|
{ |
|
"metadata": { |
|
"ParamSize": 225, |
|
"ParamBytes": 916088832.0, |
|
"BitsPerParam": 4.500650860708262 |
|
}, |
|
"records": [ |
|
{ |
|
"dataPath": "params_shard_0.bin", |
|
"format": "raw-shard", |
|
"nbytes": 164847616, |
|
"records": [ |
|
{ |
|
"name": "lm_head.q_weight", |
|
"shape": [ |
|
160984, |
|
256 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 164847616, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "66fd10d562b3377b621a1b4bacfbe607" |
|
}, |
|
{ |
|
"dataPath": "params_shard_1.bin", |
|
"format": "raw-shard", |
|
"nbytes": 164847616, |
|
"records": [ |
|
{ |
|
"name": "model.embed_tokens.q_weight", |
|
"shape": [ |
|
160984, |
|
256 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 164847616, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "83824124dc0f0dd818dcdb63c547b911" |
|
}, |
|
{ |
|
"dataPath": "params_shard_2.bin", |
|
"format": "raw-shard", |
|
"nbytes": 20605952, |
|
"records": [ |
|
{ |
|
"name": "model.embed_tokens.q_scale", |
|
"shape": [ |
|
160984, |
|
64 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 20605952, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "a8d163e70ba7ad6d6bd638dd32f28233" |
|
}, |
|
{ |
|
"dataPath": "params_shard_3.bin", |
|
"format": "raw-shard", |
|
"nbytes": 27098112, |
|
"records": [ |
|
{ |
|
"name": "lm_head.q_scale", |
|
"shape": [ |
|
160984, |
|
64 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 20605952, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.0.input_layernorm.weight", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 20605952 |
|
}, |
|
{ |
|
"name": "model.layers.0.mlp.down_proj.q_weight", |
|
"shape": [ |
|
2048, |
|
704 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5767168, |
|
"byteOffset": 20610048 |
|
}, |
|
{ |
|
"name": "model.layers.0.mlp.down_proj.q_scale", |
|
"shape": [ |
|
2048, |
|
176 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 720896, |
|
"byteOffset": 26377216 |
|
} |
|
], |
|
"md5sum": "638a28a548dee7e9430d91d06e2a62dc" |
|
}, |
|
{ |
|
"dataPath": "params_shard_4.bin", |
|
"format": "raw-shard", |
|
"nbytes": 24780800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.0.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
11264, |
|
256 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 11534336, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.0.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
11264, |
|
64 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1441792, |
|
"byteOffset": 11534336 |
|
}, |
|
{ |
|
"name": "model.layers.0.post_attention_layernorm.weight", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 12976128 |
|
}, |
|
{ |
|
"name": "model.layers.0.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
2560, |
|
256 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2621440, |
|
"byteOffset": 12980224 |
|
}, |
|
{ |
|
"name": "model.layers.0.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
2560, |
|
64 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 327680, |
|
"byteOffset": 15601664 |
|
}, |
|
{ |
|
"name": "model.layers.0.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
2048, |
|
256 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2097152, |
|
"byteOffset": 15929344 |
|
}, |
|
{ |
|
"name": "model.layers.0.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
2048, |
|
64 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 262144, |
|
"byteOffset": 18026496 |
|
}, |
|
{ |
|
"name": "model.layers.1.input_layernorm.weight", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 18288640 |
|
}, |
|
{ |
|
"name": "model.layers.1.mlp.down_proj.q_weight", |
|
"shape": [ |
|
2048, |
|
704 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5767168, |
|
"byteOffset": 18292736 |
|
}, |
|
{ |
|
"name": "model.layers.1.mlp.down_proj.q_scale", |
|
"shape": [ |
|
2048, |
|
176 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 720896, |
|
"byteOffset": 24059904 |
|
} |
|
], |
|
"md5sum": "3cf853e6f586b52e2c27b5a760a94bbb" |
|
}, |
|
{ |
|
"dataPath": "params_shard_5.bin", |
|
"format": "raw-shard", |
|
"nbytes": 24780800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.1.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
11264, |
|
256 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 11534336, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.1.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
11264, |
|
64 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1441792, |
|
"byteOffset": 11534336 |
|
}, |
|
{ |
|
"name": "model.layers.1.post_attention_layernorm.weight", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 12976128 |
|
}, |
|
{ |
|
"name": "model.layers.1.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
2560, |
|
256 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2621440, |
|
"byteOffset": 12980224 |
|
}, |
|
{ |
|
"name": "model.layers.1.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
2560, |
|
64 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 327680, |
|
"byteOffset": 15601664 |
|
}, |
|
{ |
|
"name": "model.layers.1.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
2048, |
|
256 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2097152, |
|
"byteOffset": 15929344 |
|
}, |
|
{ |
|
"name": "model.layers.1.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
2048, |
|
64 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 262144, |
|
"byteOffset": 18026496 |
|
}, |
|
{ |
|
"name": "model.layers.10.input_layernorm.weight", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 18288640 |
|
}, |
|
{ |
|
"name": "model.layers.10.mlp.down_proj.q_weight", |
|
"shape": [ |
|
2048, |
|
704 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5767168, |
