|
{ |
|
"name": "model.layers.2.self_attn.c_attn.bias", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 33056768 |
|
} |
|
], |
|
"md5sum": "ec32c77b7b448670b9fbb3e4dadd2b9f" |
|
}, |
|
{ |
|
"dataPath": "params_shard_31.bin", |
|
"format": "raw-shard", |
|
"nbytes": 27525120, |
|
"records": [ |
|
{ |
|
"name": "model.layers.20.mlp.down_proj.weight", |
|
"shape": [ |
|
1536, |
|
8960 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 27525120, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "169d2af7bb908d1d1319b2327ffd685d" |
|
}, |
|
{ |
|
"dataPath": "params_shard_32.bin", |
|
"format": "raw-shard", |
|
"nbytes": 55050240, |
|
"records": [ |
|
{ |
|
"name": "model.layers.20.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
17920, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 55050240, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "549d4ada0599a1d35bf7dd3f87dfad84" |
|
}, |
|
{ |
|
"dataPath": "params_shard_33.bin", |
|
"format": "raw-shard", |
|
"nbytes": 27525120, |
|
"records": [ |
|
{ |
|
"name": "model.layers.21.mlp.down_proj.weight", |
|
"shape": [ |
|
1536, |
|
8960 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 27525120, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "6ea484043810c0eeff8409f4fffc7c14" |
|
}, |
|
{ |
|
"dataPath": "params_shard_34.bin", |
|
"format": "raw-shard", |
|
"nbytes": 55050240, |
|
"records": [ |
|
{ |
|
"name": "model.layers.21.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
17920, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 55050240, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "f09443ff1e071a170ee446e8b5c9e983" |
|
}, |
|
{ |
|
"dataPath": "params_shard_35.bin", |
|
"format": "raw-shard", |
|
"nbytes": 27525120, |
|
"records": [ |
|
{ |
|
"name": "model.layers.22.mlp.down_proj.weight", |
|
"shape": [ |
|
1536, |
|
8960 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 27525120, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "367fc7511fd53ad92f83eff81ee49dc2" |
|
}, |
|
{ |
|
"dataPath": "params_shard_36.bin", |
|
"format": "raw-shard", |
|
"nbytes": 55050240, |
|
"records": [ |
|
{ |
|
"name": "model.layers.22.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
17920, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 55050240, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "0a8e85d059205dd0b12cbfd488dbcc1f" |
|
}, |
|
{ |
|
"dataPath": "params_shard_37.bin", |
|
"format": "raw-shard", |
|
"nbytes": 33060864, |
|
"records": [ |
|
{ |
|
"name": "model.layers.2.self_attn.c_attn.weight", |
|
"shape": [ |
|
2048, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6291456, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.2.self_attn.o_proj.weight", |
|
"shape": [ |
|
1536, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4718592, |
|
"byteOffset": 6291456 |
|
}, |
|
{ |
|
"name": "model.layers.20.input_layernorm.weight", |
|
"shape": [ |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3072, |
|
"byteOffset": 11010048 |
|
}, |
|
{ |
|
"name": "model.layers.20.post_attention_layernorm.weight", |
|
"shape": [ |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3072, |
|
"byteOffset": 11013120 |
|
}, |
|
{ |
|
"name": "model.layers.20.self_attn.c_attn.bias", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 11016192 |
|
}, |
|
{ |
|
"name": "model.layers.20.self_attn.c_attn.weight", |
|
"shape": [ |
|
2048, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6291456, |
|
"byteOffset": 11020288 |
|
}, |
|
{ |
|
"name": "model.layers.20.self_attn.o_proj.weight", |
|
"shape": [ |
|
1536, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4718592, |
|
"byteOffset": 17311744 |
|
}, |
|
{ |
|
"name": "model.layers.21.input_layernorm.weight", |
|
"shape": [ |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3072, |
|
"byteOffset": 22030336 |
|
}, |
|
{ |
|
"name": "model.layers.21.post_attention_layernorm.weight", |
|
"shape": [ |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3072, |
|
"byteOffset": 22033408 |
|
}, |
|
{ |
|
"name": "model.layers.21.self_attn.c_attn.bias", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 22036480 |
|
}, |
|
{ |
|
"name": "model.layers.21.self_attn.c_attn.weight", |
