|
{ |
|
"metadata": { |
|
"ParamSize": 389, |
|
"ParamBytes": 21111499264.0, |
|
"BitsPerParam": 3.6163146641450146 |
|
}, |
|
"records": [ |
|
{ |
|
"dataPath": "params_shard_0.bin", |
|
"format": "raw-shard", |
|
"nbytes": 52736000, |
|
"records": [ |
|
{ |
|
"name": "lm_head.q_weight", |
|
"shape": [ |
|
32000, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 52736000, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "ac3a27c922a274a2c8feac7882621799" |
|
}, |
|
{ |
|
"dataPath": "params_shard_1.bin", |
|
"format": "raw-shard", |
|
"nbytes": 378011648, |
|
"records": [ |
|
{ |
|
"name": "model.layers.30.moe.e1_e3.q_weight", |
|
"shape": [ |
|
8, |
|
28672, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 378011648, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "f0f9bdf906baea62b059eb31744b6c55" |
|
}, |
|
{ |
|
"dataPath": "params_shard_2.bin", |
|
"format": "raw-shard", |
|
"nbytes": 47251456, |
|
"records": [ |
|
{ |
|
"name": "model.layers.30.moe.e1_e3.q_scale", |
|
"shape": [ |
|
8, |
|
28672, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 47251456, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "35fba6d97f9d9e6fd7284f1b514fae53" |
|
}, |
|
{ |
|
"dataPath": "params_shard_3.bin", |
|
"format": "raw-shard", |
|
"nbytes": 188219392, |
|
"records": [ |
|
{ |
|
"name": "model.layers.30.moe.e2.q_weight", |
|
"shape": [ |
|
8, |
|
4096, |
|
1436 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 188219392, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "6b26ade735417a3c93165daa00f6b594" |
|
}, |
|
{ |
|
"dataPath": "params_shard_4.bin", |
|
"format": "raw-shard", |
|
"nbytes": 378011648, |
|
"records": [ |
|
{ |
|
"name": "model.layers.31.moe.e1_e3.q_weight", |
|
"shape": [ |
|
8, |
|
28672, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 378011648, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "412dc5e2f782ed24be1cdd1ac9b15621" |
|
}, |
|
{ |
|
"dataPath": "params_shard_5.bin", |
|
"format": "raw-shard", |
|
"nbytes": 47251456, |
|
"records": [ |
|
{ |
|
"name": "model.layers.31.moe.e1_e3.q_scale", |
|
"shape": [ |
|
8, |
|
28672, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 47251456, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "dbb75cc00221cbe67ac9eba40ddf972d" |
|
}, |
|
{ |
|
"dataPath": "params_shard_6.bin", |
|
"format": "raw-shard", |
|
"nbytes": 188219392, |
|
"records": [ |
|
{ |
|
"name": "model.layers.31.moe.e2.q_weight", |
|
"shape": [ |
|
8, |
|
4096, |
|
1436 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 188219392, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "9eedc92942af189eb8e4046369e6b674" |
|
}, |
|
{ |
|
"dataPath": "params_shard_7.bin", |
|
"format": "raw-shard", |
|
"nbytes": 23527424, |
|
"records": [ |
|
{ |
|
"name": "model.layers.31.moe.e2.q_scale", |
|
"shape": [ |
|
8, |
|
4096, |
|
359 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 23527424, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "5ffc85079d255591871beed2e4638a41" |
|
}, |
|
{ |
|
"dataPath": "params_shard_8.bin", |
|
"format": "raw-shard", |
|
"nbytes": 30167024, |
|
"records": [ |
|
{ |
|
"name": "lm_head.q_scale", |
|
"shape": [ |
|
32000, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6592000, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.30.moe.e2.q_scale", |
|
"shape": [ |
|
8, |
|
4096, |
|
359 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 23527424, |
|
"byteOffset": 6592000 |
|
}, |
|
{ |
|
"name": "model.layers.30.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 30119424 |
|
}, |
|
{ |
|
"name": "model.layers.30.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 30127616 |
|
}, |
|
{ |
|
"name": "model.layers.31.moe.gate.q_weight", |
|
"shape": [ |
|
8, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 13184, |
|
"byteOffset": 30135808 |
|
}, |
|
{ |
|
"name": "model.layers.31.moe.gate.q_scale", |
|
"shape": [ |
|
8, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1648, |
|
"byteOffset": 30148992 |
|
}, |
|
{ |
|
"name": "model.layers.31.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 30150640 |
|
}, |
|
{ |
|
"name": "model.layers.31.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 30158832 |
|
} |
|
], |
|
"md5sum": "5d8798b33aa13042b2c87d0b1686cbc7" |
|
}, |
|
{ |
|
"dataPath": "params_shard_9.bin", |
|
"format": "raw-shard", |
|
"nbytes": 52736000, |
|
"records": [ |
|
{ |
|
"name": "model.embed_tokens.q_weight", |
|
"shape": [ |
|
32000, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 52736000, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "636176f0b40b645e955bdeade38bcda8" |
|
}, |
|
{ |
|
"dataPath": "params_shard_10.bin", |
|
"format": "raw-shard", |
|
"nbytes": 378011648, |
|
"records": [ |
|
{ |
|
"name": "model.layers.0.moe.e1_e3.q_weight", |
|
"shape": [ |
|
8, |
|
28672, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 378011648, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "5f931f0de474f26cc381700853d524c4" |
|
}, |
|
{ |
|
"dataPath": "params_shard_11.bin", |
|
"format": "raw-shard", |
|
"nbytes": 47251456, |
|
"records": [ |
|
{ |
|
"name": "model.layers.0.moe.e1_e3.q_scale", |
|
"shape": [ |
|
8, |
|
28672, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 47251456, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "a10fcadde0344542bea240c4c41d9936" |
|
}, |
|
{ |
|
"dataPath": "params_shard_12.bin", |
|
"format": "raw-shard", |
|
"nbytes": 188219392, |
|
"records": [ |
|
{ |
|
"name": "model.layers.0.moe.e2.q_weight", |
|
"shape": [ |
|
8, |
|
4096, |
|
1436 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 188219392, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "9f8103400e36737fedc16c2530a96c9a" |
|
}, |
|
{ |
|
"dataPath": "params_shard_13.bin", |
|
"format": "raw-shard", |
|
"nbytes": 23527424, |
|
"records": [ |
|
{ |
|
"name": "model.layers.0.moe.e2.q_scale", |
|
"shape": [ |
|
8, |
|
4096, |
|
359 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 23527424, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "959ddb2cce68b619873ee734e2af023c" |
|
}, |
|
{ |
|
"dataPath": "params_shard_14.bin", |
|
"format": "raw-shard", |
|
"nbytes": 25616368, |
|
"records": [ |
|
{ |
|
"name": "model.layers.31.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
6144, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10125312, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.31.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
6144, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1265664, |
|
"byteOffset": 10125312 |
|
}, |
|
{ |
|
"name": "model.layers.31.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6750208, |
|
"byteOffset": 11390976 |
|
}, |
|
{ |
|
"name": "model.layers.31.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 843776, |
|
"byteOffset": 18141184 |
|
}, |
|
{ |
|
"name": "model.norm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 18984960 |
|
}, |
|
{ |
|
"name": "model.embed_tokens.q_scale", |
|
"shape": [ |
|
32000, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6592000, |
|
"byteOffset": 18993152 |
|
}, |
|
{ |
|
"name": "model.layers.0.moe.gate.q_weight", |
|
"shape": [ |
|
8, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 13184, |
|
"byteOffset": 25585152 |
|
}, |
|
{ |
|
"name": "model.layers.0.moe.gate.q_scale", |
|
"shape": [ |
|
8, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1648, |
|
"byteOffset": 25598336 |
|
}, |
|
{ |
|
"name": "model.layers.0.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 25599984 |
|
}, |
|
{ |
|
"name": "model.layers.0.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 25608176 |
|
} |
|
], |
|
"md5sum": "1f210c572f3e30bf8cf83be783eba4c1" |
|
}, |
|
{ |
|
"dataPath": "params_shard_15.bin", |
|
"format": "raw-shard", |
|
"nbytes": 378011648, |
|
"records": [ |
|
{ |
|
"name": "model.layers.1.moe.e1_e3.q_weight", |
|
"shape": [ |
|
8, |
|
28672, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 378011648, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "4b886ea786c2931650cb7af447cf28cb" |
|
}, |
|
{ |
|
"dataPath": "params_shard_16.bin", |
|
"format": "raw-shard", |
|
"nbytes": 47251456, |
|
"records": [ |
|
{ |
|
"name": "model.layers.1.moe.e1_e3.q_scale", |
|
"shape": [ |
|
8, |
|
28672, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 47251456, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "0a0b70f6cdae34fc6a059e66d575a444" |
|
}, |
|
{ |
|
"dataPath": "params_shard_17.bin", |
|
"format": "raw-shard", |
|
"nbytes": 188219392, |
|
"records": [ |
|
{ |
|
"name": "model.layers.1.moe.e2.q_weight", |
|
"shape": [ |
|
8, |
|
4096, |
|
1436 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 188219392, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "f01bae64888ef7311e9af13f89279583" |
|
}, |
|
{ |
|
"dataPath": "params_shard_18.bin", |
|
"format": "raw-shard", |
|
"nbytes": 23527424, |
|
"records": [ |
|
{ |
|
"name": "model.layers.1.moe.e2.q_scale", |
|
"shape": [ |
|
8, |
|
4096, |
|
359 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 23527424, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "a903e2bc174fa963f62ec8da3f594005" |
|
}, |
|
{ |
|
"dataPath": "params_shard_19.bin", |
|
"format": "raw-shard", |
|
"nbytes": 30390768, |
|
"records": [ |
|
{ |
|
"name": "model.layers.0.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
6144, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10125312, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.0.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
6144, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1265664, |
|
"byteOffset": 10125312 |
|
}, |
|
{ |
|
"name": "model.layers.0.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6750208, |
|
"byteOffset": 11390976 |
|
}, |
|
{ |
|
"name": "model.layers.0.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 843776, |
|
"byteOffset": 18141184 |
|
}, |
|
{ |
|
"name": "model.layers.1.moe.gate.q_weight", |
|
"shape": [ |
|
8, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 13184, |
|
"byteOffset": 18984960 |
|
}, |
|
{ |
|
"name": "model.layers.1.moe.gate.q_scale", |
|
"shape": [ |
|
8, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1648, |
|
"byteOffset": 18998144 |
|
}, |
|
{ |
|
"name": "model.layers.1.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
6144, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10125312, |
|
"byteOffset": 18999792 |
|
}, |
|
{ |
|
"name": "model.layers.1.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
6144, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1265664, |
|
"byteOffset": 29125104 |
|
} |
|
], |
|
"md5sum": "290539959e9e6810e07acffb696f1385" |
|
}, |
|
{ |
|
"dataPath": "params_shard_20.bin", |
|
"format": "raw-shard", |
|
"nbytes": 378011648, |
|
"records": [ |
|
{ |
|
"name": "model.layers.2.moe.e1_e3.q_weight", |
|
"shape": [ |
|
8, |
|
28672, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 378011648, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "0783a0968df03d28d2145c833004e6a7" |
|
}, |
|
{ |
|
"dataPath": "params_shard_21.bin", |
|
