|
{ |
|
"metadata": { |
|
"ParamSize": 170, |
|
"ParamBytes": 988065536.0, |
|
"BitsPerParam": 16.0 |
|
}, |
|
"records": [ |
|
{ |
|
"dataPath": "params_shard_0.bin", |
|
"format": "raw-shard", |
|
"nbytes": 272269312, |
|
"records": [ |
|
{ |
|
"name": "model.embed_tokens.weight", |
|
"shape": [ |
|
151936, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 272269312, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "c4b191aeb69bdf46f9fae734c7abf282" |
|
}, |
|
{ |
|
"dataPath": "params_shard_1.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29826560, |
|
"records": [ |
|
{ |
|
"name": "model.layers.0.input_layernorm.weight", |
|
"shape": [ |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1792, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.0.mlp.down_proj.weight", |
|
"shape": [ |
|
896, |
|
4864 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8716288, |
|
"byteOffset": 1792 |
|
}, |
|
{ |
|
"name": "model.layers.0.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
9728, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 17432576, |
|
"byteOffset": 8718080 |
|
}, |
|
{ |
|
"name": "model.layers.0.post_attention_layernorm.weight", |
|
"shape": [ |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1792, |
|
"byteOffset": 26150656 |
|
}, |
|
{ |
|
"name": "model.layers.0.self_attn.c_attn.bias", |
|
"shape": [ |
|
1152 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2304, |
|
"byteOffset": 26152448 |
|
}, |
|
{ |
|
"name": "model.layers.0.self_attn.c_attn.weight", |
|
"shape": [ |
|
1152, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2064384, |
|
"byteOffset": 26154752 |
|
}, |
|
{ |
|
"name": "model.layers.0.self_attn.o_proj.weight", |
|
"shape": [ |
|
896, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1605632, |
|
"byteOffset": 28219136 |
|
}, |
|
{ |
|
"name": "model.layers.1.input_layernorm.weight", |
|
"shape": [ |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1792, |
|
"byteOffset": 29824768 |
|
} |
|
], |
|
"md5sum": "d2d893d095376dade57a5e00d73b3dfb" |
|
}, |
|
{ |
|
"dataPath": "params_shard_2.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29824768, |
|
"records": [ |
|
{ |
|
"name": "model.layers.1.mlp.down_proj.weight", |
|
"shape": [ |
|
896, |
|
4864 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8716288, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.1.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
9728, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 17432576, |
|
"byteOffset": 8716288 |
|
}, |
|
{ |
|
"name": "model.layers.1.post_attention_layernorm.weight", |
|
"shape": [ |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1792, |
|
"byteOffset": 26148864 |
|
}, |
|
{ |
|
"name": "model.layers.1.self_attn.c_attn.bias", |
|
"shape": [ |
|
1152 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2304, |
|
"byteOffset": 26150656 |
|
}, |
|
{ |
|
"name": "model.layers.1.self_attn.c_attn.weight", |
|
"shape": [ |
|
1152, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2064384, |
|
"byteOffset": 26152960 |
|
}, |
|
{ |
|
"name": "model.layers.1.self_attn.o_proj.weight", |
|
"shape": [ |
|
896, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1605632, |
|
"byteOffset": 28217344 |
|
}, |
|
{ |
|
"name": "model.layers.10.input_layernorm.weight", |
|
"shape": [ |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1792, |
|
"byteOffset": 29822976 |
|
} |
|
], |
|
"md5sum": "9b045229bcf9675afdd47bec8ceb7401" |
|
}, |
|
{ |
|
"dataPath": "params_shard_3.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29824768, |
|
"records": [ |
|
{ |
|
"name": "model.layers.10.mlp.down_proj.weight", |
|
"shape": [ |
|
896, |
|
4864 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8716288, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.10.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
9728, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 17432576, |
|
"byteOffset": 8716288 |
|
}, |
|
{ |
|
"name": "model.layers.10.post_attention_layernorm.weight", |
|
"shape": [ |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1792, |
|
"byteOffset": 26148864 |
|
}, |
|
{ |
|
"name": "model.layers.10.self_attn.c_attn.bias", |
|
"shape": [ |
|
1152 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2304, |