|
"shape": [ |
|
2048, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6291456, |
|
"byteOffset": 22040576 |
|
}, |
|
{ |
|
"name": "model.layers.21.self_attn.o_proj.weight", |
|
"shape": [ |
|
1536, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4718592, |
|
"byteOffset": 28332032 |
|
}, |
|
{ |
|
"name": "model.layers.22.input_layernorm.weight", |
|
"shape": [ |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3072, |
|
"byteOffset": 33050624 |
|
}, |
|
{ |
|
"name": "model.layers.22.post_attention_layernorm.weight", |
|
"shape": [ |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3072, |
|
"byteOffset": 33053696 |
|
}, |
|
{ |
|
"name": "model.layers.22.self_attn.c_attn.bias", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 33056768 |
|
} |
|
], |
|
"md5sum": "670d9f64575bb07241d48a8283edc7c3" |
|
}, |
|
{ |
|
"dataPath": "params_shard_38.bin", |
|
"format": "raw-shard", |
|
"nbytes": 27525120, |
|
"records": [ |
|
{ |
|
"name": "model.layers.23.mlp.down_proj.weight", |
|
"shape": [ |
|
1536, |
|
8960 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 27525120, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "55dc4417efdd8592cf2596108dc49e03" |
|
}, |
|
{ |
|
"dataPath": "params_shard_39.bin", |
|
"format": "raw-shard", |
|
"nbytes": 55050240, |
|
"records": [ |
|
{ |
|
"name": "model.layers.23.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
17920, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 55050240, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "59aae069c3cf2e5dfc148b92384dea3d" |
|
}, |
|
{ |
|
"dataPath": "params_shard_40.bin", |
|
"format": "raw-shard", |
|
"nbytes": 27525120, |
|
"records": [ |
|
{ |
|
"name": "model.layers.24.mlp.down_proj.weight", |
|
"shape": [ |
|
1536, |
|
8960 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 27525120, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "3ee6d1d9d6a0d40aa5c6cda617a5d1bb" |
|
}, |
|
{ |
|
"dataPath": "params_shard_41.bin", |
|
"format": "raw-shard", |
|
"nbytes": 55050240, |
|
"records": [ |
|
{ |
|
"name": "model.layers.24.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
17920, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 55050240, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "a1c9e0afa3d19157d9470ecbe8d02441" |
|
}, |
|
{ |
|
"dataPath": "params_shard_42.bin", |
|
"format": "raw-shard", |
|
"nbytes": 27525120, |
|
"records": [ |
|
{ |
|
"name": "model.layers.25.mlp.down_proj.weight", |
|
"shape": [ |
|
1536, |
|
8960 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 27525120, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "0c88c6fbbe93a15c6d1c34b64769e9ee" |
|
}, |
|
{ |
|
"dataPath": "params_shard_43.bin", |
|
"format": "raw-shard", |
|
"nbytes": 55050240, |
|
"records": [ |
|
{ |
|
"name": "model.layers.25.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
17920, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 55050240, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "bf742044703c2a29f0c83f872a30751a" |
|
}, |
|
{ |
|
"dataPath": "params_shard_44.bin", |
|
"format": "raw-shard", |
|
"nbytes": 33060864, |
|
"records": [ |
|
{ |
|
"name": "model.layers.22.self_attn.c_attn.weight", |
|
"shape": [ |
|
2048, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6291456, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.22.self_attn.o_proj.weight", |
|
"shape": [ |
|
1536, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4718592, |
|
"byteOffset": 6291456 |
|
}, |
|
{ |
|
"name": "model.layers.23.input_layernorm.weight", |
|
"shape": [ |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3072, |
|
"byteOffset": 11010048 |
|
}, |
|
{ |
|
"name": "model.layers.23.post_attention_layernorm.weight", |
|
"shape": [ |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3072, |
|
"byteOffset": 11013120 |
|
}, |
|
{ |
|
"name": "model.layers.23.self_attn.c_attn.bias", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 11016192 |
|
}, |
|
{ |
|
"name": "model.layers.23.self_attn.c_attn.weight", |
|
"shape": [ |
|
2048, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6291456, |
|
"byteOffset": 11020288 |
|
}, |
|
{ |
|