"format": "raw-shard", |
|
"nbytes": 47251456, |
|
"records": [ |
|
{ |
|
"name": "model.layers.2.moe.e1_e3.q_scale", |
|
"shape": [ |
|
8, |
|
28672, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 47251456, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "d0c9d6c467d27a946dcbc57d33777615" |
|
}, |
|
{ |
|
"dataPath": "params_shard_22.bin", |
|
"format": "raw-shard", |
|
"nbytes": 188219392, |
|
"records": [ |
|
{ |
|
"name": "model.layers.2.moe.e2.q_weight", |
|
"shape": [ |
|
8, |
|
4096, |
|
1436 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 188219392, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "e428051521ea9c92330869ef7ab7abb2" |
|
}, |
|
{ |
|
"dataPath": "params_shard_23.bin", |
|
"format": "raw-shard", |
|
"nbytes": 31169008, |
|
"records": [ |
|
{ |
|
"name": "model.layers.1.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6750208, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.1.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 843776, |
|
"byteOffset": 6750208 |
|
}, |
|
{ |
|
"name": "model.layers.1.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 7593984 |
|
}, |
|
{ |
|
"name": "model.layers.1.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 7602176 |
|
}, |
|
{ |
|
"name": "model.layers.2.moe.e2.q_scale", |
|
"shape": [ |
|
8, |
|
4096, |
|
359 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 23527424, |
|
"byteOffset": 7610368 |
|
}, |
|
{ |
|
"name": "model.layers.2.moe.gate.q_weight", |
|
"shape": [ |
|
8, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 13184, |
|
"byteOffset": 31137792 |
|
}, |
|
{ |
|
"name": "model.layers.2.moe.gate.q_scale", |
|
"shape": [ |
|
8, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1648, |
|
"byteOffset": 31150976 |
|
}, |
|
{ |
|
"name": "model.layers.2.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 31152624 |
|
}, |
|
{ |
|
"name": "model.layers.2.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 31160816 |
|
} |
|
], |
|
"md5sum": "acb59b4e4b64f01ec49abdc9e3201143" |
|
}, |
|
{ |
|
"dataPath": "params_shard_24.bin", |
|
"format": "raw-shard", |
|
"nbytes": 378011648, |
|
"records": [ |
|
{ |
|
"name": "model.layers.3.moe.e1_e3.q_weight", |
|
"shape": [ |
|
8, |
|
28672, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 378011648, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "56ab27bb57dd4e6291126647d061ff45" |
|
}, |
|
{ |
|
"dataPath": "params_shard_25.bin", |
|
"format": "raw-shard", |
|
"nbytes": 47251456, |
|
"records": [ |
|
{ |
|
"name": "model.layers.3.moe.e1_e3.q_scale", |
|
"shape": [ |
|
8, |
|
28672, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 47251456, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "09a9c1625d1265f31ff803543bea0212" |
|
}, |
|
{ |
|
"dataPath": "params_shard_26.bin", |
|
"format": "raw-shard", |
|
"nbytes": 188219392, |
|
"records": [ |
|
{ |
|
"name": "model.layers.3.moe.e2.q_weight", |
|
"shape": [ |
|
8, |
|
4096, |
|
1436 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 188219392, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "d5e18af51789ddc055558f0ba1dff95c" |
|
}, |
|
{ |
|
"dataPath": "params_shard_27.bin", |
|
"format": "raw-shard", |
|
"nbytes": 23527424, |
|
"records": [ |
|
{ |
|
"name": "model.layers.3.moe.e2.q_scale", |
|
"shape": [ |
|
8, |
|
4096, |
|
359 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 23527424, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "9831a0cb32bbf0fcb9fa54df8aa30c21" |
|
}, |
|
{ |
|
"dataPath": "params_shard_28.bin", |
|
"format": "raw-shard", |
|
"nbytes": 30390768, |
|
"records": [ |
|
{ |
|
"name": "model.layers.2.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
6144, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10125312, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.2.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
6144, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1265664, |
|
"byteOffset": 10125312 |
|
}, |
|
{ |
|
"name": "model.layers.2.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6750208, |
|
"byteOffset": 11390976 |
|
}, |
|
{ |
|
"name": "model.layers.2.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 843776, |
|
"byteOffset": 18141184 |
|
}, |
|
{ |
|
"name": "model.layers.3.moe.gate.q_weight", |
|
"shape": [ |
|
8, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 13184, |
|
"byteOffset": 18984960 |
|
}, |
|
{ |
|
"name": "model.layers.3.moe.gate.q_scale", |
|
"shape": [ |
|
8, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1648, |
|
"byteOffset": 18998144 |
|
}, |
|
{ |
|
"name": "model.layers.3.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
6144, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10125312, |
|
"byteOffset": 18999792 |
|
}, |
|
{ |
|
"name": "model.layers.3.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
6144, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1265664, |
|
"byteOffset": 29125104 |
|
} |
|
], |
|
"md5sum": "1bc7de22a3f001e5d49a753af52c58fe" |
|
}, |
|
{ |
|
"dataPath": "params_shard_29.bin", |
|
"format": "raw-shard", |
|
"nbytes": 378011648, |
|
"records": [ |
|
{ |
|
"name": "model.layers.10.moe.e1_e3.q_weight", |
|
"shape": [ |
|
8, |
|
28672, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 378011648, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "32d98d997a007f3bfc3b2f6d6370cb3d" |
|
}, |
|
{ |
|
"dataPath": "params_shard_30.bin", |
|
"format": "raw-shard", |
|
"nbytes": 47251456, |
|
"records": [ |
|
{ |
|
"name": "model.layers.10.moe.e1_e3.q_scale", |
|
"shape": [ |
|
8, |
|
28672, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 47251456, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "5b2f14f04174c52abfc14d6683bde9f6" |
|
}, |
|
{ |
|
"dataPath": "params_shard_31.bin", |
|
"format": "raw-shard", |
|
"nbytes": 188219392, |
|
"records": [ |
|
{ |
|
"name": "model.layers.10.moe.e2.q_weight", |
|
"shape": [ |
|
8, |
|
4096, |
|
1436 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 188219392, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "03daefe9aaa29879e18f413d90b9b7c0" |
|
}, |
|
{ |
|
"dataPath": "params_shard_32.bin", |
|
"format": "raw-shard", |
|
"nbytes": 31136240, |
|
"records": [ |
|
{ |
|
"name": "model.layers.3.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6750208, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.3.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 843776, |
|
"byteOffset": 6750208 |
|
}, |
|
{ |
|
"name": "model.layers.10.moe.e2.q_scale", |
|
"shape": [ |
|
8, |
|
4096, |
|
359 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 23527424, |
|
"byteOffset": 7593984 |
|
}, |
|
{ |
|
"name": "model.layers.10.moe.gate.q_weight", |
|
"shape": [ |
|
8, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 13184, |
|
"byteOffset": 31121408 |
|
}, |
|
{ |
|
"name": "model.layers.10.moe.gate.q_scale", |
|
"shape": [ |
|
8, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1648, |
|
"byteOffset": 31134592 |
|
} |
|
], |
|
"md5sum": "8e9d880e2a10fbf86d9d7dca20d85775" |
|
}, |
|
{ |
|
"dataPath": "params_shard_33.bin", |
|
"format": "raw-shard", |
|
"nbytes": 188219392, |
|
"records": [ |
|
{ |
|
"name": "model.layers.8.moe.e2.q_weight", |
|
"shape": [ |
|
8, |
|
4096, |
|
1436 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 188219392, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "f573a86687ca7ed036f63aa83c92d41b" |
|
}, |
|
{ |
|
"dataPath": "params_shard_34.bin", |
|
"format": "raw-shard", |
|
"nbytes": 23527424, |
|
"records": [ |
|
{ |
|
"name": "model.layers.8.moe.e2.q_scale", |
|
"shape": [ |
|
8, |
|
4096, |
|
359 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 23527424, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "b6d411aa7451a9d682dc5fe710bc14cb" |
|
}, |
|
{ |
|
"dataPath": "params_shard_35.bin", |
|
"format": "raw-shard", |
|
"nbytes": 378011648, |
|
"records": [ |
|
{ |
|
"name": "model.layers.8.moe.e1_e3.q_weight", |
|
"shape": [ |
|
8, |
|
28672, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 378011648, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "24cc152792c3b612dc9d7dfeda17cf2b" |
|
}, |
|
{ |
|
"dataPath": "params_shard_36.bin", |
|
"format": "raw-shard", |
|
"nbytes": 47251456, |
|
"records": [ |
|
{ |
|
"name": "model.layers.8.moe.e1_e3.q_scale", |
|
"shape": [ |
|
8, |
|
28672, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 47251456, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "77c0fa2a226ffaab55d09e91e8236e52" |
|
}, |
|
{ |
|
"dataPath": "params_shard_37.bin", |
|
"format": "raw-shard", |
|
"nbytes": 378011648, |
|
"records": [ |
|
{ |
|
"name": "model.layers.9.moe.e1_e3.q_weight", |
|
"shape": [ |
|
8, |
|
28672, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 378011648, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "c8d233d9661079c4a0ed0fba119be902" |
|
}, |
|
{ |
|
"dataPath": "params_shard_38.bin", |
|
"format": "raw-shard", |
|
"nbytes": 47251456, |
|
"records": [ |
|
{ |
|
"name": "model.layers.9.moe.e1_e3.q_scale", |
|
"shape": [ |
|
8, |
|
28672, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 47251456, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "41f174a358e3d9ab743b28cac77970e3" |
|
}, |
|
{ |
|
"dataPath": "params_shard_39.bin", |
|
"format": "raw-shard", |
|
"nbytes": 188219392, |
|
"records": [ |
|
{ |
|
"name": "model.layers.9.moe.e2.q_weight", |
|
"shape": [ |
|
8, |
|
4096, |
|
1436 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 188219392, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "61865f4083929642e2eb50636686da39" |
|
}, |
|
{ |
|
"dataPath": "params_shard_40.bin", |
|
"format": "raw-shard", |
|
"nbytes": 23527424, |
|
"records": [ |
|
{ |
|
"name": "model.layers.9.moe.e2.q_scale", |
|
"shape": [ |
|
8, |
|
4096, |
|
359 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 23527424, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "dcb666b973f7f237813d8a8a0c220eb8" |
|
}, |
|
{ |
|
"dataPath": "params_shard_41.bin", |
|
"format": "raw-shard", |
|
"nbytes": 30423536, |
|
"records": [ |
|
{ |
|
"name": "model.layers.10.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
6144, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10125312, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.10.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
6144, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1265664, |
|
"byteOffset": 10125312 |
|
}, |
|
{ |
|
"name": "model.layers.10.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6750208, |
|
"byteOffset": 11390976 |
|
}, |
|
{ |
|
"name": "model.layers.10.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 843776, |
|
"byteOffset": 18141184 |
|
}, |
|
{ |
|
"name": "model.layers.8.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 18984960 |
|
}, |
|
{ |
|
"name": "model.layers.8.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 18993152 |
|
}, |
|
{ |
|
"name": "model.layers.9.moe.gate.q_weight", |
|
"shape": [ |
|
8, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 13184, |
|
"byteOffset": 19001344 |
|
}, |
|
{ |
|