|
"byteOffset": 18292736 |
|
}, |
|
{ |
|
"name": "model.layers.10.mlp.down_proj.q_scale", |
|
"shape": [ |
|
2048, |
|
176 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 720896, |
|
"byteOffset": 24059904 |
|
} |
|
], |
|
"md5sum": "28b16f3a2f3b53d1352916220db52388" |
|
}, |
|
{ |
|
"dataPath": "params_shard_6.bin", |
|
"format": "raw-shard", |
|
"nbytes": 24780800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.10.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
11264, |
|
256 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 11534336, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.10.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
11264, |
|
64 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1441792, |
|
"byteOffset": 11534336 |
|
}, |
|
{ |
|
"name": "model.layers.10.post_attention_layernorm.weight", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 12976128 |
|
}, |
|
{ |
|
"name": "model.layers.10.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
2560, |
|
256 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2621440, |
|
"byteOffset": 12980224 |
|
}, |
|
{ |
|
"name": "model.layers.10.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
2560, |
|
64 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 327680, |
|
"byteOffset": 15601664 |
|
}, |
|
{ |
|
"name": "model.layers.10.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
2048, |
|
256 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2097152, |
|
"byteOffset": 15929344 |
|
}, |
|
{ |
|
"name": "model.layers.10.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
2048, |
|
64 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 262144, |
|
"byteOffset": 18026496 |
|
}, |
|
{ |
|
"name": "model.layers.11.input_layernorm.weight", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 18288640 |
|
}, |
|
{ |
|
"name": "model.layers.11.mlp.down_proj.q_weight", |
|
"shape": [ |
|
2048, |
|
704 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5767168, |
|
"byteOffset": 18292736 |
|
}, |
|
{ |
|
"name": "model.layers.11.mlp.down_proj.q_scale", |
|
"shape": [ |
|
2048, |
|
176 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 720896, |
|
"byteOffset": 24059904 |
|
} |
|
], |
|
"md5sum": "73fea510e5ce8153c99850aba8ea2dca" |
|
}, |
|
{ |
|
"dataPath": "params_shard_7.bin", |
|
"format": "raw-shard", |
|
"nbytes": 24780800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.11.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
11264, |
|
256 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 11534336, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.11.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
11264, |
|
64 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1441792, |
|
"byteOffset": 11534336 |
|
}, |
|
{ |
|
"name": "model.layers.11.post_attention_layernorm.weight", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 12976128 |
|
}, |
|
{ |
|
"name": "model.layers.11.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
2560, |
|
256 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2621440, |
|
"byteOffset": 12980224 |
|
}, |
|
{ |
|
"name": "model.layers.11.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
2560, |
|
64 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 327680, |
|
"byteOffset": 15601664 |
|
}, |
|
{ |
|
"name": "model.layers.11.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
2048, |
|
256 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2097152, |
|
"byteOffset": 15929344 |
|
}, |
|
{ |
|
"name": "model.layers.11.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
2048, |
|
64 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 262144, |
|
"byteOffset": 18026496 |
|
}, |
|
{ |
|
"name": "model.layers.12.input_layernorm.weight", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 18288640 |
|
}, |
|
{ |
|
"name": "model.layers.12.mlp.down_proj.q_weight", |
|
"shape": [ |
|
2048, |
|
704 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5767168, |
|
"byteOffset": 18292736 |
|
}, |
|
{ |
|
"name": "model.layers.12.mlp.down_proj.q_scale", |
|
"shape": [ |
|
2048, |
|
176 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 720896, |
|
"byteOffset": 24059904 |
|
} |
|
], |
|
"md5sum": "f8fa1159fa72bb6c264da79e2b89924b" |
|
}, |
|
{ |
|
"dataPath": "params_shard_8.bin", |
|
"format": "raw-shard", |
|
"nbytes": 24780800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.12.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
11264, |
|
256 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 11534336, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.12.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
11264, |
|
64 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1441792, |
|
"byteOffset": 11534336 |
|
}, |
|
{ |
|
"name": "model.layers.12.post_attention_layernorm.weight", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 12976128 |
|
}, |
|
{ |
|
"name": "model.layers.12.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
2560, |
|
256 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2621440, |
|
"byteOffset": 12980224 |
|
}, |
|
{ |
|
"name": "model.layers.12.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
2560, |
|
64 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 327680, |
|
"byteOffset": 15601664 |
|
}, |
|
{ |
|
"name": "model.layers.12.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
2048, |
|
256 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2097152, |
|
"byteOffset": 15929344 |
|
}, |
|
{ |
|
"name": "model.layers.12.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
2048, |
|
64 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 262144, |