|
"byteOffset": 26150656 |
|
}, |
|
{ |
|
"name": "model.layers.10.self_attn.c_attn.weight", |
|
"shape": [ |
|
1152, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2064384, |
|
"byteOffset": 26152960 |
|
}, |
|
{ |
|
"name": "model.layers.10.self_attn.o_proj.weight", |
|
"shape": [ |
|
896, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1605632, |
|
"byteOffset": 28217344 |
|
}, |
|
{ |
|
"name": "model.layers.11.input_layernorm.weight", |
|
"shape": [ |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1792, |
|
"byteOffset": 29822976 |
|
} |
|
], |
|
"md5sum": "88089a99efcd66b2fdd15657546f22b4" |
|
}, |
|
{ |
|
"dataPath": "params_shard_4.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29824768, |
|
"records": [ |
|
{ |
|
"name": "model.layers.11.mlp.down_proj.weight", |
|
"shape": [ |
|
896, |
|
4864 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8716288, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.11.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
9728, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 17432576, |
|
"byteOffset": 8716288 |
|
}, |
|
{ |
|
"name": "model.layers.11.post_attention_layernorm.weight", |
|
"shape": [ |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1792, |
|
"byteOffset": 26148864 |
|
}, |
|
{ |
|
"name": "model.layers.11.self_attn.c_attn.bias", |
|
"shape": [ |
|
1152 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2304, |
|
"byteOffset": 26150656 |
|
}, |
|
{ |
|
"name": "model.layers.11.self_attn.c_attn.weight", |
|
"shape": [ |
|
1152, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2064384, |
|
"byteOffset": 26152960 |
|
}, |
|
{ |
|
"name": "model.layers.11.self_attn.o_proj.weight", |
|
"shape": [ |
|
896, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1605632, |
|
"byteOffset": 28217344 |
|
}, |
|
{ |
|
"name": "model.layers.12.input_layernorm.weight", |
|
"shape": [ |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1792, |
|
"byteOffset": 29822976 |
|
} |
|
], |
|
"md5sum": "74a85b0bb53d7b51261fdac697bf4127" |
|
}, |
|
{ |
|
"dataPath": "params_shard_5.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29824768, |
|
"records": [ |
|
{ |
|
"name": "model.layers.12.mlp.down_proj.weight", |
|
"shape": [ |
|
896, |
|
4864 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8716288, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.12.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
9728, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 17432576, |
|
"byteOffset": 8716288 |
|
}, |
|
{ |
|
"name": "model.layers.12.post_attention_layernorm.weight", |
|
"shape": [ |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1792, |
|
"byteOffset": 26148864 |
|
}, |
|
{ |
|
"name": "model.layers.12.self_attn.c_attn.bias", |
|
"shape": [ |
|
1152 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2304, |
|
"byteOffset": 26150656 |
|
}, |
|
{ |
|
"name": "model.layers.12.self_attn.c_attn.weight", |
|
"shape": [ |
|
1152, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2064384, |
|
"byteOffset": 26152960 |
|
}, |
|
{ |
|
"name": "model.layers.12.self_attn.o_proj.weight", |
|
"shape": [ |
|
896, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1605632, |
|
"byteOffset": 28217344 |
|
}, |
|
{ |
|
"name": "model.layers.13.input_layernorm.weight", |
|
"shape": [ |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1792, |
|
"byteOffset": 29822976 |
|
} |
|
], |
|
"md5sum": "717a91755df2188518bd55d1efe9eae0" |
|
}, |
|
{ |
|
"dataPath": "params_shard_6.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29824768, |
|
"records": [ |
|
{ |
|
"name": "model.layers.13.mlp.down_proj.weight", |
|
"shape": [ |
|
896, |
|
4864 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8716288, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.13.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
9728, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 17432576, |
|
"byteOffset": 8716288 |
|
}, |
|
{ |
|
"name": "model.layers.13.post_attention_layernorm.weight", |
|
"shape": [ |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1792, |
|
"byteOffset": 26148864 |
|
}, |
|
{ |
|
"name": "model.layers.13.self_attn.c_attn.bias", |
|
"shape": [ |
|
1152 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2304, |