"name": "model.layers.9.moe.gate.q_scale", |
|
"shape": [ |
|
8, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1648, |
|
"byteOffset": 19014528 |
|
}, |
|
{ |
|
"name": "model.layers.9.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 19016176 |
|
}, |
|
{ |
|
"name": "model.layers.9.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 19024368 |
|
}, |
|
{ |
|
"name": "model.layers.9.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
6144, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10125312, |
|
"byteOffset": 19032560 |
|
}, |
|
{ |
|
"name": "model.layers.9.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
6144, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1265664, |
|
"byteOffset": 29157872 |
|
} |
|
], |
|
"md5sum": "e5950f7a75d6ae483596b6a02d0d50ec" |
|
}, |
|
{ |
|
"dataPath": "params_shard_42.bin", |
|
"format": "raw-shard", |
|
"nbytes": 378011648, |
|
"records": [ |
|
{ |
|
"name": "model.layers.11.moe.e1_e3.q_weight", |
|
"shape": [ |
|
8, |
|
28672, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 378011648, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "4ea8f56857f5c1fc36d5dde6e2f0442e" |
|
}, |
|
{ |
|
"dataPath": "params_shard_43.bin", |
|
"format": "raw-shard", |
|
"nbytes": 47251456, |
|
"records": [ |
|
{ |
|
"name": "model.layers.11.moe.e1_e3.q_scale", |
|
"shape": [ |
|
8, |
|
28672, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 47251456, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "535bec0b14716d341afb93266a815723" |
|
}, |
|
{ |
|
"dataPath": "params_shard_44.bin", |
|
"format": "raw-shard", |
|
"nbytes": 188219392, |
|
"records": [ |
|
{ |
|
"name": "model.layers.11.moe.e2.q_weight", |
|
"shape": [ |
|
8, |
|
4096, |
|
1436 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 188219392, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "d6d00ddd4dcdd1cb4d66bf007de4d99f" |
|
}, |
|
{ |
|
"dataPath": "params_shard_45.bin", |
|
"format": "raw-shard", |
|
"nbytes": 31152624, |
|
"records": [ |
|
{ |
|
"name": "model.layers.9.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6750208, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.9.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 843776, |
|
"byteOffset": 6750208 |
|
}, |
|
{ |
|
"name": "model.layers.10.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 7593984 |
|
}, |
|
{ |
|
"name": "model.layers.10.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 7602176 |
|
}, |
|
{ |
|
"name": "model.layers.11.moe.e2.q_scale", |
|
"shape": [ |
|
8, |
|
4096, |
|
359 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 23527424, |
|
"byteOffset": 7610368 |
|
}, |
|
{ |
|
"name": "model.layers.11.moe.gate.q_weight", |
|
"shape": [ |
|
8, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 13184, |
|
"byteOffset": 31137792 |
|
}, |
|
{ |
|
"name": "model.layers.11.moe.gate.q_scale", |
|
"shape": [ |
|
8, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1648, |
|
"byteOffset": 31150976 |
|
} |
|
], |
|
"md5sum": "4643d348a869b46a5ec40f6603ffdc91" |
|
}, |
|
{ |
|
"dataPath": "params_shard_46.bin", |
|
"format": "raw-shard", |
|
"nbytes": 378011648, |
|
"records": [ |
|
{ |
|
"name": "model.layers.12.moe.e1_e3.q_weight", |
|
"shape": [ |
|
8, |
|
28672, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 378011648, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "a0b2cf6f3a6a4931d33d326e1d298e2f" |
|
}, |
|
{ |
|
"dataPath": "params_shard_47.bin", |
|
"format": "raw-shard", |
|
"nbytes": 47251456, |
|
"records": [ |
|
{ |
|
"name": "model.layers.12.moe.e1_e3.q_scale", |
|
"shape": [ |
|
8, |
|
28672, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 47251456, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "b17cd5b0d678f8d184e0b52371c69e72" |
|
}, |
|
{ |
|
"dataPath": "params_shard_48.bin", |
|
"format": "raw-shard", |
|
"nbytes": 188219392, |
|
"records": [ |
|
{ |
|
"name": "model.layers.12.moe.e2.q_weight", |
|
"shape": [ |
|
8, |
|
4096, |
|
1436 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 188219392, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "6519d4c002689fc212e8be97e10a21ae" |
|
}, |
|
{ |
|
"dataPath": "params_shard_49.bin", |
|
"format": "raw-shard", |
|
"nbytes": 23527424, |
|
"records": [ |
|
{ |
|
"name": "model.layers.12.moe.e2.q_scale", |
|
"shape": [ |
|
8, |
|
4096, |
|
359 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 23527424, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "b63991d6aa33f57a8921e59d34ea7fc5" |
|
}, |
|
{ |
|
"dataPath": "params_shard_50.bin", |
|
"format": "raw-shard", |
|
"nbytes": 30423536, |
|
"records": [ |
|
{ |
|
"name": "model.layers.11.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
6144, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10125312, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.11.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
6144, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1265664, |
|
"byteOffset": 10125312 |
|
}, |
|
{ |
|
"name": "model.layers.11.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6750208, |
|
"byteOffset": 11390976 |
|
}, |
|
{ |
|
"name": "model.layers.11.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 843776, |
|
"byteOffset": 18141184 |
|
}, |
|
{ |
|
"name": "model.layers.11.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 18984960 |
|
}, |
|
{ |
|
"name": "model.layers.11.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 18993152 |
|
}, |
|
{ |
|
"name": "model.layers.12.moe.gate.q_weight", |
|
"shape": [ |
|
8, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 13184, |
|
"byteOffset": 19001344 |
|
}, |
|
{ |
|
"name": "model.layers.12.moe.gate.q_scale", |
|
"shape": [ |
|
8, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1648, |
|
"byteOffset": 19014528 |
|
}, |
|
{ |
|
"name": "model.layers.12.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 19016176 |
|
}, |
|
{ |
|
"name": "model.layers.12.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 19024368 |
|
}, |
|
{ |
|
"name": "model.layers.12.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
6144, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10125312, |
|
"byteOffset": 19032560 |
|
}, |
|
{ |
|
"name": "model.layers.12.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
6144, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1265664, |
|
"byteOffset": 29157872 |
|
} |
|
], |
|
"md5sum": "d6045d0efa921bb5665e6a44b291cbbe" |
|
}, |
|
{ |
|
"dataPath": "params_shard_51.bin", |
|
"format": "raw-shard", |
|
"nbytes": 378011648, |
|
"records": [ |
|
{ |
|
"name": "model.layers.13.moe.e1_e3.q_weight", |
|
"shape": [ |
|
8, |
|
28672, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 378011648, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "608acff8552aaefc906fe2319da9289b" |
|
}, |
|
{ |
|
"dataPath": "params_shard_52.bin", |
|
"format": "raw-shard", |
|
"nbytes": 47251456, |
|
"records": [ |
|
{ |
|
"name": "model.layers.13.moe.e1_e3.q_scale", |
|
"shape": [ |
|
8, |
|
28672, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 47251456, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "36c0dbee3c1da2016c45745c5b92952c" |
|
}, |
|
{ |
|
"dataPath": "params_shard_53.bin", |
|
"format": "raw-shard", |
|
"nbytes": 188219392, |
|
"records": [ |
|
{ |
|
"name": "model.layers.13.moe.e2.q_weight", |
|
"shape": [ |
|
8, |
|
4096, |
|
1436 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 188219392, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "c722a1aac8cbdeadf535f091595ac814" |
|
}, |
|
{ |
|
"dataPath": "params_shard_54.bin", |
|
"format": "raw-shard", |
|
"nbytes": 31136240, |
|
"records": [ |
|
{ |
|
"name": "model.layers.12.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6750208, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.12.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 843776, |
|
"byteOffset": 6750208 |
|
}, |
|
{ |
|
"name": "model.layers.13.moe.e2.q_scale", |
|
"shape": [ |
|
8, |
|
4096, |
|
359 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 23527424, |
|
"byteOffset": 7593984 |
|
}, |
|
{ |
|
"name": "model.layers.13.moe.gate.q_weight", |
|
"shape": [ |
|
8, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 13184, |
|
"byteOffset": 31121408 |
|
}, |
|
{ |
|
"name": "model.layers.13.moe.gate.q_scale", |
|
"shape": [ |
|
8, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1648, |
|
"byteOffset": 31134592 |
|
} |
|
], |
|
"md5sum": "4232135edfa7e7a55bed90e0533f04d9" |
|
}, |
|
{ |
|
"dataPath": "params_shard_55.bin", |
|
"format": "raw-shard", |
|
"nbytes": 378011648, |
|
"records": [ |
|
{ |
|
"name": "model.layers.14.moe.e1_e3.q_weight", |
|
"shape": [ |
|
8, |
|
28672, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 378011648, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "f9475494628f598c8bf88913808ae406" |
|
}, |
|
{ |
|
"dataPath": "params_shard_56.bin", |
|
"format": "raw-shard", |
|
"nbytes": 47251456, |
|
"records": [ |
|
{ |
|
"name": "model.layers.14.moe.e1_e3.q_scale", |
|
"shape": [ |
|
8, |
|
28672, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 47251456, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "67e4e5ba70d2ead0045bda96d2d294e8" |
|
}, |
|
{ |
|
"dataPath": "params_shard_57.bin", |
|
"format": "raw-shard", |
|
"nbytes": 188219392, |
|
"records": [ |
|
{ |
|
"name": "model.layers.14.moe.e2.q_weight", |
|
"shape": [ |
|
8, |
|
4096, |
|
1436 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 188219392, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "c0bf37d729e75111bf1348eb22ca308a" |
|
}, |
|
{ |
|
"dataPath": "params_shard_58.bin", |
|
"format": "raw-shard", |
|
"nbytes": 23527424, |
|
"records": [ |
|
{ |
|
"name": "model.layers.14.moe.e2.q_scale", |
|
"shape": [ |
|
8, |
|
4096, |
|
359 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 23527424, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "64bd3b91b562f25661eca248fdf6c3d8" |
|
}, |
|
{ |
|
"dataPath": "params_shard_59.bin", |
|
"format": "raw-shard", |
|
"nbytes": 30423536, |
|
"records": [ |
|
{ |
|
"name": "model.layers.13.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
6144, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10125312, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.13.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
6144, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1265664, |
|
"byteOffset": 10125312 |
|
}, |
|
{ |
|
"name": "model.layers.13.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6750208, |
|
"byteOffset": 11390976 |
|
}, |
|
{ |
|
"name": "model.layers.13.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 843776, |
|
"byteOffset": 18141184 |
|
}, |
|
{ |
|
"name": "model.layers.13.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 18984960 |
|
}, |
|
{ |
|
"name": "model.layers.13.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 18993152 |
|
}, |
|
{ |
|
"name": "model.layers.14.moe.gate.q_weight", |
|
"shape": [ |
|
8, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 13184, |
|
"byteOffset": 19001344 |
|
}, |
|
{ |
|