|
"byteOffset": 18026496 |
|
}, |
|
{ |
|
"name": "model.layers.13.input_layernorm.weight", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 18288640 |
|
}, |
|
{ |
|
"name": "model.layers.13.mlp.down_proj.q_weight", |
|
"shape": [ |
|
2048, |
|
704 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5767168, |
|
"byteOffset": 18292736 |
|
}, |
|
{ |
|
"name": "model.layers.13.mlp.down_proj.q_scale", |
|
"shape": [ |
|
2048, |
|
176 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 720896, |
|
"byteOffset": 24059904 |
|
} |
|
], |
|
"md5sum": "4567b9396fb721482e3fa6c249c9aa3a" |
|
}, |
|
{ |
|
"dataPath": "params_shard_9.bin", |
|
"format": "raw-shard", |
|
"nbytes": 24780800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.13.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
11264, |
|
256 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 11534336, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.13.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
11264, |
|
64 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1441792, |
|
"byteOffset": 11534336 |
|
}, |
|
{ |
|
"name": "model.layers.13.post_attention_layernorm.weight", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 12976128 |
|
}, |
|
{ |
|
"name": "model.layers.13.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
2560, |
|
256 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2621440, |
|
"byteOffset": 12980224 |
|
}, |
|
{ |
|
"name": "model.layers.13.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
2560, |
|
64 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 327680, |
|
"byteOffset": 15601664 |
|
}, |
|
{ |
|
"name": "model.layers.13.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
2048, |
|
256 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2097152, |
|
"byteOffset": 15929344 |
|
}, |
|
{ |
|
"name": "model.layers.13.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
2048, |
|
64 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 262144, |
|
"byteOffset": 18026496 |
|
}, |
|
{ |
|
"name": "model.layers.14.input_layernorm.weight", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 18288640 |
|
}, |
|
{ |
|
"name": "model.layers.14.mlp.down_proj.q_weight", |
|
"shape": [ |
|
2048, |
|
704 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5767168, |
|
"byteOffset": 18292736 |
|
}, |
|
{ |
|
"name": "model.layers.14.mlp.down_proj.q_scale", |
|
"shape": [ |
|
2048, |
|
176 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 720896, |
|
"byteOffset": 24059904 |
|
} |
|
], |
|
"md5sum": "539a5193dfdb13cacdd3c3a4c88dcfbf" |
|
}, |
|
{ |
|
"dataPath": "params_shard_10.bin", |
|
"format": "raw-shard", |
|
"nbytes": 24780800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.14.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
11264, |
|
256 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 11534336, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.14.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
11264, |
|
64 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1441792, |
|
"byteOffset": 11534336 |
|
}, |
|
{ |
|
"name": "model.layers.14.post_attention_layernorm.weight", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 12976128 |
|
}, |
|
{ |
|
"name": "model.layers.14.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
2560, |
|
256 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2621440, |
|
"byteOffset": 12980224 |
|
}, |
|
{ |
|
"name": "model.layers.14.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
2560, |
|
64 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 327680, |
|
"byteOffset": 15601664 |
|
}, |
|
{ |
|
"name": "model.layers.14.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
2048, |
|
256 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2097152, |
|
"byteOffset": 15929344 |
|
}, |
|
{ |
|
"name": "model.layers.14.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
2048, |
|
64 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 262144, |
|
"byteOffset": 18026496 |
|
}, |
|
{ |
|
"name": "model.layers.15.input_layernorm.weight", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 18288640 |
|
}, |
|
{ |
|
"name": "model.layers.15.mlp.down_proj.q_weight", |
|
"shape": [ |
|
2048, |
|
704 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5767168, |
|
"byteOffset": 18292736 |
|
}, |
|
{ |
|
"name": "model.layers.15.mlp.down_proj.q_scale", |
|
"shape": [ |
|
2048, |
|
176 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 720896, |
|
"byteOffset": 24059904 |
|
} |
|
], |
|
"md5sum": "0468961fda097b96aaf0e782f93f8b00" |
|
}, |
|
{ |
|
"dataPath": "params_shard_11.bin", |
|
"format": "raw-shard", |
|
"nbytes": 24780800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.15.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
11264, |
|
256 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 11534336, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.15.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
11264, |
|
64 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1441792, |
|
"byteOffset": 11534336 |
|
}, |
|
{ |
|
"name": "model.layers.15.post_attention_layernorm.weight", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 12976128 |
|
}, |
|
{ |
|
"name": "model.layers.15.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
2560, |
|
256 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2621440, |
|
"byteOffset": 12980224 |
|
}, |
|
{ |
|
"name": "model.layers.15.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
2560, |
|
64 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 327680, |
|
"byteOffset": 15601664 |
|
}, |
|
{ |
|
"name": "model.layers.15.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