"name": "model.layers.23.self_attn.o_proj.weight", |
|
"shape": [ |
|
1536, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4718592, |
|
"byteOffset": 17311744 |
|
}, |
|
{ |
|
"name": "model.layers.24.input_layernorm.weight", |
|
"shape": [ |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3072, |
|
"byteOffset": 22030336 |
|
}, |
|
{ |
|
"name": "model.layers.24.post_attention_layernorm.weight", |
|
"shape": [ |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3072, |
|
"byteOffset": 22033408 |
|
}, |
|
{ |
|
"name": "model.layers.24.self_attn.c_attn.bias", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 22036480 |
|
}, |
|
{ |
|
"name": "model.layers.24.self_attn.c_attn.weight", |
|
"shape": [ |
|
2048, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6291456, |
|
"byteOffset": 22040576 |
|
}, |
|
{ |
|
"name": "model.layers.24.self_attn.o_proj.weight", |
|
"shape": [ |
|
1536, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4718592, |
|
"byteOffset": 28332032 |
|
}, |
|
{ |
|
"name": "model.layers.25.input_layernorm.weight", |
|
"shape": [ |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3072, |
|
"byteOffset": 33050624 |
|
}, |
|
{ |
|
"name": "model.layers.25.post_attention_layernorm.weight", |
|
"shape": [ |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3072, |
|
"byteOffset": 33053696 |
|
}, |
|
{ |
|
"name": "model.layers.25.self_attn.c_attn.bias", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 33056768 |
|
} |
|
], |
|
"md5sum": "9bd20d328ef42e9cb0daeea34f8f1665" |
|
}, |
|
{ |
|
"dataPath": "params_shard_45.bin", |
|
"format": "raw-shard", |
|
"nbytes": 27525120, |
|
"records": [ |
|
{ |
|
"name": "model.layers.26.mlp.down_proj.weight", |
|
"shape": [ |
|
1536, |
|
8960 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 27525120, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "3bf660c4dd495b4cb010e090958b399f" |
|
}, |
|
{ |
|
"dataPath": "params_shard_46.bin", |
|
"format": "raw-shard", |
|
"nbytes": 55050240, |
|
"records": [ |
|
{ |
|
"name": "model.layers.26.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
17920, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 55050240, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "1d8d43c1f77c22de3ed30d08f84db8c1" |
|
}, |
|
{ |
|
"dataPath": "params_shard_47.bin", |
|
"format": "raw-shard", |
|
"nbytes": 27525120, |
|
"records": [ |
|
{ |
|
"name": "model.layers.27.mlp.down_proj.weight", |
|
"shape": [ |
|
1536, |
|
8960 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 27525120, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "5dba30ad09b4e0832d4b66cbab7cbb65" |
|
}, |
|
{ |
|
"dataPath": "params_shard_48.bin", |
|
"format": "raw-shard", |
|
"nbytes": 55050240, |
|
"records": [ |
|
{ |
|
"name": "model.layers.27.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
17920, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 55050240, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "3e3f1c5f902e1612e29d8d4bfce8c13f" |
|
}, |
|
{ |
|
"dataPath": "params_shard_49.bin", |
|
"format": "raw-shard", |
|
"nbytes": 27525120, |
|
"records": [ |
|
{ |
|
"name": "model.layers.3.mlp.down_proj.weight", |
|
"shape": [ |
|
1536, |
|
8960 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 27525120, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "dafb2ba9ed30881ead0f758444c710e9" |
|
}, |
|
{ |
|
"dataPath": "params_shard_50.bin", |
|
"format": "raw-shard", |
|
"nbytes": 55050240, |
|
"records": [ |
|
{ |
|
"name": "model.layers.3.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
17920, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 55050240, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "fae672c0483259b7c6f78ebe8c9bc007" |
|
}, |
|
{ |
|
"dataPath": "params_shard_51.bin", |
|
"format": "raw-shard", |
|
"nbytes": 33060864, |
|
"records": [ |
|
{ |
|
"name": "model.layers.25.self_attn.c_attn.weight", |
|
"shape": [ |
|
2048, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6291456, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.25.self_attn.o_proj.weight", |
|
"shape": [ |
|
1536, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4718592, |
|
"byteOffset": 6291456 |
|
}, |
|
{ |
|