"name": "model.layers.14.moe.gate.q_scale", |
|
"shape": [ |
|
8, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1648, |
|
"byteOffset": 19014528 |
|
}, |
|
{ |
|
"name": "model.layers.14.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 19016176 |
|
}, |
|
{ |
|
"name": "model.layers.14.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 19024368 |
|
}, |
|
{ |
|
"name": "model.layers.14.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
6144, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10125312, |
|
"byteOffset": 19032560 |
|
}, |
|
{ |
|
"name": "model.layers.14.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
6144, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1265664, |
|
"byteOffset": 29157872 |
|
} |
|
], |
|
"md5sum": "0f000620830d2ab309ee624a2e248aa2" |
|
}, |
|
{ |
|
"dataPath": "params_shard_60.bin", |
|
"format": "raw-shard", |
|
"nbytes": 378011648, |
|
"records": [ |
|
{ |
|
"name": "model.layers.15.moe.e1_e3.q_weight", |
|
"shape": [ |
|
8, |
|
28672, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 378011648, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "bd6f321236a6699fd65fb8739b8391b8" |
|
}, |
|
{ |
|
"dataPath": "params_shard_61.bin", |
|
"format": "raw-shard", |
|
"nbytes": 47251456, |
|
"records": [ |
|
{ |
|
"name": "model.layers.15.moe.e1_e3.q_scale", |
|
"shape": [ |
|
8, |
|
28672, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 47251456, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "da14da2a55c9c3e28cd1dd58da39af7d" |
|
}, |
|
{ |
|
"dataPath": "params_shard_62.bin", |
|
"format": "raw-shard", |
|
"nbytes": 188219392, |
|
"records": [ |
|
{ |
|
"name": "model.layers.15.moe.e2.q_weight", |
|
"shape": [ |
|
8, |
|
4096, |
|
1436 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 188219392, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "afed86116935402e87a3cdb7ecd741fb" |
|
}, |
|
{ |
|
"dataPath": "params_shard_63.bin", |
|
"format": "raw-shard", |
|
"nbytes": 31136240, |
|
"records": [ |
|
{ |
|
"name": "model.layers.14.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6750208, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.14.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 843776, |
|
"byteOffset": 6750208 |
|
}, |
|
{ |
|
"name": "model.layers.15.moe.e2.q_scale", |
|
"shape": [ |
|
8, |
|
4096, |
|
359 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 23527424, |
|
"byteOffset": 7593984 |
|
}, |
|
{ |
|
"name": "model.layers.15.moe.gate.q_weight", |
|
"shape": [ |
|
8, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 13184, |
|
"byteOffset": 31121408 |
|
}, |
|
{ |
|
"name": "model.layers.15.moe.gate.q_scale", |
|
"shape": [ |
|
8, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1648, |
|
"byteOffset": 31134592 |
|
} |
|
], |
|
"md5sum": "fdb086a8dc7277c34e88efdcbcf738f3" |
|
}, |
|
{ |
|
"dataPath": "params_shard_64.bin", |
|
"format": "raw-shard", |
|
"nbytes": 378011648, |
|
"records": [ |
|
{ |
|
"name": "model.layers.16.moe.e1_e3.q_weight", |
|
"shape": [ |
|
8, |
|
28672, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 378011648, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "95aed5afddd7e57ab332e5614084f909" |
|
}, |
|
{ |
|
"dataPath": "params_shard_65.bin", |
|
"format": "raw-shard", |
|
"nbytes": 47251456, |
|
"records": [ |
|
{ |
|
"name": "model.layers.16.moe.e1_e3.q_scale", |
|
"shape": [ |
|
8, |
|
28672, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 47251456, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "155a215bddf08c28fada3f0785bb56dc" |
|
}, |
|
{ |
|
"dataPath": "params_shard_66.bin", |
|
"format": "raw-shard", |
|
"nbytes": 188219392, |
|
"records": [ |
|
{ |
|
"name": "model.layers.16.moe.e2.q_weight", |
|
"shape": [ |
|
8, |
|
4096, |
|
1436 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 188219392, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "d030eb0eba6c5f10efe69b6cec3c0914" |
|
}, |
|
{ |
|
"dataPath": "params_shard_67.bin", |
|
"format": "raw-shard", |
|
"nbytes": 23527424, |
|
"records": [ |
|
{ |
|
"name": "model.layers.16.moe.e2.q_scale", |
|
"shape": [ |
|
8, |
|
4096, |
|
359 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 23527424, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "ee61e9180c8eab64debecd06ac4d0c2d" |
|
}, |
|
{ |
|
"dataPath": "params_shard_68.bin", |
|
"format": "raw-shard", |
|
"nbytes": 30407152, |
|
"records": [ |
|
{ |
|
"name": "model.layers.15.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
6144, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10125312, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.15.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
6144, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1265664, |
|
"byteOffset": 10125312 |
|
}, |
|
{ |
|
"name": "model.layers.15.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6750208, |
|
"byteOffset": 11390976 |
|
}, |
|
{ |
|
"name": "model.layers.15.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 843776, |
|
"byteOffset": 18141184 |
|
}, |
|
{ |
|
"name": "model.layers.15.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 18984960 |
|
}, |
|
{ |
|
"name": "model.layers.15.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 18993152 |
|
}, |
|
{ |
|
"name": "model.layers.16.moe.gate.q_weight", |
|
"shape": [ |
|
8, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 13184, |
|
"byteOffset": 19001344 |
|
}, |
|
{ |
|
"name": "model.layers.16.moe.gate.q_scale", |
|
"shape": [ |
|
8, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1648, |
|
"byteOffset": 19014528 |
|
}, |
|
{ |
|
"name": "model.layers.16.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
6144, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10125312, |
|
"byteOffset": 19016176 |
|
}, |
|
{ |
|
"name": "model.layers.16.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
6144, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1265664, |
|
"byteOffset": 29141488 |
|
} |
|
], |
|
"md5sum": "9009f4ec9c583a1bfd057d96135db951" |
|
}, |
|
{ |
|
"dataPath": "params_shard_69.bin", |
|
"format": "raw-shard", |
|
"nbytes": 378011648, |
|
"records": [ |
|
{ |
|
"name": "model.layers.17.moe.e1_e3.q_weight", |
|
"shape": [ |
|
8, |
|
28672, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 378011648, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "1d3caebcc390a7324e4f7c55b6e06706" |
|
}, |
|
{ |
|
"dataPath": "params_shard_70.bin", |
|
"format": "raw-shard", |
|
"nbytes": 47251456, |
|
"records": [ |
|
{ |
|
"name": "model.layers.17.moe.e1_e3.q_scale", |
|
"shape": [ |
|
8, |
|
28672, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 47251456, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "8dc2d42001bb69e46dc77c7a13f685b2" |
|
}, |
|
{ |
|
"dataPath": "params_shard_71.bin", |
|
"format": "raw-shard", |
|
"nbytes": 188219392, |
|
"records": [ |
|
{ |
|
"name": "model.layers.17.moe.e2.q_weight", |
|
"shape": [ |
|
8, |
|
4096, |
|
1436 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 188219392, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "2859320f04a5e48c450e756fef126cb7" |
|
}, |
|
{ |
|
"dataPath": "params_shard_72.bin", |
|
"format": "raw-shard", |
|
"nbytes": 31169008, |
|
"records": [ |
|
{ |
|
"name": "model.layers.16.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6750208, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.16.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 843776, |
|
"byteOffset": 6750208 |
|
}, |
|
{ |
|
"name": "model.layers.16.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 7593984 |
|
}, |
|
{ |
|
"name": "model.layers.16.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 7602176 |
|
}, |
|
{ |
|
"name": "model.layers.17.moe.e2.q_scale", |
|
"shape": [ |
|
8, |
|
4096, |
|
359 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 23527424, |
|
"byteOffset": 7610368 |
|
}, |
|
{ |
|
"name": "model.layers.17.moe.gate.q_weight", |
|
"shape": [ |
|
8, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 13184, |
|
"byteOffset": 31137792 |
|
}, |
|
{ |
|
"name": "model.layers.17.moe.gate.q_scale", |
|
"shape": [ |
|
8, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1648, |
|
"byteOffset": 31150976 |
|
}, |
|
{ |
|
"name": "model.layers.17.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 31152624 |
|
}, |
|
{ |
|
"name": "model.layers.17.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 31160816 |
|
} |
|
], |
|
"md5sum": "bd090370516f19716c799e189fe9eeb5" |
|
}, |
|
{ |
|
"dataPath": "params_shard_73.bin", |
|
"format": "raw-shard", |
|
"nbytes": 378011648, |
|
"records": [ |
|
{ |
|
"name": "model.layers.18.moe.e1_e3.q_weight", |
|
"shape": [ |
|
8, |
|
28672, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 378011648, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "963ff00418f72facbd024518f78282d3" |
|
}, |
|
{ |
|
"dataPath": "params_shard_74.bin", |
|
"format": "raw-shard", |
|
"nbytes": 47251456, |
|
"records": [ |
|
{ |
|
"name": "model.layers.18.moe.e1_e3.q_scale", |
|
"shape": [ |
|
8, |
|
28672, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 47251456, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "aa273bb44e432e09484304382c049110" |
|
}, |
|
{ |
|
"dataPath": "params_shard_75.bin", |
|
"format": "raw-shard", |
|
"nbytes": 188219392, |
|
"records": [ |
|
{ |
|
"name": "model.layers.18.moe.e2.q_weight", |
|
"shape": [ |
|
8, |
|
4096, |
|
1436 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 188219392, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "5c87ffdc084525a0f63ccec57bdd55be" |
|
}, |
|
{ |
|
"dataPath": "params_shard_76.bin", |
|
"format": "raw-shard", |
|
"nbytes": 23527424, |
|
"records": [ |
|
{ |
|
"name": "model.layers.18.moe.e2.q_scale", |
|
"shape": [ |
|
8, |
|
4096, |
|
359 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 23527424, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "d832f7754fdedd03f57fd478dd147624" |
|
}, |
|
{ |
|
"dataPath": "params_shard_77.bin", |
|
"format": "raw-shard", |
|
"nbytes": 30390768, |
|
"records": [ |
|
{ |
|
"name": "model.layers.17.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
6144, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10125312, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.17.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
6144, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1265664, |
|
"byteOffset": 10125312 |
|
}, |
|
{ |
|
"name": "model.layers.17.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6750208, |
|
"byteOffset": 11390976 |
|
}, |
|
{ |
|
"name": "model.layers.17.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 843776, |
|
"byteOffset": 18141184 |
|
}, |
|
{ |
|
"name": "model.layers.18.moe.gate.q_weight", |
|
"shape": [ |
|
8, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 13184, |
|
"byteOffset": 18984960 |
|
}, |
|
{ |
|
"name": "model.layers.18.moe.gate.q_scale", |
|
"shape": [ |
|
8, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1648, |
|
"byteOffset": 18998144 |
|
}, |
|
{ |
|