2048, |
|
256 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2097152, |
|
"byteOffset": 15929344 |
|
}, |
|
{ |
|
"name": "model.layers.15.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
2048, |
|
64 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 262144, |
|
"byteOffset": 18026496 |
|
}, |
|
{ |
|
"name": "model.layers.16.input_layernorm.weight", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 18288640 |
|
}, |
|
{ |
|
"name": "model.layers.16.mlp.down_proj.q_weight", |
|
"shape": [ |
|
2048, |
|
704 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5767168, |
|
"byteOffset": 18292736 |
|
}, |
|
{ |
|
"name": "model.layers.16.mlp.down_proj.q_scale", |
|
"shape": [ |
|
2048, |
|
176 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 720896, |
|
"byteOffset": 24059904 |
|
} |
|
], |
|
"md5sum": "aa19f11c9d0b953ea02da32c9c1c129e" |
|
}, |
|
{ |
|
"dataPath": "params_shard_12.bin", |
|
"format": "raw-shard", |
|
"nbytes": 24780800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.16.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
11264, |
|
256 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 11534336, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.16.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
11264, |
|
64 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1441792, |
|
"byteOffset": 11534336 |
|
}, |
|
{ |
|
"name": "model.layers.16.post_attention_layernorm.weight", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 12976128 |
|
}, |
|
{ |
|
"name": "model.layers.16.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
2560, |
|
256 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2621440, |
|
"byteOffset": 12980224 |
|
}, |
|
{ |
|
"name": "model.layers.16.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
2560, |
|
64 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 327680, |
|
"byteOffset": 15601664 |
|
}, |
|
{ |
|
"name": "model.layers.16.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
2048, |
|
256 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2097152, |
|
"byteOffset": 15929344 |
|
}, |
|
{ |
|
"name": "model.layers.16.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
2048, |
|
64 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 262144, |
|
"byteOffset": 18026496 |
|
}, |
|
{ |
|
"name": "model.layers.17.input_layernorm.weight", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 18288640 |
|
}, |
|
{ |
|
"name": "model.layers.17.mlp.down_proj.q_weight", |
|
"shape": [ |
|
2048, |
|
704 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5767168, |
|
"byteOffset": 18292736 |
|
}, |
|
{ |
|
"name": "model.layers.17.mlp.down_proj.q_scale", |
|
"shape": [ |
|
2048, |
|
176 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 720896, |
|
"byteOffset": 24059904 |
|
} |
|
], |
|
"md5sum": "0d1433365bb4e76f8212019422e6a437" |
|
}, |
|
{ |
|
"dataPath": "params_shard_13.bin", |
|
"format": "raw-shard", |
|
"nbytes": 24780800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.17.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
11264, |
|
256 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 11534336, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.17.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
11264, |
|
64 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1441792, |
|
"byteOffset": 11534336 |
|
}, |
|
{ |
|
"name": "model.layers.17.post_attention_layernorm.weight", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 12976128 |
|
}, |
|
{ |
|
"name": "model.layers.17.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
2560, |
|
256 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2621440, |
|
"byteOffset": 12980224 |
|
}, |
|
{ |
|
"name": "model.layers.17.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
2560, |
|
64 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 327680, |
|
"byteOffset": 15601664 |
|
}, |
|
{ |
|
"name": "model.layers.17.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
2048, |
|
256 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2097152, |
|
"byteOffset": 15929344 |
|
}, |
|
{ |
|
"name": "model.layers.17.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
2048, |
|
64 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 262144, |
|
"byteOffset": 18026496 |
|
}, |
|
{ |
|
"name": "model.layers.18.input_layernorm.weight", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 18288640 |
|
}, |
|
{ |
|
"name": "model.layers.18.mlp.down_proj.q_weight", |
|
"shape": [ |
|
2048, |
|
704 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5767168, |
|
"byteOffset": 18292736 |
|
}, |
|
{ |
|
"name": "model.layers.18.mlp.down_proj.q_scale", |
|
"shape": [ |
|
2048, |
|
176 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 720896, |
|
"byteOffset": 24059904 |
|
} |
|
], |
|
"md5sum": "715aec75e345801dfb2b515cda65d382" |
|
}, |
|
{ |
|
"dataPath": "params_shard_14.bin", |
|
"format": "raw-shard", |
|
"nbytes": 24780800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.18.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
11264, |
|
256 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 11534336, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.18.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
11264, |
|
64 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1441792, |
|
"byteOffset": 11534336 |
|
}, |
|
{ |
|
"name": "model.layers.18.post_attention_layernorm.weight", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 12976128 |
|
}, |
|
{ |
|
"name": "model.layers.18.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
2560, |
|
256 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2621440, |