"name": "model.layers.26.input_layernorm.weight", |
|
"shape": [ |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3072, |
|
"byteOffset": 11010048 |
|
}, |
|
{ |
|
"name": "model.layers.26.post_attention_layernorm.weight", |
|
"shape": [ |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3072, |
|
"byteOffset": 11013120 |
|
}, |
|
{ |
|
"name": "model.layers.26.self_attn.c_attn.bias", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 11016192 |
|
}, |
|
{ |
|
"name": "model.layers.26.self_attn.c_attn.weight", |
|
"shape": [ |
|
2048, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6291456, |
|
"byteOffset": 11020288 |
|
}, |
|
{ |
|
"name": "model.layers.26.self_attn.o_proj.weight", |
|
"shape": [ |
|
1536, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4718592, |
|
"byteOffset": 17311744 |
|
}, |
|
{ |
|
"name": "model.layers.27.input_layernorm.weight", |
|
"shape": [ |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3072, |
|
"byteOffset": 22030336 |
|
}, |
|
{ |
|
"name": "model.layers.27.post_attention_layernorm.weight", |
|
"shape": [ |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3072, |
|
"byteOffset": 22033408 |
|
}, |
|
{ |
|
"name": "model.layers.27.self_attn.c_attn.bias", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 22036480 |
|
}, |
|
{ |
|
"name": "model.layers.27.self_attn.c_attn.weight", |
|
"shape": [ |
|
2048, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6291456, |
|
"byteOffset": 22040576 |
|
}, |
|
{ |
|
"name": "model.layers.27.self_attn.o_proj.weight", |
|
"shape": [ |
|
1536, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4718592, |
|
"byteOffset": 28332032 |
|
}, |
|
{ |
|
"name": "model.layers.3.input_layernorm.weight", |
|
"shape": [ |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3072, |
|
"byteOffset": 33050624 |
|
}, |
|
{ |
|
"name": "model.layers.3.post_attention_layernorm.weight", |
|
"shape": [ |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3072, |
|
"byteOffset": 33053696 |
|
}, |
|
{ |
|
"name": "model.layers.3.self_attn.c_attn.bias", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 33056768 |
|
} |
|
], |
|
"md5sum": "e15198cbf013718fbac52a1a8d94a4bd" |
|
}, |
|
{ |
|
"dataPath": "params_shard_52.bin", |
|
"format": "raw-shard", |
|
"nbytes": 27525120, |
|
"records": [ |
|
{ |
|
"name": "model.layers.4.mlp.down_proj.weight", |
|
"shape": [ |
|
1536, |
|
8960 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 27525120, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "8ef490e2d5fdd10b563790c6c8ddf751" |
|
}, |
|
{ |
|
"dataPath": "params_shard_53.bin", |
|
"format": "raw-shard", |
|
"nbytes": 55050240, |
|
"records": [ |
|
{ |
|
"name": "model.layers.4.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
17920, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 55050240, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "0d9f22936600b212ad7509684535ed16" |
|
}, |
|
{ |
|
"dataPath": "params_shard_54.bin", |
|
"format": "raw-shard", |
|
"nbytes": 27525120, |
|
"records": [ |
|
{ |
|
"name": "model.layers.5.mlp.down_proj.weight", |
|
"shape": [ |
|
1536, |
|
8960 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 27525120, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "b877bb9f1825407f4828cde2906e483c" |
|
}, |
|
{ |
|
"dataPath": "params_shard_55.bin", |
|
"format": "raw-shard", |
|
"nbytes": 55050240, |
|
"records": [ |
|
{ |
|
"name": "model.layers.5.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
17920, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 55050240, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "4aeb2df9e320197a7328f274ccc1e0c6" |
|
}, |
|
{ |
|
"dataPath": "params_shard_56.bin", |
|
"format": "raw-shard", |
|
"nbytes": 27525120, |
|
"records": [ |
|
{ |
|
"name": "model.layers.6.mlp.down_proj.weight", |
|
"shape": [ |
|
1536, |
|
8960 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 27525120, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "4159b8469797370880dec9cef854c8b1" |
|
}, |
|
{ |
|
"dataPath": "params_shard_57.bin", |
|
"format": "raw-shard", |
|
"nbytes": 55050240, |
|
"records": [ |
|
{ |
|
"name": "model.layers.6.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