"name": "model.layers.18.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
6144, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10125312, |
|
"byteOffset": 18999792 |
|
}, |
|
{ |
|
"name": "model.layers.18.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
6144, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1265664, |
|
"byteOffset": 29125104 |
|
} |
|
], |
|
"md5sum": "19f967b0c416b6905fbab7024b4d3376" |
|
}, |
|
{ |
|
"dataPath": "params_shard_78.bin", |
|
"format": "raw-shard", |
|
"nbytes": 378011648, |
|
"records": [ |
|
{ |
|
"name": "model.layers.19.moe.e1_e3.q_weight", |
|
"shape": [ |
|
8, |
|
28672, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 378011648, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "00dd8703b0bb916ad93052d442ae6b78" |
|
}, |
|
{ |
|
"dataPath": "params_shard_79.bin", |
|
"format": "raw-shard", |
|
"nbytes": 47251456, |
|
"records": [ |
|
{ |
|
"name": "model.layers.19.moe.e1_e3.q_scale", |
|
"shape": [ |
|
8, |
|
28672, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 47251456, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "41d83c0d7ee727d20bef86d6fd6fa661" |
|
}, |
|
{ |
|
"dataPath": "params_shard_80.bin", |
|
"format": "raw-shard", |
|
"nbytes": 188219392, |
|
"records": [ |
|
{ |
|
"name": "model.layers.19.moe.e2.q_weight", |
|
"shape": [ |
|
8, |
|
4096, |
|
1436 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 188219392, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "8da17633021c3a414b826eefbf7489e0" |
|
}, |
|
{ |
|
"dataPath": "params_shard_81.bin", |
|
"format": "raw-shard", |
|
"nbytes": 31169008, |
|
"records": [ |
|
{ |
|
"name": "model.layers.18.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6750208, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.18.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 843776, |
|
"byteOffset": 6750208 |
|
}, |
|
{ |
|
"name": "model.layers.18.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 7593984 |
|
}, |
|
{ |
|
"name": "model.layers.18.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 7602176 |
|
}, |
|
{ |
|
"name": "model.layers.19.moe.e2.q_scale", |
|
"shape": [ |
|
8, |
|
4096, |
|
359 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 23527424, |
|
"byteOffset": 7610368 |
|
}, |
|
{ |
|
"name": "model.layers.19.moe.gate.q_weight", |
|
"shape": [ |
|
8, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 13184, |
|
"byteOffset": 31137792 |
|
}, |
|
{ |
|
"name": "model.layers.19.moe.gate.q_scale", |
|
"shape": [ |
|
8, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1648, |
|
"byteOffset": 31150976 |
|
}, |
|
{ |
|
"name": "model.layers.19.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 31152624 |
|
}, |
|
{ |
|
"name": "model.layers.19.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 31160816 |
|
} |
|
], |
|
"md5sum": "ef390b65f65786c4401c467c3f03870d" |
|
}, |
|
{ |
|
"dataPath": "params_shard_82.bin", |
|
"format": "raw-shard", |
|
"nbytes": 378011648, |
|
"records": [ |
|
{ |
|
"name": "model.layers.20.moe.e1_e3.q_weight", |
|
"shape": [ |
|
8, |
|
28672, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 378011648, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "29df8333cf570321964ad14c57dc80b9" |
|
}, |
|
{ |
|
"dataPath": "params_shard_83.bin", |
|
"format": "raw-shard", |
|
"nbytes": 47251456, |
|
"records": [ |
|
{ |
|
"name": "model.layers.20.moe.e1_e3.q_scale", |
|
"shape": [ |
|
8, |
|
28672, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 47251456, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "ed1bc95fdfb5a5fe8b826b737ab0faf4" |
|
}, |
|
{ |
|
"dataPath": "params_shard_84.bin", |
|
"format": "raw-shard", |
|
"nbytes": 188219392, |
|
"records": [ |
|
{ |
|
"name": "model.layers.20.moe.e2.q_weight", |
|
"shape": [ |
|
8, |
|
4096, |
|
1436 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 188219392, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "137a08a118fd023b07ef8e21d08dee20" |
|
}, |
|
{ |
|
"dataPath": "params_shard_85.bin", |
|
"format": "raw-shard", |
|
"nbytes": 23527424, |
|
"records": [ |
|
{ |
|
"name": "model.layers.20.moe.e2.q_scale", |
|
"shape": [ |
|
8, |
|
4096, |
|
359 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 23527424, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "b8d0947729b1aedfb0b4e0de31149c2c" |
|
}, |
|
{ |
|
"dataPath": "params_shard_86.bin", |
|
"format": "raw-shard", |
|
"nbytes": 30390768, |
|
"records": [ |
|
{ |
|
"name": "model.layers.19.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
6144, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10125312, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.19.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
6144, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1265664, |
|
"byteOffset": 10125312 |
|
}, |
|
{ |
|
"name": "model.layers.19.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6750208, |
|
"byteOffset": 11390976 |
|
}, |
|
{ |
|
"name": "model.layers.19.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 843776, |
|
"byteOffset": 18141184 |
|
}, |
|
{ |
|
"name": "model.layers.20.moe.gate.q_weight", |
|
"shape": [ |
|
8, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 13184, |
|
"byteOffset": 18984960 |
|
}, |
|
{ |
|
"name": "model.layers.20.moe.gate.q_scale", |
|
"shape": [ |
|
8, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1648, |
|
"byteOffset": 18998144 |
|
}, |
|
{ |
|
"name": "model.layers.20.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
6144, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10125312, |
|
"byteOffset": 18999792 |
|
}, |
|
{ |
|
"name": "model.layers.20.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
6144, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1265664, |
|
"byteOffset": 29125104 |
|
} |
|
], |
|
"md5sum": "6d71e2da5d2c5bc436b5037bc4a874d0" |
|
}, |
|
{ |
|
"dataPath": "params_shard_87.bin", |
|
"format": "raw-shard", |
|
"nbytes": 378011648, |
|
"records": [ |
|
{ |
|
"name": "model.layers.21.moe.e1_e3.q_weight", |
|
"shape": [ |
|
8, |
|
28672, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 378011648, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "fcb51c16257ed55898d4ba66c4699aec" |
|
}, |
|
{ |
|
"dataPath": "params_shard_88.bin", |
|
"format": "raw-shard", |
|
"nbytes": 47251456, |
|
"records": [ |
|
{ |
|
"name": "model.layers.21.moe.e1_e3.q_scale", |
|
"shape": [ |
|
8, |
|
28672, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 47251456, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "3d18747615ffc745451cfc5d452e183e" |
|
}, |
|
{ |
|
"dataPath": "params_shard_89.bin", |
|
"format": "raw-shard", |
|
"nbytes": 188219392, |
|
"records": [ |
|
{ |
|
"name": "model.layers.21.moe.e2.q_weight", |
|
"shape": [ |
|
8, |
|
4096, |
|
1436 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 188219392, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "6c0a6ce6fbe00f6443d41797300783ea" |
|
}, |
|
{ |
|
"dataPath": "params_shard_90.bin", |
|
"format": "raw-shard", |
|
"nbytes": 31169008, |
|
"records": [ |
|
{ |
|
"name": "model.layers.20.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6750208, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.20.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 843776, |
|
"byteOffset": 6750208 |
|
}, |
|
{ |
|
"name": "model.layers.20.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 7593984 |
|
}, |
|
{ |
|
"name": "model.layers.20.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 7602176 |
|
}, |
|
{ |
|
"name": "model.layers.21.moe.e2.q_scale", |
|
"shape": [ |
|
8, |
|
4096, |
|
359 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 23527424, |
|
"byteOffset": 7610368 |
|
}, |
|
{ |
|
"name": "model.layers.21.moe.gate.q_weight", |
|
"shape": [ |
|
8, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 13184, |
|
"byteOffset": 31137792 |
|
}, |
|
{ |
|
"name": "model.layers.21.moe.gate.q_scale", |
|
"shape": [ |
|
8, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1648, |
|
"byteOffset": 31150976 |
|
}, |
|
{ |
|
"name": "model.layers.21.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 31152624 |
|
}, |
|
{ |
|
"name": "model.layers.21.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 31160816 |
|
} |
|
], |
|
"md5sum": "901c93471fed14a1f2278072d066dcfd" |
|
}, |
|
{ |
|
"dataPath": "params_shard_91.bin", |
|
"format": "raw-shard", |
|
"nbytes": 378011648, |
|
"records": [ |
|
{ |
|
"name": "model.layers.22.moe.e1_e3.q_weight", |
|
"shape": [ |
|
8, |
|
28672, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 378011648, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "a0545410371557aa020e662bbb6db368" |
|
}, |
|
{ |
|
"dataPath": "params_shard_92.bin", |
|
"format": "raw-shard", |
|
"nbytes": 47251456, |
|
"records": [ |
|
{ |
|
"name": "model.layers.22.moe.e1_e3.q_scale", |
|
"shape": [ |
|
8, |
|
28672, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 47251456, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "20ae74d09e1392b06e7acc6e6eabe4ad" |
|
}, |
|
{ |
|
"dataPath": "params_shard_93.bin", |
|
"format": "raw-shard", |
|
"nbytes": 188219392, |
|
"records": [ |
|
{ |
|
"name": "model.layers.22.moe.e2.q_weight", |
|
"shape": [ |
|
8, |
|
4096, |
|
1436 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 188219392, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "b12b43f4c6afa38f7228483231216f79" |
|
}, |
|
{ |
|
"dataPath": "params_shard_94.bin", |
|
"format": "raw-shard", |
|
"nbytes": 23527424, |
|
"records": [ |
|
{ |
|
"name": "model.layers.22.moe.e2.q_scale", |
|
"shape": [ |
|
8, |
|
4096, |
|
359 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 23527424, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "3b90246dac53d206c13f4b0d709a6e1a" |
|
}, |
|
{ |
|
"dataPath": "params_shard_95.bin", |
|
"format": "raw-shard", |
|
"nbytes": 30390768, |
|
"records": [ |
|
{ |
|
"name": "model.layers.21.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
6144, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10125312, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.21.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
6144, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1265664, |
|
"byteOffset": 10125312 |
|
}, |
|
{ |
|
"name": "model.layers.21.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6750208, |
|
"byteOffset": 11390976 |
|
}, |
|
{ |
|
"name": "model.layers.21.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 843776, |
|
"byteOffset": 18141184 |
|
}, |
|
{ |
|
"name": "model.layers.22.moe.gate.q_weight", |
|
"shape": [ |
|
8, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 13184, |
|
"byteOffset": 18984960 |
|
}, |
|
{ |
|
"name": "model.layers.22.moe.gate.q_scale", |
|
"shape": [ |
|
8, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1648, |
|
"byteOffset": 18998144 |
|
}, |
|
{ |
|
"name": "model.layers.22.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
6144, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10125312, |
|
"byteOffset": 18999792 |
|
}, |
|
{ |
|