|
"byteOffset": 12980224 |
|
}, |
|
{ |
|
"name": "model.layers.18.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
2560, |
|
64 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 327680, |
|
"byteOffset": 15601664 |
|
}, |
|
{ |
|
"name": "model.layers.18.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
2048, |
|
256 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2097152, |
|
"byteOffset": 15929344 |
|
}, |
|
{ |
|
"name": "model.layers.18.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
2048, |
|
64 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 262144, |
|
"byteOffset": 18026496 |
|
}, |
|
{ |
|
"name": "model.layers.19.input_layernorm.weight", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 18288640 |
|
}, |
|
{ |
|
"name": "model.layers.19.mlp.down_proj.q_weight", |
|
"shape": [ |
|
2048, |
|
704 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5767168, |
|
"byteOffset": 18292736 |
|
}, |
|
{ |
|
"name": "model.layers.19.mlp.down_proj.q_scale", |
|
"shape": [ |
|
2048, |
|
176 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 720896, |
|
"byteOffset": 24059904 |
|
} |
|
], |
|
"md5sum": "d5790615c3c2626be51ff0fc3a34fa1a" |
|
}, |
|
{ |
|
"dataPath": "params_shard_15.bin", |
|
"format": "raw-shard", |
|
"nbytes": 24780800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.19.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
11264, |
|
256 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 11534336, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.19.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
11264, |
|
64 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1441792, |
|
"byteOffset": 11534336 |
|
}, |
|
{ |
|
"name": "model.layers.19.post_attention_layernorm.weight", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 12976128 |
|
}, |
|
{ |
|
"name": "model.layers.19.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
2560, |
|
256 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2621440, |
|
"byteOffset": 12980224 |
|
}, |
|
{ |
|
"name": "model.layers.19.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
2560, |
|
64 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 327680, |
|
"byteOffset": 15601664 |
|
}, |
|
{ |
|
"name": "model.layers.19.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
2048, |
|
256 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2097152, |
|
"byteOffset": 15929344 |
|
}, |
|
{ |
|
"name": "model.layers.19.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
2048, |
|
64 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 262144, |
|
"byteOffset": 18026496 |
|
}, |
|
{ |
|
"name": "model.layers.2.input_layernorm.weight", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 18288640 |
|
}, |
|
{ |
|
"name": "model.layers.2.mlp.down_proj.q_weight", |
|
"shape": [ |
|
2048, |
|
704 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5767168, |
|
"byteOffset": 18292736 |
|
}, |
|
{ |
|
"name": "model.layers.2.mlp.down_proj.q_scale", |
|
"shape": [ |
|
2048, |
|
176 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 720896, |
|
"byteOffset": 24059904 |
|
} |
|
], |
|
"md5sum": "d9bd6d310275218595c1d6484617426a" |
|
}, |
|
{ |
|
"dataPath": "params_shard_16.bin", |
|
"format": "raw-shard", |
|
"nbytes": 24780800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.2.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
11264, |
|
256 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 11534336, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.2.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
11264, |
|
64 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1441792, |
|
"byteOffset": 11534336 |
|
}, |
|
{ |
|
"name": "model.layers.2.post_attention_layernorm.weight", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 12976128 |
|
}, |
|
{ |
|
"name": "model.layers.2.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
2560, |
|
256 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2621440, |
|
"byteOffset": 12980224 |
|
}, |
|
{ |
|
"name": "model.layers.2.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
2560, |
|
64 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 327680, |
|
"byteOffset": 15601664 |
|
}, |
|
{ |
|
"name": "model.layers.2.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
2048, |
|
256 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2097152, |
|
"byteOffset": 15929344 |
|
}, |
|
{ |
|
"name": "model.layers.2.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
2048, |
|
64 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 262144, |
|
"byteOffset": 18026496 |
|
}, |
|
{ |
|
"name": "model.layers.20.input_layernorm.weight", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 18288640 |
|
}, |
|
{ |
|
"name": "model.layers.20.mlp.down_proj.q_weight", |
|
"shape": [ |
|
2048, |
|
704 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5767168, |
|
"byteOffset": 18292736 |
|
}, |
|
{ |
|
"name": "model.layers.20.mlp.down_proj.q_scale", |
|
"shape": [ |
|
2048, |
|
176 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 720896, |
|
"byteOffset": 24059904 |
|
} |
|
], |
|
"md5sum": "955a56034913a0475558510118fce4a2" |
|
}, |
|
{ |
|
"dataPath": "params_shard_17.bin", |
|
"format": "raw-shard", |
|
"nbytes": 24780800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.20.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
11264, |
|
256 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 11534336, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.20.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
11264, |
|
64 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1441792, |
|
"byteOffset": 11534336 |
|