|
"byteOffset": 26150656 |
|
}, |
|
{ |
|
"name": "model.layers.13.self_attn.c_attn.weight", |
|
"shape": [ |
|
1152, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2064384, |
|
"byteOffset": 26152960 |
|
}, |
|
{ |
|
"name": "model.layers.13.self_attn.o_proj.weight", |
|
"shape": [ |
|
896, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1605632, |
|
"byteOffset": 28217344 |
|
}, |
|
{ |
|
"name": "model.layers.14.input_layernorm.weight", |
|
"shape": [ |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1792, |
|
"byteOffset": 29822976 |
|
} |
|
], |
|
"md5sum": "44ef9f488fca051b35e4ead6925b6417" |
|
}, |
|
{ |
|
"dataPath": "params_shard_7.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29824768, |
|
"records": [ |
|
{ |
|
"name": "model.layers.14.mlp.down_proj.weight", |
|
"shape": [ |
|
896, |
|
4864 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8716288, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.14.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
9728, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 17432576, |
|
"byteOffset": 8716288 |
|
}, |
|
{ |
|
"name": "model.layers.14.post_attention_layernorm.weight", |
|
"shape": [ |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1792, |
|
"byteOffset": 26148864 |
|
}, |
|
{ |
|
"name": "model.layers.14.self_attn.c_attn.bias", |
|
"shape": [ |
|
1152 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2304, |
|
"byteOffset": 26150656 |
|
}, |
|
{ |
|
"name": "model.layers.14.self_attn.c_attn.weight", |
|
"shape": [ |
|
1152, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2064384, |
|
"byteOffset": 26152960 |
|
}, |
|
{ |
|
"name": "model.layers.14.self_attn.o_proj.weight", |
|
"shape": [ |
|
896, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1605632, |
|
"byteOffset": 28217344 |
|
}, |
|
{ |
|
"name": "model.layers.15.input_layernorm.weight", |
|
"shape": [ |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1792, |
|
"byteOffset": 29822976 |
|
} |
|
], |
|
"md5sum": "4c5ea4e91f9210863ab7d4675c0a5ead" |
|
}, |
|
{ |
|
"dataPath": "params_shard_8.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29824768, |
|
"records": [ |
|
{ |
|
"name": "model.layers.15.mlp.down_proj.weight", |
|
"shape": [ |
|
896, |
|
4864 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8716288, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.15.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
9728, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 17432576, |
|
"byteOffset": 8716288 |
|
}, |
|
{ |
|
"name": "model.layers.15.post_attention_layernorm.weight", |
|
"shape": [ |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1792, |
|
"byteOffset": 26148864 |
|
}, |
|
{ |
|
"name": "model.layers.15.self_attn.c_attn.bias", |
|
"shape": [ |
|
1152 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2304, |
|
"byteOffset": 26150656 |
|
}, |
|
{ |
|
"name": "model.layers.15.self_attn.c_attn.weight", |
|
"shape": [ |
|
1152, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2064384, |
|
"byteOffset": 26152960 |
|
}, |
|
{ |
|
"name": "model.layers.15.self_attn.o_proj.weight", |
|
"shape": [ |
|
896, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1605632, |
|
"byteOffset": 28217344 |
|
}, |
|
{ |
|
"name": "model.layers.16.input_layernorm.weight", |
|
"shape": [ |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1792, |
|
"byteOffset": 29822976 |
|
} |
|
], |
|
"md5sum": "ff6b2f540077ec6e636988a0bd5bddaa" |
|
}, |
|
{ |
|
"dataPath": "params_shard_9.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29824768, |
|
"records": [ |
|
{ |
|
"name": "model.layers.16.mlp.down_proj.weight", |
|
"shape": [ |
|
896, |
|
4864 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8716288, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.16.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
9728, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 17432576, |
|
"byteOffset": 8716288 |
|
}, |
|
{ |
|
"name": "model.layers.16.post_attention_layernorm.weight", |
|
"shape": [ |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1792, |
|
"byteOffset": 26148864 |
|
}, |
|
{ |
|
"name": "model.layers.16.self_attn.c_attn.bias", |
|
"shape": [ |
|