17920, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 55050240, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "f6f34569657363a613bb38ffa4a8ce25" |
|
}, |
|
{ |
|
"dataPath": "params_shard_58.bin", |
|
"format": "raw-shard", |
|
"nbytes": 33060864, |
|
"records": [ |
|
{ |
|
"name": "model.layers.3.self_attn.c_attn.weight", |
|
"shape": [ |
|
2048, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6291456, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.3.self_attn.o_proj.weight", |
|
"shape": [ |
|
1536, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4718592, |
|
"byteOffset": 6291456 |
|
}, |
|
{ |
|
"name": "model.layers.4.input_layernorm.weight", |
|
"shape": [ |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3072, |
|
"byteOffset": 11010048 |
|
}, |
|
{ |
|
"name": "model.layers.4.post_attention_layernorm.weight", |
|
"shape": [ |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3072, |
|
"byteOffset": 11013120 |
|
}, |
|
{ |
|
"name": "model.layers.4.self_attn.c_attn.bias", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 11016192 |
|
}, |
|
{ |
|
"name": "model.layers.4.self_attn.c_attn.weight", |
|
"shape": [ |
|
2048, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6291456, |
|
"byteOffset": 11020288 |
|
}, |
|
{ |
|
"name": "model.layers.4.self_attn.o_proj.weight", |
|
"shape": [ |
|
1536, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4718592, |
|
"byteOffset": 17311744 |
|
}, |
|
{ |
|
"name": "model.layers.5.input_layernorm.weight", |
|
"shape": [ |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3072, |
|
"byteOffset": 22030336 |
|
}, |
|
{ |
|
"name": "model.layers.5.post_attention_layernorm.weight", |
|
"shape": [ |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3072, |
|
"byteOffset": 22033408 |
|
}, |
|
{ |
|
"name": "model.layers.5.self_attn.c_attn.bias", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 22036480 |
|
}, |
|
{ |
|
"name": "model.layers.5.self_attn.c_attn.weight", |
|
"shape": [ |
|
2048, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6291456, |
|
"byteOffset": 22040576 |
|
}, |
|
{ |
|
"name": "model.layers.5.self_attn.o_proj.weight", |
|
"shape": [ |
|
1536, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4718592, |
|
"byteOffset": 28332032 |
|
}, |
|
{ |
|
"name": "model.layers.6.input_layernorm.weight", |
|
"shape": [ |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3072, |
|
"byteOffset": 33050624 |
|
}, |
|
{ |
|
"name": "model.layers.6.post_attention_layernorm.weight", |
|
"shape": [ |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3072, |
|
"byteOffset": 33053696 |
|
}, |
|
{ |
|
"name": "model.layers.6.self_attn.c_attn.bias", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 33056768 |
|
} |
|
], |
|
"md5sum": "4b9635bfbb9a0f8e379594d577e24e79" |
|
}, |
|
{ |
|
"dataPath": "params_shard_59.bin", |
|
"format": "raw-shard", |
|
"nbytes": 27525120, |
|
"records": [ |
|
{ |
|
"name": "model.layers.7.mlp.down_proj.weight", |
|
"shape": [ |
|
1536, |
|
8960 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 27525120, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "6f06f08ee4e830a7f35fad5489e2df96" |
|
}, |
|
{ |
|
"dataPath": "params_shard_60.bin", |
|
"format": "raw-shard", |
|
"nbytes": 55050240, |
|
"records": [ |
|
{ |
|
"name": "model.layers.7.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
17920, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 55050240, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "6a51b2acc4eb22511d78c73146e97c57" |
|
}, |
|
{ |
|
"dataPath": "params_shard_61.bin", |
|
"format": "raw-shard", |
|
"nbytes": 27525120, |
|
"records": [ |
|
{ |
|
"name": "model.layers.8.mlp.down_proj.weight", |
|
"shape": [ |
|
1536, |
|
8960 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 27525120, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "422c9f65efd3c517f5f597ff198b9b54" |
|
}, |
|
{ |
|
"dataPath": "params_shard_62.bin", |
|
"format": "raw-shard", |
|
"nbytes": 55050240, |
|
"records": [ |
|
{ |
|
"name": "model.layers.8.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