}, |
|
{ |
|
"name": "model.layers.20.post_attention_layernorm.weight", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 12976128 |
|
}, |
|
{ |
|
"name": "model.layers.20.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
2560, |
|
256 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2621440, |
|
"byteOffset": 12980224 |
|
}, |
|
{ |
|
"name": "model.layers.20.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
2560, |
|
64 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 327680, |
|
"byteOffset": 15601664 |
|
}, |
|
{ |
|
"name": "model.layers.20.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
2048, |
|
256 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2097152, |
|
"byteOffset": 15929344 |
|
}, |
|
{ |
|
"name": "model.layers.20.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
2048, |
|
64 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 262144, |
|
"byteOffset": 18026496 |
|
}, |
|
{ |
|
"name": "model.layers.21.input_layernorm.weight", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 18288640 |
|
}, |
|
{ |
|
"name": "model.layers.21.mlp.down_proj.q_weight", |
|
"shape": [ |
|
2048, |
|
704 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5767168, |
|
"byteOffset": 18292736 |
|
}, |
|
{ |
|
"name": "model.layers.21.mlp.down_proj.q_scale", |
|
"shape": [ |
|
2048, |
|
176 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 720896, |
|
"byteOffset": 24059904 |
|
} |
|
], |
|
"md5sum": "e264ee20d99d95912760bafd8c76e2d0" |
|
}, |
|
{ |
|
"dataPath": "params_shard_18.bin", |
|
"format": "raw-shard", |
|
"nbytes": 24780800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.21.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
11264, |
|
256 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 11534336, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.21.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
11264, |
|
64 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1441792, |
|
"byteOffset": 11534336 |
|
}, |
|
{ |
|
"name": "model.layers.21.post_attention_layernorm.weight", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 12976128 |
|
}, |
|
{ |
|
"name": "model.layers.21.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
2560, |
|
256 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2621440, |
|
"byteOffset": 12980224 |
|
}, |
|
{ |
|
"name": "model.layers.21.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
2560, |
|
64 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 327680, |
|
"byteOffset": 15601664 |
|
}, |
|
{ |
|
"name": "model.layers.21.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
2048, |
|
256 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2097152, |
|
"byteOffset": 15929344 |
|
}, |
|
{ |
|
"name": "model.layers.21.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
2048, |
|
64 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 262144, |
|
"byteOffset": 18026496 |
|
}, |
|
{ |
|
"name": "model.layers.3.input_layernorm.weight", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 18288640 |
|
}, |
|
{ |
|
"name": "model.layers.3.mlp.down_proj.q_weight", |
|
"shape": [ |
|
2048, |
|
704 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5767168, |
|
"byteOffset": 18292736 |
|
}, |
|
{ |
|
"name": "model.layers.3.mlp.down_proj.q_scale", |
|
"shape": [ |
|
2048, |
|
176 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 720896, |
|
"byteOffset": 24059904 |
|
} |
|
], |
|
"md5sum": "6df816583a637670927e9adc7ee55b56" |
|
}, |
|
{ |
|
"dataPath": "params_shard_19.bin", |
|
"format": "raw-shard", |
|
"nbytes": 24780800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.3.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
11264, |
|
256 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 11534336, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.3.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
11264, |
|
64 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1441792, |
|
"byteOffset": 11534336 |
|
}, |
|
{ |
|
"name": "model.layers.3.post_attention_layernorm.weight", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 12976128 |
|
}, |
|
{ |
|
"name": "model.layers.3.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
2560, |
|
256 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2621440, |
|
"byteOffset": 12980224 |
|
}, |
|
{ |
|
"name": "model.layers.3.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
2560, |
|
64 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 327680, |
|
"byteOffset": 15601664 |
|
}, |
|
{ |
|
"name": "model.layers.3.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
2048, |
|
256 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2097152, |
|
"byteOffset": 15929344 |
|
}, |
|
{ |
|
"name": "model.layers.3.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
2048, |
|
64 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 262144, |
|
"byteOffset": 18026496 |
|
}, |
|
{ |
|
"name": "model.layers.4.input_layernorm.weight", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 18288640 |
|
}, |
|
{ |
|
"name": "model.layers.4.mlp.down_proj.q_weight", |
|
"shape": [ |
|
2048, |
|
704 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5767168, |
|
"byteOffset": 18292736 |
|
}, |
|
{ |
|
"name": "model.layers.4.mlp.down_proj.q_scale", |
|
"shape": [ |
|
2048, |
|
176 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 720896, |
|
"byteOffset": 24059904 |
|
} |
|
], |
|
"md5sum": "20d577ebe3dff0dbe6b1f32e87604d59" |
|
}, |
|
{ |
|
"dataPath": "params_shard_20.bin", |
|
"format": "raw-shard", |
|
"nbytes": 24780800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.4.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
11264, |