1152 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2304, |
|
"byteOffset": 26150656 |
|
}, |
|
{ |
|
"name": "model.layers.16.self_attn.c_attn.weight", |
|
"shape": [ |
|
1152, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2064384, |
|
"byteOffset": 26152960 |
|
}, |
|
{ |
|
"name": "model.layers.16.self_attn.o_proj.weight", |
|
"shape": [ |
|
896, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1605632, |
|
"byteOffset": 28217344 |
|
}, |
|
{ |
|
"name": "model.layers.17.input_layernorm.weight", |
|
"shape": [ |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1792, |
|
"byteOffset": 29822976 |
|
} |
|
], |
|
"md5sum": "4ed7b7d8824afd10fe5da30607ac41ab" |
|
}, |
|
{ |
|
"dataPath": "params_shard_10.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29824768, |
|
"records": [ |
|
{ |
|
"name": "model.layers.17.mlp.down_proj.weight", |
|
"shape": [ |
|
896, |
|
4864 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8716288, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.17.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
9728, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 17432576, |
|
"byteOffset": 8716288 |
|
}, |
|
{ |
|
"name": "model.layers.17.post_attention_layernorm.weight", |
|
"shape": [ |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1792, |
|
"byteOffset": 26148864 |
|
}, |
|
{ |
|
"name": "model.layers.17.self_attn.c_attn.bias", |
|
"shape": [ |
|
1152 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2304, |
|
"byteOffset": 26150656 |
|
}, |
|
{ |
|
"name": "model.layers.17.self_attn.c_attn.weight", |
|
"shape": [ |
|
1152, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2064384, |
|
"byteOffset": 26152960 |
|
}, |
|
{ |
|
"name": "model.layers.17.self_attn.o_proj.weight", |
|
"shape": [ |
|
896, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1605632, |
|
"byteOffset": 28217344 |
|
}, |
|
{ |
|
"name": "model.layers.18.input_layernorm.weight", |
|
"shape": [ |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1792, |
|
"byteOffset": 29822976 |
|
} |
|
], |
|
"md5sum": "a67b6e53c651835482f14a5171f09b17" |
|
}, |
|
{ |
|
"dataPath": "params_shard_11.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29824768, |
|
"records": [ |
|
{ |
|
"name": "model.layers.18.mlp.down_proj.weight", |
|
"shape": [ |
|
896, |
|
4864 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8716288, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.18.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
9728, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 17432576, |
|
"byteOffset": 8716288 |
|
}, |
|
{ |
|
"name": "model.layers.18.post_attention_layernorm.weight", |
|
"shape": [ |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1792, |
|
"byteOffset": 26148864 |
|
}, |
|
{ |
|
"name": "model.layers.18.self_attn.c_attn.bias", |
|
"shape": [ |
|
1152 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2304, |
|
"byteOffset": 26150656 |
|
}, |
|
{ |
|
"name": "model.layers.18.self_attn.c_attn.weight", |
|
"shape": [ |
|
1152, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2064384, |
|
"byteOffset": 26152960 |
|
}, |
|
{ |
|
"name": "model.layers.18.self_attn.o_proj.weight", |
|
"shape": [ |
|
896, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1605632, |
|
"byteOffset": 28217344 |
|
}, |
|
{ |
|
"name": "model.layers.19.input_layernorm.weight", |
|
"shape": [ |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1792, |
|
"byteOffset": 29822976 |
|
} |
|
], |
|
"md5sum": "897336098613d7ad771566154c7e1cfc" |
|
}, |
|
{ |
|
"dataPath": "params_shard_12.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29824768, |
|
"records": [ |
|
{ |
|
"name": "model.layers.19.mlp.down_proj.weight", |
|
"shape": [ |
|
896, |
|
4864 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8716288, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.19.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
9728, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 17432576, |
|
"byteOffset": 8716288 |
|
}, |
|
{ |
|
"name": "model.layers.19.post_attention_layernorm.weight", |
|
"shape": [ |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1792, |
|
"byteOffset": 26148864 |
|
}, |
|
{ |
|
"name": "model.layers.19.self_attn.c_attn.bias", |
|
"shape": [ |
|