"name": "model.layers.22.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
6144, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1265664, |
|
"byteOffset": 29125104 |
|
} |
|
], |
|
"md5sum": "d5c37a2fb2ff64670fc8bb443b834212" |
|
}, |
|
{ |
|
"dataPath": "params_shard_96.bin", |
|
"format": "raw-shard", |
|
"nbytes": 378011648, |
|
"records": [ |
|
{ |
|
"name": "model.layers.23.moe.e1_e3.q_weight", |
|
"shape": [ |
|
8, |
|
28672, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 378011648, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "13d50334571113505c7e94ed6992e0ee" |
|
}, |
|
{ |
|
"dataPath": "params_shard_97.bin", |
|
"format": "raw-shard", |
|
"nbytes": 47251456, |
|
"records": [ |
|
{ |
|
"name": "model.layers.23.moe.e1_e3.q_scale", |
|
"shape": [ |
|
8, |
|
28672, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 47251456, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "65af2f80eefb3fcd8979d4a756d9ddef" |
|
}, |
|
{ |
|
"dataPath": "params_shard_98.bin", |
|
"format": "raw-shard", |
|
"nbytes": 188219392, |
|
"records": [ |
|
{ |
|
"name": "model.layers.23.moe.e2.q_weight", |
|
"shape": [ |
|
8, |
|
4096, |
|
1436 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 188219392, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "8f4e2ea7c11a7886525516fc446de6f1" |
|
}, |
|
{ |
|
"dataPath": "params_shard_99.bin", |
|
"format": "raw-shard", |
|
"nbytes": 31152624, |
|
"records": [ |
|
{ |
|
"name": "model.layers.22.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6750208, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.22.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 843776, |
|
"byteOffset": 6750208 |
|
}, |
|
{ |
|
"name": "model.layers.22.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 7593984 |
|
}, |
|
{ |
|
"name": "model.layers.22.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 7602176 |
|
}, |
|
{ |
|
"name": "model.layers.23.moe.e2.q_scale", |
|
"shape": [ |
|
8, |
|
4096, |
|
359 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 23527424, |
|
"byteOffset": 7610368 |
|
}, |
|
{ |
|
"name": "model.layers.23.moe.gate.q_weight", |
|
"shape": [ |
|
8, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 13184, |
|
"byteOffset": 31137792 |
|
}, |
|
{ |
|
"name": "model.layers.23.moe.gate.q_scale", |
|
"shape": [ |
|
8, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1648, |
|
"byteOffset": 31150976 |
|
} |
|
], |
|
"md5sum": "1c113c0156ea25223cd842b27ac490b8" |
|
}, |
|
{ |
|
"dataPath": "params_shard_100.bin", |
|
"format": "raw-shard", |
|
"nbytes": 378011648, |
|
"records": [ |
|
{ |
|
"name": "model.layers.24.moe.e1_e3.q_weight", |
|
"shape": [ |
|
8, |
|
28672, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 378011648, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "0226146a99ff7e76ff8613e351089e12" |
|
}, |
|
{ |
|
"dataPath": "params_shard_101.bin", |
|
"format": "raw-shard", |
|
"nbytes": 47251456, |
|
"records": [ |
|
{ |
|
"name": "model.layers.24.moe.e1_e3.q_scale", |
|
"shape": [ |
|
8, |
|
28672, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 47251456, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "f40238267929673810df4f1e0a3795ce" |
|
}, |
|
{ |
|
"dataPath": "params_shard_102.bin", |
|
"format": "raw-shard", |
|
"nbytes": 188219392, |
|
"records": [ |
|
{ |
|
"name": "model.layers.24.moe.e2.q_weight", |
|
"shape": [ |
|
8, |
|
4096, |
|
1436 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 188219392, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "d0d810f259704340d929f76c1822280a" |
|
}, |
|
{ |
|
"dataPath": "params_shard_103.bin", |
|
"format": "raw-shard", |
|
"nbytes": 23527424, |
|
"records": [ |
|
{ |
|
"name": "model.layers.24.moe.e2.q_scale", |
|
"shape": [ |
|
8, |
|
4096, |
|
359 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 23527424, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "2c773b5677ffbae8d5c8440703b1455c" |
|
}, |
|
{ |
|
"dataPath": "params_shard_104.bin", |
|
"format": "raw-shard", |
|
"nbytes": 30423536, |
|
"records": [ |
|
{ |
|
"name": "model.layers.23.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
6144, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10125312, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.23.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
6144, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1265664, |
|
"byteOffset": 10125312 |
|
}, |
|
{ |
|
"name": "model.layers.23.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6750208, |
|
"byteOffset": 11390976 |
|
}, |
|
{ |
|
"name": "model.layers.23.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 843776, |
|
"byteOffset": 18141184 |
|
}, |
|
{ |
|
"name": "model.layers.23.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 18984960 |
|
}, |
|
{ |
|
"name": "model.layers.23.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 18993152 |
|
}, |
|
{ |
|
"name": "model.layers.24.moe.gate.q_weight", |
|
"shape": [ |
|
8, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 13184, |
|
"byteOffset": 19001344 |
|
}, |
|
{ |
|
"name": "model.layers.24.moe.gate.q_scale", |
|
"shape": [ |
|
8, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1648, |
|
"byteOffset": 19014528 |
|
}, |
|
{ |
|
"name": "model.layers.24.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 19016176 |
|
}, |
|
{ |
|
"name": "model.layers.24.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 19024368 |
|
}, |
|
{ |
|
"name": "model.layers.24.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
6144, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10125312, |
|
"byteOffset": 19032560 |
|
}, |
|
{ |
|
"name": "model.layers.24.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
6144, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1265664, |
|
"byteOffset": 29157872 |
|
} |
|
], |
|
"md5sum": "be2538f515bd38e96bb838f373736b92" |
|
}, |
|
{ |
|
"dataPath": "params_shard_105.bin", |
|
"format": "raw-shard", |
|
"nbytes": 378011648, |
|
"records": [ |
|
{ |
|
"name": "model.layers.25.moe.e1_e3.q_weight", |
|
"shape": [ |
|
8, |
|
28672, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 378011648, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "99a5d15126f5620da30501df8217ed3e" |
|
}, |
|
{ |
|
"dataPath": "params_shard_106.bin", |
|
"format": "raw-shard", |
|
"nbytes": 47251456, |
|
"records": [ |
|
{ |
|
"name": "model.layers.25.moe.e1_e3.q_scale", |
|
"shape": [ |
|
8, |
|
28672, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 47251456, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "e3ab0dbb876c3667972f23ba39d2941c" |
|
}, |
|
{ |
|
"dataPath": "params_shard_107.bin", |
|
"format": "raw-shard", |
|
"nbytes": 188219392, |
|
"records": [ |
|
{ |
|
"name": "model.layers.25.moe.e2.q_weight", |
|
"shape": [ |
|
8, |
|
4096, |
|
1436 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 188219392, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "5bc70aec30f6c71cfb5c0d994177ac67" |
|
}, |
|
{ |
|
"dataPath": "params_shard_108.bin", |
|
"format": "raw-shard", |
|
"nbytes": 31136240, |
|
"records": [ |
|
{ |
|
"name": "model.layers.24.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6750208, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.24.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 843776, |
|
"byteOffset": 6750208 |
|
}, |
|
{ |
|
"name": "model.layers.25.moe.e2.q_scale", |
|
"shape": [ |
|
8, |
|
4096, |
|
359 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 23527424, |
|
"byteOffset": 7593984 |
|
}, |
|
{ |
|
"name": "model.layers.25.moe.gate.q_weight", |
|
"shape": [ |
|
8, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 13184, |
|
"byteOffset": 31121408 |
|
}, |
|
{ |
|
"name": "model.layers.25.moe.gate.q_scale", |
|
"shape": [ |
|
8, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1648, |
|
"byteOffset": 31134592 |
|
} |
|
], |
|
"md5sum": "0a35e938600bca8d3d664b3638074fcb" |
|
}, |
|
{ |
|
"dataPath": "params_shard_109.bin", |
|
"format": "raw-shard", |
|
"nbytes": 378011648, |
|
"records": [ |
|
{ |
|
"name": "model.layers.26.moe.e1_e3.q_weight", |
|
"shape": [ |
|
8, |
|
28672, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 378011648, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "414c50fa24ced2b89c1a31218cb01a31" |
|
}, |
|
{ |
|
"dataPath": "params_shard_110.bin", |
|
"format": "raw-shard", |
|
"nbytes": 47251456, |
|
"records": [ |
|
{ |
|
"name": "model.layers.26.moe.e1_e3.q_scale", |
|
"shape": [ |
|
8, |
|
28672, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 47251456, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "e399d2a5ac59d4c713cfb1de7780dbd6" |
|
}, |
|
{ |
|
"dataPath": "params_shard_111.bin", |
|
"format": "raw-shard", |
|
"nbytes": 188219392, |
|
"records": [ |
|
{ |
|
"name": "model.layers.26.moe.e2.q_weight", |
|
"shape": [ |
|
8, |
|
4096, |
|
1436 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 188219392, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "5001a6292f894a981f0155cf5d90e4cc" |
|
}, |
|
{ |
|
"dataPath": "params_shard_112.bin", |
|
"format": "raw-shard", |
|
"nbytes": 23527424, |
|
"records": [ |
|
{ |
|
"name": "model.layers.26.moe.e2.q_scale", |
|
"shape": [ |
|
8, |
|
4096, |
|
359 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 23527424, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "8d7ac9965cef1d83d89a370f7f8cc383" |
|
}, |
|
{ |
|
"dataPath": "params_shard_113.bin", |
|
"format": "raw-shard", |
|
"nbytes": 30423536, |
|
"records": [ |
|
{ |
|
"name": "model.layers.25.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
6144, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10125312, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.25.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
6144, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1265664, |
|
"byteOffset": 10125312 |
|
}, |
|
{ |
|
"name": "model.layers.25.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6750208, |
|
"byteOffset": 11390976 |
|
}, |
|
{ |
|
"name": "model.layers.25.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 843776, |
|
"byteOffset": 18141184 |
|
}, |
|
{ |
|
"name": "model.layers.25.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 18984960 |
|
}, |
|
{ |
|
"name": "model.layers.25.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 18993152 |
|
}, |
|
{ |
|
"name": "model.layers.26.moe.gate.q_weight", |
|
"shape": [ |
|
8, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 13184, |
|
"byteOffset": 19001344 |
|
}, |
|
{ |
|
"name": "model.layers.26.moe.gate.q_scale", |
|
"shape": [ |
|
8, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1648, |
|
"byteOffset": 19014528 |
|
}, |
|
{ |
|
"name": "model.layers.26.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 19016176 |
|
}, |
|
{ |
|
"name": "model.layers.26.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 19024368 |
|
}, |
|
{ |
|
"name": "model.layers.26.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
6144, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10125312, |
|
"byteOffset": 19032560 |
|
}, |
|
{ |
|