|
256 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 11534336, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.4.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
11264, |
|
64 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1441792, |
|
"byteOffset": 11534336 |
|
}, |
|
{ |
|
"name": "model.layers.4.post_attention_layernorm.weight", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 12976128 |
|
}, |
|
{ |
|
"name": "model.layers.4.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
2560, |
|
256 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2621440, |
|
"byteOffset": 12980224 |
|
}, |
|
{ |
|
"name": "model.layers.4.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
2560, |
|
64 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 327680, |
|
"byteOffset": 15601664 |
|
}, |
|
{ |
|
"name": "model.layers.4.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
2048, |
|
256 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2097152, |
|
"byteOffset": 15929344 |
|
}, |
|
{ |
|
"name": "model.layers.4.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
2048, |
|
64 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 262144, |
|
"byteOffset": 18026496 |
|
}, |
|
{ |
|
"name": "model.layers.5.input_layernorm.weight", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 18288640 |
|
}, |
|
{ |
|
"name": "model.layers.5.mlp.down_proj.q_weight", |
|
"shape": [ |
|
2048, |
|
704 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5767168, |
|
"byteOffset": 18292736 |
|
}, |
|
{ |
|
"name": "model.layers.5.mlp.down_proj.q_scale", |
|
"shape": [ |
|
2048, |
|
176 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 720896, |
|
"byteOffset": 24059904 |
|
} |
|
], |
|
"md5sum": "740f9acb4525b2383170be87bb22e7a0" |
|
}, |
|
{ |
|
"dataPath": "params_shard_21.bin", |
|
"format": "raw-shard", |
|
"nbytes": 24780800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.5.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
11264, |
|
256 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 11534336, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.5.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
11264, |
|
64 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1441792, |
|
"byteOffset": 11534336 |
|
}, |
|
{ |
|
"name": "model.layers.5.post_attention_layernorm.weight", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 12976128 |
|
}, |
|
{ |
|
"name": "model.layers.5.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
2560, |
|
256 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2621440, |
|
"byteOffset": 12980224 |
|
}, |
|
{ |
|
"name": "model.layers.5.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
2560, |
|
64 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 327680, |
|
"byteOffset": 15601664 |
|
}, |
|
{ |
|
"name": "model.layers.5.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
2048, |
|
256 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2097152, |
|
"byteOffset": 15929344 |
|
}, |
|
{ |
|
"name": "model.layers.5.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
2048, |
|
64 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 262144, |
|
"byteOffset": 18026496 |
|
}, |
|
{ |
|
"name": "model.layers.6.input_layernorm.weight", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 18288640 |
|
}, |
|
{ |
|
"name": "model.layers.6.mlp.down_proj.q_weight", |
|
"shape": [ |
|
2048, |
|
704 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5767168, |
|
"byteOffset": 18292736 |
|
}, |
|
{ |
|
"name": "model.layers.6.mlp.down_proj.q_scale", |
|
"shape": [ |
|
2048, |
|
176 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 720896, |
|
"byteOffset": 24059904 |
|
} |
|
], |
|
"md5sum": "eccaea4f41ba41cb9a61adb8d30778f2" |
|
}, |
|
{ |
|
"dataPath": "params_shard_22.bin", |
|
"format": "raw-shard", |
|
"nbytes": 24780800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.6.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
11264, |
|
256 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 11534336, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.6.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
11264, |
|
64 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1441792, |
|
"byteOffset": 11534336 |
|
}, |
|
{ |
|
"name": "model.layers.6.post_attention_layernorm.weight", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 12976128 |
|
}, |
|
{ |
|
"name": "model.layers.6.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
2560, |
|
256 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2621440, |
|
"byteOffset": 12980224 |
|
}, |
|
{ |
|
"name": "model.layers.6.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
2560, |
|
64 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 327680, |
|
"byteOffset": 15601664 |
|
}, |
|
{ |
|
"name": "model.layers.6.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
2048, |
|
256 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2097152, |
|
"byteOffset": 15929344 |
|
}, |
|
{ |
|
"name": "model.layers.6.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
2048, |
|
64 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 262144, |
|
"byteOffset": 18026496 |
|
}, |
|
{ |
|
"name": "model.layers.7.input_layernorm.weight", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 18288640 |
|
}, |
|
{ |
|
"name": "model.layers.7.mlp.down_proj.q_weight", |
|
"shape": [ |
|
2048, |
|
704 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5767168, |
|
"byteOffset": 18292736 |
|
}, |
|
{ |
|
"name": "model.layers.7.mlp.down_proj.q_scale", |
|
"shape": [ |
|
2048, |
|
176 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 720896, |
|
"byteOffset": 24059904 |
|
} |