17920, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 55050240, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "194381860a8101e6639b37c321b03e53" |
|
}, |
|
{ |
|
"dataPath": "params_shard_63.bin", |
|
"format": "raw-shard", |
|
"nbytes": 27525120, |
|
"records": [ |
|
{ |
|
"name": "model.layers.9.mlp.down_proj.weight", |
|
"shape": [ |
|
1536, |
|
8960 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 27525120, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "dcc2852e43b9cca8d247abb596a6cfd3" |
|
}, |
|
{ |
|
"dataPath": "params_shard_64.bin", |
|
"format": "raw-shard", |
|
"nbytes": 55050240, |
|
"records": [ |
|
{ |
|
"name": "model.layers.9.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
17920, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 55050240, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "31b0adf54bda832e421327cc270f38de" |
|
}, |
|
{ |
|
"dataPath": "params_shard_65.bin", |
|
"format": "raw-shard", |
|
"nbytes": 33060864, |
|
"records": [ |
|
{ |
|
"name": "model.layers.6.self_attn.c_attn.weight", |
|
"shape": [ |
|
2048, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6291456, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.6.self_attn.o_proj.weight", |
|
"shape": [ |
|
1536, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4718592, |
|
"byteOffset": 6291456 |
|
}, |
|
{ |
|
"name": "model.layers.7.input_layernorm.weight", |
|
"shape": [ |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3072, |
|
"byteOffset": 11010048 |
|
}, |
|
{ |
|
"name": "model.layers.7.post_attention_layernorm.weight", |
|
"shape": [ |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3072, |
|
"byteOffset": 11013120 |
|
}, |
|
{ |
|
"name": "model.layers.7.self_attn.c_attn.bias", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 11016192 |
|
}, |
|
{ |
|
"name": "model.layers.7.self_attn.c_attn.weight", |
|
"shape": [ |
|
2048, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6291456, |
|
"byteOffset": 11020288 |
|
}, |
|
{ |
|
"name": "model.layers.7.self_attn.o_proj.weight", |
|
"shape": [ |
|
1536, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4718592, |
|
"byteOffset": 17311744 |
|
}, |
|
{ |
|
"name": "model.layers.8.input_layernorm.weight", |
|
"shape": [ |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3072, |
|
"byteOffset": 22030336 |
|
}, |
|
{ |
|
"name": "model.layers.8.post_attention_layernorm.weight", |
|
"shape": [ |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3072, |
|
"byteOffset": 22033408 |
|
}, |
|
{ |
|
"name": "model.layers.8.self_attn.c_attn.bias", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 22036480 |
|
}, |
|
{ |
|
"name": "model.layers.8.self_attn.c_attn.weight", |
|
"shape": [ |
|
2048, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6291456, |
|
"byteOffset": 22040576 |
|
}, |
|
{ |
|
"name": "model.layers.8.self_attn.o_proj.weight", |
|
"shape": [ |
|
1536, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4718592, |
|
"byteOffset": 28332032 |
|
}, |
|
{ |
|
"name": "model.layers.9.input_layernorm.weight", |
|
"shape": [ |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3072, |
|
"byteOffset": 33050624 |
|
}, |
|
{ |
|
"name": "model.layers.9.post_attention_layernorm.weight", |
|
"shape": [ |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3072, |
|
"byteOffset": 33053696 |
|
}, |
|
{ |
|
"name": "model.layers.9.self_attn.c_attn.bias", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 33056768 |
|
} |
|
], |
|
"md5sum": "80e3191e706ecd10535e81ffa38fc3c2" |
|
}, |
|
{ |
|
"dataPath": "params_shard_66.bin", |
|
"format": "raw-shard", |
|
"nbytes": 11013120, |
|
"records": [ |
|
{ |
|
"name": "model.layers.9.self_attn.c_attn.weight", |
|
"shape": [ |
|
2048, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6291456, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.9.self_attn.o_proj.weight", |
|
"shape": [ |
|
1536, |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4718592, |
|
"byteOffset": 6291456 |
|
}, |
|
{ |
|
"name": "model.norm.weight", |
|
"shape": [ |
|
1536 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 3072, |
|
"byteOffset": 11010048 |
|
} |
|
], |
|
"md5sum": "554e351ae89de4c09af73e23fd71576f" |
|
} |
|
] |
|
} |