1152 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2304, |
|
"byteOffset": 26150656 |
|
}, |
|
{ |
|
"name": "model.layers.19.self_attn.c_attn.weight", |
|
"shape": [ |
|
1152, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2064384, |
|
"byteOffset": 26152960 |
|
}, |
|
{ |
|
"name": "model.layers.19.self_attn.o_proj.weight", |
|
"shape": [ |
|
896, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1605632, |
|
"byteOffset": 28217344 |
|
}, |
|
{ |
|
"name": "model.layers.2.input_layernorm.weight", |
|
"shape": [ |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1792, |
|
"byteOffset": 29822976 |
|
} |
|
], |
|
"md5sum": "d26919ddbbf1f456ccc15588c1564a08" |
|
}, |
|
{ |
|
"dataPath": "params_shard_13.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29824768, |
|
"records": [ |
|
{ |
|
"name": "model.layers.2.mlp.down_proj.weight", |
|
"shape": [ |
|
896, |
|
4864 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8716288, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.2.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
9728, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 17432576, |
|
"byteOffset": 8716288 |
|
}, |
|
{ |
|
"name": "model.layers.2.post_attention_layernorm.weight", |
|
"shape": [ |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1792, |
|
"byteOffset": 26148864 |
|
}, |
|
{ |
|
"name": "model.layers.2.self_attn.c_attn.bias", |
|
"shape": [ |
|
1152 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2304, |
|
"byteOffset": 26150656 |
|
}, |
|
{ |
|
"name": "model.layers.2.self_attn.c_attn.weight", |
|
"shape": [ |
|
1152, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2064384, |
|
"byteOffset": 26152960 |
|
}, |
|
{ |
|
"name": "model.layers.2.self_attn.o_proj.weight", |
|
"shape": [ |
|
896, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1605632, |
|
"byteOffset": 28217344 |
|
}, |
|
{ |
|
"name": "model.layers.20.input_layernorm.weight", |
|
"shape": [ |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1792, |
|
"byteOffset": 29822976 |
|
} |
|
], |
|
"md5sum": "938fe3f027477b74f902d93d7ad3d651" |
|
}, |
|
{ |
|
"dataPath": "params_shard_14.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29824768, |
|
"records": [ |
|
{ |
|
"name": "model.layers.20.mlp.down_proj.weight", |
|
"shape": [ |
|
896, |
|
4864 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8716288, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.20.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
9728, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 17432576, |
|
"byteOffset": 8716288 |
|
}, |
|
{ |
|
"name": "model.layers.20.post_attention_layernorm.weight", |
|
"shape": [ |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1792, |
|
"byteOffset": 26148864 |
|
}, |
|
{ |
|
"name": "model.layers.20.self_attn.c_attn.bias", |
|
"shape": [ |
|
1152 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2304, |
|
"byteOffset": 26150656 |
|
}, |
|
{ |
|
"name": "model.layers.20.self_attn.c_attn.weight", |
|
"shape": [ |
|
1152, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2064384, |
|
"byteOffset": 26152960 |
|
}, |
|
{ |
|
"name": "model.layers.20.self_attn.o_proj.weight", |
|
"shape": [ |
|
896, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1605632, |
|
"byteOffset": 28217344 |
|
}, |
|
{ |
|
"name": "model.layers.21.input_layernorm.weight", |
|
"shape": [ |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1792, |
|
"byteOffset": 29822976 |
|
} |
|
], |
|
"md5sum": "9fd65e0cf86c38ae09507665ccf179d8" |
|
}, |
|
{ |
|
"dataPath": "params_shard_15.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29824768, |
|
"records": [ |
|
{ |
|
"name": "model.layers.21.mlp.down_proj.weight", |
|
"shape": [ |
|
896, |
|
4864 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8716288, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.21.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
9728, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 17432576, |
|
"byteOffset": 8716288 |
|
}, |
|
{ |
|
"name": "model.layers.21.post_attention_layernorm.weight", |
|
"shape": [ |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1792, |
|
"byteOffset": 26148864 |
|
}, |
|
{ |
|
"name": "model.layers.21.self_attn.c_attn.bias", |
|
"shape": [ |
|