"name": "model.layers.26.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
6144, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1265664, |
|
"byteOffset": 29157872 |
|
} |
|
], |
|
"md5sum": "e352ab9e424b67b352ed57cdf65a0fb5" |
|
}, |
|
{ |
|
"dataPath": "params_shard_114.bin", |
|
"format": "raw-shard", |
|
"nbytes": 378011648, |
|
"records": [ |
|
{ |
|
"name": "model.layers.27.moe.e1_e3.q_weight", |
|
"shape": [ |
|
8, |
|
28672, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 378011648, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "198e10879f730b0e4d95d8f48521a111" |
|
}, |
|
{ |
|
"dataPath": "params_shard_115.bin", |
|
"format": "raw-shard", |
|
"nbytes": 47251456, |
|
"records": [ |
|
{ |
|
"name": "model.layers.27.moe.e1_e3.q_scale", |
|
"shape": [ |
|
8, |
|
28672, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 47251456, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "fcea24bdeee117957147c4afecde4093" |
|
}, |
|
{ |
|
"dataPath": "params_shard_116.bin", |
|
"format": "raw-shard", |
|
"nbytes": 188219392, |
|
"records": [ |
|
{ |
|
"name": "model.layers.27.moe.e2.q_weight", |
|
"shape": [ |
|
8, |
|
4096, |
|
1436 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 188219392, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "66c55f681f93632f893d406f427a9942" |
|
}, |
|
{ |
|
"dataPath": "params_shard_117.bin", |
|
"format": "raw-shard", |
|
"nbytes": 31136240, |
|
"records": [ |
|
{ |
|
"name": "model.layers.26.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6750208, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.26.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 843776, |
|
"byteOffset": 6750208 |
|
}, |
|
{ |
|
"name": "model.layers.27.moe.e2.q_scale", |
|
"shape": [ |
|
8, |
|
4096, |
|
359 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 23527424, |
|
"byteOffset": 7593984 |
|
}, |
|
{ |
|
"name": "model.layers.27.moe.gate.q_weight", |
|
"shape": [ |
|
8, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 13184, |
|
"byteOffset": 31121408 |
|
}, |
|
{ |
|
"name": "model.layers.27.moe.gate.q_scale", |
|
"shape": [ |
|
8, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1648, |
|
"byteOffset": 31134592 |
|
} |
|
], |
|
"md5sum": "409cf2a6076cf97a1db4f5e03b054010" |
|
}, |
|
{ |
|
"dataPath": "params_shard_118.bin", |
|
"format": "raw-shard", |
|
"nbytes": 378011648, |
|
"records": [ |
|
{ |
|
"name": "model.layers.28.moe.e1_e3.q_weight", |
|
"shape": [ |
|
8, |
|
28672, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 378011648, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "ff4ada4c2b952e1938e18ff76e89f348" |
|
}, |
|
{ |
|
"dataPath": "params_shard_119.bin", |
|
"format": "raw-shard", |
|
"nbytes": 47251456, |
|
"records": [ |
|
{ |
|
"name": "model.layers.28.moe.e1_e3.q_scale", |
|
"shape": [ |
|
8, |
|
28672, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 47251456, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "99b1ef4eaf2b7c85995cf0163744feac" |
|
}, |
|
{ |
|
"dataPath": "params_shard_120.bin", |
|
"format": "raw-shard", |
|
"nbytes": 188219392, |
|
"records": [ |
|
{ |
|
"name": "model.layers.28.moe.e2.q_weight", |
|
"shape": [ |
|
8, |
|
4096, |
|
1436 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 188219392, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "cfe69a3eab93820fb737680adb684259" |
|
}, |
|
{ |
|
"dataPath": "params_shard_121.bin", |
|
"format": "raw-shard", |
|
"nbytes": 23527424, |
|
"records": [ |
|
{ |
|
"name": "model.layers.28.moe.e2.q_scale", |
|
"shape": [ |
|
8, |
|
4096, |
|
359 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 23527424, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "7063dc8dcd5e89283933cf93af4159ad" |
|
}, |
|
{ |
|
"dataPath": "params_shard_122.bin", |
|
"format": "raw-shard", |
|
"nbytes": 30407152, |
|
"records": [ |
|
{ |
|
"name": "model.layers.27.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
6144, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10125312, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.27.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
6144, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1265664, |
|
"byteOffset": 10125312 |
|
}, |
|
{ |
|
"name": "model.layers.27.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6750208, |
|
"byteOffset": 11390976 |
|
}, |
|
{ |
|
"name": "model.layers.27.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 843776, |
|
"byteOffset": 18141184 |
|
}, |
|
{ |
|
"name": "model.layers.27.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 18984960 |
|
}, |
|
{ |
|
"name": "model.layers.27.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 18993152 |
|
}, |
|
{ |
|
"name": "model.layers.28.moe.gate.q_weight", |
|
"shape": [ |
|
8, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 13184, |
|
"byteOffset": 19001344 |
|
}, |
|
{ |
|
"name": "model.layers.28.moe.gate.q_scale", |
|
"shape": [ |
|
8, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1648, |
|
"byteOffset": 19014528 |
|
}, |
|
{ |
|
"name": "model.layers.28.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
6144, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10125312, |
|
"byteOffset": 19016176 |
|
}, |
|
{ |
|
"name": "model.layers.28.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
6144, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1265664, |
|
"byteOffset": 29141488 |
|
} |
|
], |
|
"md5sum": "01b46e5e8769ade036454ed23f538ce4" |
|
}, |
|
{ |
|
"dataPath": "params_shard_123.bin", |
|
"format": "raw-shard", |
|
"nbytes": 378011648, |
|
"records": [ |
|
{ |
|
"name": "model.layers.29.moe.e1_e3.q_weight", |
|
"shape": [ |
|
8, |
|
28672, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 378011648, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "28770dbe0b1a517123694a38fb96b16a" |
|
}, |
|
{ |
|
"dataPath": "params_shard_124.bin", |
|
"format": "raw-shard", |
|
"nbytes": 47251456, |
|
"records": [ |
|
{ |
|
"name": "model.layers.29.moe.e1_e3.q_scale", |
|
"shape": [ |
|
8, |
|
28672, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 47251456, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "c952d63cca43e144bf3c6b4ac01800b8" |
|
}, |
|
{ |
|
"dataPath": "params_shard_125.bin", |
|
"format": "raw-shard", |
|
"nbytes": 188219392, |
|
"records": [ |
|
{ |
|
"name": "model.layers.29.moe.e2.q_weight", |
|
"shape": [ |
|
8, |
|
4096, |
|
1436 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 188219392, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "4b7a12efd22cb0b993a112e77a712ed3" |
|
}, |
|
{ |
|
"dataPath": "params_shard_126.bin", |
|
"format": "raw-shard", |
|
"nbytes": 31169008, |
|
"records": [ |
|
{ |
|
"name": "model.layers.28.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6750208, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.28.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 843776, |
|
"byteOffset": 6750208 |
|
}, |
|
{ |
|
"name": "model.layers.28.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 7593984 |
|
}, |
|
{ |
|
"name": "model.layers.28.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 7602176 |
|
}, |
|
{ |
|
"name": "model.layers.29.moe.e2.q_scale", |
|
"shape": [ |
|
8, |
|
4096, |
|
359 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 23527424, |
|
"byteOffset": 7610368 |
|
}, |
|
{ |
|
"name": "model.layers.29.moe.gate.q_weight", |
|
"shape": [ |
|
8, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 13184, |
|
"byteOffset": 31137792 |
|
}, |
|
{ |
|
"name": "model.layers.29.moe.gate.q_scale", |
|
"shape": [ |
|
8, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1648, |
|
"byteOffset": 31150976 |
|
}, |
|
{ |
|
"name": "model.layers.29.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 31152624 |
|
}, |
|
{ |
|
"name": "model.layers.29.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 31160816 |
|
} |
|
], |
|
"md5sum": "30a0cde4ff0f52c63c524382b922016e" |
|
}, |
|
{ |
|
"dataPath": "params_shard_127.bin", |
|
"format": "raw-shard", |
|
"nbytes": 30390768, |
|
"records": [ |
|
{ |
|
"name": "model.layers.29.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
6144, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10125312, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.29.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
6144, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1265664, |
|
"byteOffset": 10125312 |
|
}, |
|
{ |
|
"name": "model.layers.29.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6750208, |
|
"byteOffset": 11390976 |
|
}, |
|
{ |
|
"name": "model.layers.29.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 843776, |
|
"byteOffset": 18141184 |
|
}, |
|
{ |
|
"name": "model.layers.30.moe.gate.q_weight", |
|
"shape": [ |
|
8, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 13184, |
|
"byteOffset": 18984960 |
|
}, |
|
{ |
|
"name": "model.layers.30.moe.gate.q_scale", |
|
"shape": [ |
|
8, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1648, |
|
"byteOffset": 18998144 |
|
}, |
|
{ |
|
"name": "model.layers.30.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
6144, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10125312, |
|
"byteOffset": 18999792 |
|
}, |
|
{ |
|
"name": "model.layers.30.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
6144, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1265664, |
|
"byteOffset": 29125104 |
|
} |
|
], |
|
"md5sum": "ac9be55f35c1e22cebeadd2d10bec8f2" |
|
}, |
|
{ |
|
"dataPath": "params_shard_128.bin", |
|
"format": "raw-shard", |
|
"nbytes": 378011648, |
|
"records": [ |
|
{ |
|
"name": "model.layers.4.moe.e1_e3.q_weight", |
|
"shape": [ |
|
8, |
|
28672, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 378011648, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "4f2d8e509ffcd738cfc283b0d7b6fffd" |
|
}, |
|
{ |
|
"dataPath": "params_shard_129.bin", |
|
"format": "raw-shard", |
|
"nbytes": 47251456, |
|
"records": [ |
|
{ |
|
"name": "model.layers.4.moe.e1_e3.q_scale", |
|
"shape": [ |
|
8, |
|
28672, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 47251456, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "71c608d2ad4d9580f1c7218a349a08bf" |
|
}, |
|
{ |
|
"dataPath": "params_shard_130.bin", |
|
"format": "raw-shard", |
|
"nbytes": 188219392, |
|
"records": [ |
|
{ |
|
"name": "model.layers.4.moe.e2.q_weight", |
|
"shape": [ |
|
8, |
|
4096, |
|
1436 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 188219392, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "57e40007ddf8c677f1d20c09f9de9b19" |
|
}, |
|
{ |
|
"dataPath": "params_shard_131.bin", |
|
"format": "raw-shard", |
|
"nbytes": 31169008, |
|
"records": [ |
|
{ |
|
"name": "model.layers.30.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6750208, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.30.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 843776, |
|
"byteOffset": 6750208 |
|
}, |
|
{ |
|
"name": "model.layers.3.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 7593984 |
|
}, |
|
{ |
|