|
], |
|
"md5sum": "13ae56bbebe69cf1bf4b269193bf55b1" |
|
}, |
|
{ |
|
"dataPath": "params_shard_23.bin", |
|
"format": "raw-shard", |
|
"nbytes": 24780800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.7.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
11264, |
|
256 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 11534336, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.7.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
11264, |
|
64 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1441792, |
|
"byteOffset": 11534336 |
|
}, |
|
{ |
|
"name": "model.layers.7.post_attention_layernorm.weight", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 12976128 |
|
}, |
|
{ |
|
"name": "model.layers.7.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
2560, |
|
256 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2621440, |
|
"byteOffset": 12980224 |
|
}, |
|
{ |
|
"name": "model.layers.7.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
2560, |
|
64 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 327680, |
|
"byteOffset": 15601664 |
|
}, |
|
{ |
|
"name": "model.layers.7.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
2048, |
|
256 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2097152, |
|
"byteOffset": 15929344 |
|
}, |
|
{ |
|
"name": "model.layers.7.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
2048, |
|
64 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 262144, |
|
"byteOffset": 18026496 |
|
}, |
|
{ |
|
"name": "model.layers.8.input_layernorm.weight", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 18288640 |
|
}, |
|
{ |
|
"name": "model.layers.8.mlp.down_proj.q_weight", |
|
"shape": [ |
|
2048, |
|
704 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5767168, |
|
"byteOffset": 18292736 |
|
}, |
|
{ |
|
"name": "model.layers.8.mlp.down_proj.q_scale", |
|
"shape": [ |
|
2048, |
|
176 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 720896, |
|
"byteOffset": 24059904 |
|
} |
|
], |
|
"md5sum": "251e4c557bc60412e9b0180f8a246945" |
|
}, |
|
{ |
|
"dataPath": "params_shard_24.bin", |
|
"format": "raw-shard", |
|
"nbytes": 24780800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.8.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
11264, |
|
256 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 11534336, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.8.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
11264, |
|
64 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1441792, |
|
"byteOffset": 11534336 |
|
}, |
|
{ |
|
"name": "model.layers.8.post_attention_layernorm.weight", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 12976128 |
|
}, |
|
{ |
|
"name": "model.layers.8.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
2560, |
|
256 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2621440, |
|
"byteOffset": 12980224 |
|
}, |
|
{ |
|
"name": "model.layers.8.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
2560, |
|
64 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 327680, |
|
"byteOffset": 15601664 |
|
}, |
|
{ |
|
"name": "model.layers.8.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
2048, |
|
256 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2097152, |
|
"byteOffset": 15929344 |
|
}, |
|
{ |
|
"name": "model.layers.8.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
2048, |
|
64 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 262144, |
|
"byteOffset": 18026496 |
|
}, |
|
{ |
|
"name": "model.layers.9.input_layernorm.weight", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 18288640 |
|
}, |
|
{ |
|
"name": "model.layers.9.mlp.down_proj.q_weight", |
|
"shape": [ |
|
2048, |
|
704 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 5767168, |
|
"byteOffset": 18292736 |
|
}, |
|
{ |
|
"name": "model.layers.9.mlp.down_proj.q_scale", |
|
"shape": [ |
|
2048, |
|
176 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 720896, |
|
"byteOffset": 24059904 |
|
} |
|
], |
|
"md5sum": "3f8563933d4248222bea59edc6f84444" |
|
}, |
|
{ |
|
"dataPath": "params_shard_25.bin", |
|
"format": "raw-shard", |
|
"nbytes": 18292736, |
|
"records": [ |
|
{ |
|
"name": "model.layers.9.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
11264, |
|
256 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 11534336, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.9.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
11264, |
|
64 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1441792, |
|
"byteOffset": 11534336 |
|
}, |
|
{ |
|
"name": "model.layers.9.post_attention_layernorm.weight", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 12976128 |
|
}, |
|
{ |
|
"name": "model.layers.9.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
2560, |
|
256 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2621440, |
|
"byteOffset": 12980224 |
|
}, |
|
{ |
|
"name": "model.layers.9.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
2560, |
|
64 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 327680, |
|
"byteOffset": 15601664 |
|
}, |
|
{ |
|
"name": "model.layers.9.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
2048, |
|
256 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2097152, |
|
"byteOffset": 15929344 |
|
}, |
|
{ |
|
"name": "model.layers.9.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
2048, |
|
64 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 262144, |
|
"byteOffset": 18026496 |
|
}, |
|
{ |
|
"name": "model.norm.weight", |
|
"shape": [ |
|
2048 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 4096, |
|
"byteOffset": 18288640 |
|
} |
|
], |
|
"md5sum": "415e1da793d4f918f3ffadcacad262bd" |
|
} |
|
] |
|
} |