1152 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2304, |
|
"byteOffset": 26150656 |
|
}, |
|
{ |
|
"name": "model.layers.21.self_attn.c_attn.weight", |
|
"shape": [ |
|
1152, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2064384, |
|
"byteOffset": 26152960 |
|
}, |
|
{ |
|
"name": "model.layers.21.self_attn.o_proj.weight", |
|
"shape": [ |
|
896, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1605632, |
|
"byteOffset": 28217344 |
|
}, |
|
{ |
|
"name": "model.layers.22.input_layernorm.weight", |
|
"shape": [ |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1792, |
|
"byteOffset": 29822976 |
|
} |
|
], |
|
"md5sum": "bd913451cecb2c7e14a48d81c685377a" |
|
}, |
|
{ |
|
"dataPath": "params_shard_16.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29824768, |
|
"records": [ |
|
{ |
|
"name": "model.layers.22.mlp.down_proj.weight", |
|
"shape": [ |
|
896, |
|
4864 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8716288, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.22.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
9728, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 17432576, |
|
"byteOffset": 8716288 |
|
}, |
|
{ |
|
"name": "model.layers.22.post_attention_layernorm.weight", |
|
"shape": [ |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1792, |
|
"byteOffset": 26148864 |
|
}, |
|
{ |
|
"name": "model.layers.22.self_attn.c_attn.bias", |
|
"shape": [ |
|
1152 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2304, |
|
"byteOffset": 26150656 |
|
}, |
|
{ |
|
"name": "model.layers.22.self_attn.c_attn.weight", |
|
"shape": [ |
|
1152, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2064384, |
|
"byteOffset": 26152960 |
|
}, |
|
{ |
|
"name": "model.layers.22.self_attn.o_proj.weight", |
|
"shape": [ |
|
896, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1605632, |
|
"byteOffset": 28217344 |
|
}, |
|
{ |
|
"name": "model.layers.23.input_layernorm.weight", |
|
"shape": [ |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1792, |
|
"byteOffset": 29822976 |
|
} |
|
], |
|
"md5sum": "f743212068e10689ffd009fe18aec9ea" |
|
}, |
|
{ |
|
"dataPath": "params_shard_17.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29824768, |
|
"records": [ |
|
{ |
|
"name": "model.layers.23.mlp.down_proj.weight", |
|
"shape": [ |
|
896, |
|
4864 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8716288, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.23.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
9728, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 17432576, |
|
"byteOffset": 8716288 |
|
}, |
|
{ |
|
"name": "model.layers.23.post_attention_layernorm.weight", |
|
"shape": [ |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1792, |
|
"byteOffset": 26148864 |
|
}, |
|
{ |
|
"name": "model.layers.23.self_attn.c_attn.bias", |
|
"shape": [ |
|
1152 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2304, |
|
"byteOffset": 26150656 |
|
}, |
|
{ |
|
"name": "model.layers.23.self_attn.c_attn.weight", |
|
"shape": [ |
|
1152, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2064384, |
|
"byteOffset": 26152960 |
|
}, |
|
{ |
|
"name": "model.layers.23.self_attn.o_proj.weight", |
|
"shape": [ |
|
896, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1605632, |
|
"byteOffset": 28217344 |
|
}, |
|
{ |
|
"name": "model.layers.3.input_layernorm.weight", |
|
"shape": [ |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1792, |
|
"byteOffset": 29822976 |
|
} |
|
], |
|
"md5sum": "28dd1b12ea0e4a9526dd75a216686d23" |
|
}, |
|
{ |
|
"dataPath": "params_shard_18.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29824768, |
|
"records": [ |
|
{ |
|
"name": "model.layers.3.mlp.down_proj.weight", |
|
"shape": [ |
|
896, |
|
4864 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8716288, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.3.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
9728, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 17432576, |
|
"byteOffset": 8716288 |
|
}, |
|
{ |
|
"name": "model.layers.3.post_attention_layernorm.weight", |
|
"shape": [ |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1792, |
|
"byteOffset": 26148864 |
|
}, |
|
{ |
|
"name": "model.layers.3.self_attn.c_attn.bias", |
|