"name": "model.layers.3.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 7602176 |
|
}, |
|
{ |
|
"name": "model.layers.4.moe.e2.q_scale", |
|
"shape": [ |
|
8, |
|
4096, |
|
359 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 23527424, |
|
"byteOffset": 7610368 |
|
}, |
|
{ |
|
"name": "model.layers.4.moe.gate.q_weight", |
|
"shape": [ |
|
8, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 13184, |
|
"byteOffset": 31137792 |
|
}, |
|
{ |
|
"name": "model.layers.4.moe.gate.q_scale", |
|
"shape": [ |
|
8, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1648, |
|
"byteOffset": 31150976 |
|
}, |
|
{ |
|
"name": "model.layers.4.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 31152624 |
|
}, |
|
{ |
|
"name": "model.layers.4.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 31160816 |
|
} |
|
], |
|
"md5sum": "42eea54a75f74202e01f2bfd15a43ea6" |
|
}, |
|
{ |
|
"dataPath": "params_shard_132.bin", |
|
"format": "raw-shard", |
|
"nbytes": 30390768, |
|
"records": [ |
|
{ |
|
"name": "model.layers.4.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
6144, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10125312, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.4.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
6144, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1265664, |
|
"byteOffset": 10125312 |
|
}, |
|
{ |
|
"name": "model.layers.4.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6750208, |
|
"byteOffset": 11390976 |
|
}, |
|
{ |
|
"name": "model.layers.4.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 843776, |
|
"byteOffset": 18141184 |
|
}, |
|
{ |
|
"name": "model.layers.5.moe.gate.q_weight", |
|
"shape": [ |
|
8, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 13184, |
|
"byteOffset": 18984960 |
|
}, |
|
{ |
|
"name": "model.layers.5.moe.gate.q_scale", |
|
"shape": [ |
|
8, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1648, |
|
"byteOffset": 18998144 |
|
}, |
|
{ |
|
"name": "model.layers.5.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
6144, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10125312, |
|
"byteOffset": 18999792 |
|
}, |
|
{ |
|
"name": "model.layers.5.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
6144, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1265664, |
|
"byteOffset": 29125104 |
|
} |
|
], |
|
"md5sum": "5769521078bb43c6f95d9508f6ab2e86" |
|
}, |
|
{ |
|
"dataPath": "params_shard_133.bin", |
|
"format": "raw-shard", |
|
"nbytes": 378011648, |
|
"records": [ |
|
{ |
|
"name": "model.layers.5.moe.e1_e3.q_weight", |
|
"shape": [ |
|
8, |
|
28672, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 378011648, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "0a330592048daee1c4b8cbe5c60d25df" |
|
}, |
|
{ |
|
"dataPath": "params_shard_134.bin", |
|
"format": "raw-shard", |
|
"nbytes": 47251456, |
|
"records": [ |
|
{ |
|
"name": "model.layers.5.moe.e1_e3.q_scale", |
|
"shape": [ |
|
8, |
|
28672, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 47251456, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "9add9377b83e5cf1d68c6a84d74a5492" |
|
}, |
|
{ |
|
"dataPath": "params_shard_135.bin", |
|
"format": "raw-shard", |
|
"nbytes": 188219392, |
|
"records": [ |
|
{ |
|
"name": "model.layers.5.moe.e2.q_weight", |
|
"shape": [ |
|
8, |
|
4096, |
|
1436 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 188219392, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "3bfa7ceb6154a74f42e354b19a6a75fc" |
|
}, |
|
{ |
|
"dataPath": "params_shard_136.bin", |
|
"format": "raw-shard", |
|
"nbytes": 378011648, |
|
"records": [ |
|
{ |
|
"name": "model.layers.6.moe.e1_e3.q_weight", |
|
"shape": [ |
|
8, |
|
28672, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 378011648, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "b85373920bba5aebc34b4b53fbbe1316" |
|
}, |
|
{ |
|
"dataPath": "params_shard_137.bin", |
|
"format": "raw-shard", |
|
"nbytes": 47251456, |
|
"records": [ |
|
{ |
|
"name": "model.layers.6.moe.e1_e3.q_scale", |
|
"shape": [ |
|
8, |
|
28672, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 47251456, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "689d10536b59ebbcd92cb8a4cedc9d74" |
|
}, |
|
{ |
|
"dataPath": "params_shard_138.bin", |
|
"format": "raw-shard", |
|
"nbytes": 188219392, |
|
"records": [ |
|
{ |
|
"name": "model.layers.6.moe.e2.q_weight", |
|
"shape": [ |
|
8, |
|
4096, |
|
1436 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 188219392, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "4c1708209f9ba6eb553de2b01a2e13f9" |
|
}, |
|
{ |
|
"dataPath": "params_shard_139.bin", |
|
"format": "raw-shard", |
|
"nbytes": 23527424, |
|
"records": [ |
|
{ |
|
"name": "model.layers.6.moe.e2.q_scale", |
|
"shape": [ |
|
8, |
|
4096, |
|
359 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 23527424, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "78563cffcad9431ce270ac58b6fda1fe" |
|
}, |
|
{ |
|
"dataPath": "params_shard_140.bin", |
|
"format": "raw-shard", |
|
"nbytes": 31152624, |
|
"records": [ |
|
{ |
|
"name": "model.layers.5.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6750208, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.5.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 843776, |
|
"byteOffset": 6750208 |
|
}, |
|
{ |
|
"name": "model.layers.5.moe.e2.q_scale", |
|
"shape": [ |
|
8, |
|
4096, |
|
359 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 23527424, |
|
"byteOffset": 7593984 |
|
}, |
|
{ |
|
"name": "model.layers.5.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 31121408 |
|
}, |
|
{ |
|
"name": "model.layers.5.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 31129600 |
|
}, |
|
{ |
|
"name": "model.layers.6.moe.gate.q_weight", |
|
"shape": [ |
|
8, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 13184, |
|
"byteOffset": 31137792 |
|
}, |
|
{ |
|
"name": "model.layers.6.moe.gate.q_scale", |
|
"shape": [ |
|
8, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1648, |
|
"byteOffset": 31150976 |
|
} |
|
], |
|
"md5sum": "3ce414f780d72134ced04798c4c2de72" |
|
}, |
|
{ |
|
"dataPath": "params_shard_141.bin", |
|
"format": "raw-shard", |
|
"nbytes": 378011648, |
|
"records": [ |
|
{ |
|
"name": "model.layers.7.moe.e1_e3.q_weight", |
|
"shape": [ |
|
8, |
|
28672, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 378011648, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "f4023d68753109a066349a0559f193be" |
|
}, |
|
{ |
|
"dataPath": "params_shard_142.bin", |
|
"format": "raw-shard", |
|
"nbytes": 47251456, |
|
"records": [ |
|
{ |
|
"name": "model.layers.7.moe.e1_e3.q_scale", |
|
"shape": [ |
|
8, |
|
28672, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 47251456, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "3c59ca67697a89c8f02d3859880ddf61" |
|
}, |
|
{ |
|
"dataPath": "params_shard_143.bin", |
|
"format": "raw-shard", |
|
"nbytes": 188219392, |
|
"records": [ |
|
{ |
|
"name": "model.layers.7.moe.e2.q_weight", |
|
"shape": [ |
|
8, |
|
4096, |
|
1436 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 188219392, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "bf99bfe47cc6299639a35a30806de6fe" |
|
}, |
|
{ |
|
"dataPath": "params_shard_144.bin", |
|
"format": "raw-shard", |
|
"nbytes": 23527424, |
|
"records": [ |
|
{ |
|
"name": "model.layers.7.moe.e2.q_scale", |
|
"shape": [ |
|
8, |
|
4096, |
|
359 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 23527424, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "32fc249617d765012e4d33deff05713e" |
|
}, |
|
{ |
|
"dataPath": "params_shard_145.bin", |
|
"format": "raw-shard", |
|
"nbytes": 30423536, |
|
"records": [ |
|
{ |
|
"name": "model.layers.6.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
6144, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10125312, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.6.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
6144, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1265664, |
|
"byteOffset": 10125312 |
|
}, |
|
{ |
|
"name": "model.layers.6.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6750208, |
|
"byteOffset": 11390976 |
|
}, |
|
{ |
|
"name": "model.layers.6.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 843776, |
|
"byteOffset": 18141184 |
|
}, |
|
{ |
|
"name": "model.layers.6.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 18984960 |
|
}, |
|
{ |
|
"name": "model.layers.6.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 18993152 |
|
}, |
|
{ |
|
"name": "model.layers.7.moe.gate.q_weight", |
|
"shape": [ |
|
8, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 13184, |
|
"byteOffset": 19001344 |
|
}, |
|
{ |
|
"name": "model.layers.7.moe.gate.q_scale", |
|
"shape": [ |
|
8, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1648, |
|
"byteOffset": 19014528 |
|
}, |
|
{ |
|
"name": "model.layers.7.input_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 19016176 |
|
}, |
|
{ |
|
"name": "model.layers.7.post_attention_layernorm.weight", |
|
"shape": [ |
|
4096 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8192, |
|
"byteOffset": 19024368 |
|
}, |
|
{ |
|
"name": "model.layers.7.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
6144, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10125312, |
|
"byteOffset": 19032560 |
|
}, |
|
{ |
|
"name": "model.layers.7.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
6144, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1265664, |
|
"byteOffset": 29157872 |
|
} |
|
], |
|
"md5sum": "57c9ee0b9959695b8b87d13e1db910e7" |
|
}, |
|
{ |
|
"dataPath": "params_shard_146.bin", |
|
"format": "raw-shard", |
|
"nbytes": 26593776, |
|
"records": [ |
|
{ |
|
"name": "model.layers.7.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6750208, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.7.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 843776, |
|
"byteOffset": 6750208 |
|
}, |
|
{ |
|
"name": "model.layers.8.moe.gate.q_weight", |
|
"shape": [ |
|
8, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 13184, |
|
"byteOffset": 7593984 |
|
}, |
|
{ |
|
"name": "model.layers.8.moe.gate.q_scale", |
|
"shape": [ |
|
8, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1648, |
|
"byteOffset": 7607168 |
|
}, |
|
{ |
|
"name": "model.layers.8.self_attn.qkv_proj.q_weight", |
|
"shape": [ |
|
6144, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10125312, |
|
"byteOffset": 7608816 |
|
}, |
|
{ |
|
"name": "model.layers.8.self_attn.qkv_proj.q_scale", |
|
"shape": [ |
|
6144, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1265664, |
|
"byteOffset": 17734128 |
|
}, |
|
{ |
|
"name": "model.layers.8.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
4096, |
|
412 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6750208, |
|
"byteOffset": 18999792 |
|
}, |
|
{ |
|
"name": "model.layers.8.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
4096, |
|
103 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 843776, |
|
"byteOffset": 25750000 |
|
} |
|
], |
|
"md5sum": "96b13cc4292f94a5ded79f020e103792" |
|
} |
|
] |
|
} |