"shape": [ |
|
1152 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2304, |
|
"byteOffset": 26150656 |
|
}, |
|
{ |
|
"name": "model.layers.3.self_attn.c_attn.weight", |
|
"shape": [ |
|
1152, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2064384, |
|
"byteOffset": 26152960 |
|
}, |
|
{ |
|
"name": "model.layers.3.self_attn.o_proj.weight", |
|
"shape": [ |
|
896, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1605632, |
|
"byteOffset": 28217344 |
|
}, |
|
{ |
|
"name": "model.layers.4.input_layernorm.weight", |
|
"shape": [ |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1792, |
|
"byteOffset": 29822976 |
|
} |
|
], |
|
"md5sum": "1b8922e494246cedaf4678bb653d5b21" |
|
}, |
|
{ |
|
"dataPath": "params_shard_19.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29824768, |
|
"records": [ |
|
{ |
|
"name": "model.layers.4.mlp.down_proj.weight", |
|
"shape": [ |
|
896, |
|
4864 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8716288, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.4.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
9728, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 17432576, |
|
"byteOffset": 8716288 |
|
}, |
|
{ |
|
"name": "model.layers.4.post_attention_layernorm.weight", |
|
"shape": [ |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1792, |
|
"byteOffset": 26148864 |
|
}, |
|
{ |
|
"name": "model.layers.4.self_attn.c_attn.bias", |
|
"shape": [ |
|
1152 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2304, |
|
"byteOffset": 26150656 |
|
}, |
|
{ |
|
"name": "model.layers.4.self_attn.c_attn.weight", |
|
"shape": [ |
|
1152, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2064384, |
|
"byteOffset": 26152960 |
|
}, |
|
{ |
|
"name": "model.layers.4.self_attn.o_proj.weight", |
|
"shape": [ |
|
896, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1605632, |
|
"byteOffset": 28217344 |
|
}, |
|
{ |
|
"name": "model.layers.5.input_layernorm.weight", |
|
"shape": [ |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1792, |
|
"byteOffset": 29822976 |
|
} |
|
], |
|
"md5sum": "38a0c5edcabb885b03046be7b497d446" |
|
}, |
|
{ |
|
"dataPath": "params_shard_20.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29824768, |
|
"records": [ |
|
{ |
|
"name": "model.layers.5.mlp.down_proj.weight", |
|
"shape": [ |
|
896, |
|
4864 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8716288, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.5.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
9728, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 17432576, |
|
"byteOffset": 8716288 |
|
}, |
|
{ |
|
"name": "model.layers.5.post_attention_layernorm.weight", |
|
"shape": [ |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1792, |
|
"byteOffset": 26148864 |
|
}, |
|
{ |
|
"name": "model.layers.5.self_attn.c_attn.bias", |
|
"shape": [ |
|
1152 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2304, |
|
"byteOffset": 26150656 |
|
}, |
|
{ |
|
"name": "model.layers.5.self_attn.c_attn.weight", |
|
"shape": [ |
|
1152, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2064384, |
|
"byteOffset": 26152960 |
|
}, |
|
{ |
|
"name": "model.layers.5.self_attn.o_proj.weight", |
|
"shape": [ |
|
896, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1605632, |
|
"byteOffset": 28217344 |
|
}, |
|
{ |
|
"name": "model.layers.6.input_layernorm.weight", |
|
"shape": [ |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1792, |
|
"byteOffset": 29822976 |
|
} |
|
], |
|
"md5sum": "0653163b6ccd9d416a607c1f58fac827" |
|
}, |
|
{ |
|
"dataPath": "params_shard_21.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29824768, |
|
"records": [ |
|
{ |
|
"name": "model.layers.6.mlp.down_proj.weight", |
|
"shape": [ |
|
896, |
|
4864 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8716288, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.6.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
9728, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 17432576, |
|
"byteOffset": 8716288 |
|
}, |
|
{ |
|
"name": "model.layers.6.post_attention_layernorm.weight", |
|
"shape": [ |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1792, |
|
"byteOffset": 26148864 |
|
}, |
|
{ |
|
"name": "model.layers.6.self_attn.c_attn.bias", |
|
"shape": [ |
|
1152 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2304, |
|
"byteOffset": 26150656 |
|
}, |
|
{ |
|
"name": "model.layers.6.self_attn.c_attn.weight", |
|
"shape": [ |
|
1152, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2064384, |
|
"byteOffset": 26152960 |
|
}, |
|
{ |
|
"name": "model.layers.6.self_attn.o_proj.weight", |
|
"shape": [ |
|
896, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1605632, |
|
"byteOffset": 28217344 |
|
}, |
|
{ |
|
"name": "model.layers.7.input_layernorm.weight", |
|
"shape": [ |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1792, |
|
"byteOffset": 29822976 |
|
} |
|
], |
|
"md5sum": "7bf5a3d331e20a6c94e24e0db9ff90f3" |
|
}, |
|
{ |
|
"dataPath": "params_shard_22.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29824768, |
|
"records": [ |
|
{ |
|
"name": "model.layers.7.mlp.down_proj.weight", |
|
"shape": [ |
|
896, |
|
4864 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8716288, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.7.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
9728, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 17432576, |
|
"byteOffset": 8716288 |
|
}, |
|
{ |
|
"name": "model.layers.7.post_attention_layernorm.weight", |
|
"shape": [ |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1792, |
|
"byteOffset": 26148864 |
|
}, |
|
{ |
|
"name": "model.layers.7.self_attn.c_attn.bias", |
|
"shape": [ |
|
1152 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2304, |
|
"byteOffset": 26150656 |
|
}, |
|
{ |
|
"name": "model.layers.7.self_attn.c_attn.weight", |
|
"shape": [ |
|
1152, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2064384, |
|
"byteOffset": 26152960 |
|
}, |
|
{ |
|
"name": "model.layers.7.self_attn.o_proj.weight", |
|
"shape": [ |
|
896, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1605632, |
|
"byteOffset": 28217344 |
|
}, |
|
{ |
|
"name": "model.layers.8.input_layernorm.weight", |
|
"shape": [ |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1792, |
|
"byteOffset": 29822976 |
|
} |
|
], |
|
"md5sum": "fe922d33f03d31c7d2b41357680168d1" |
|
}, |
|
{ |
|
"dataPath": "params_shard_23.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29824768, |
|
"records": [ |
|
{ |
|
"name": "model.layers.8.mlp.down_proj.weight", |
|
"shape": [ |
|
896, |
|
4864 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8716288, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.8.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
9728, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 17432576, |
|
"byteOffset": 8716288 |
|
}, |
|
{ |
|
"name": "model.layers.8.post_attention_layernorm.weight", |
|
"shape": [ |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1792, |
|
"byteOffset": 26148864 |
|
}, |
|
{ |
|
"name": "model.layers.8.self_attn.c_attn.bias", |
|
"shape": [ |
|
1152 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2304, |
|
"byteOffset": 26150656 |
|
}, |
|
{ |
|
"name": "model.layers.8.self_attn.c_attn.weight", |
|
"shape": [ |
|
1152, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2064384, |
|
"byteOffset": 26152960 |
|
}, |
|
{ |
|
"name": "model.layers.8.self_attn.o_proj.weight", |
|
"shape": [ |
|
896, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1605632, |
|
"byteOffset": 28217344 |
|
}, |
|
{ |
|
"name": "model.layers.9.input_layernorm.weight", |
|
"shape": [ |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1792, |
|
"byteOffset": 29822976 |
|
} |
|
], |
|
"md5sum": "faa33e73829b77b5d3b60edd5a30aa6b" |
|
}, |
|
{ |
|
"dataPath": "params_shard_24.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29824768, |
|
"records": [ |
|
{ |
|
"name": "model.layers.9.mlp.down_proj.weight", |
|
"shape": [ |
|
896, |
|
4864 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8716288, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.9.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
9728, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 17432576, |
|
"byteOffset": 8716288 |
|
}, |
|
{ |
|
"name": "model.layers.9.post_attention_layernorm.weight", |
|
"shape": [ |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1792, |
|
"byteOffset": 26148864 |
|
}, |
|
{ |
|
"name": "model.layers.9.self_attn.c_attn.bias", |
|
"shape": [ |
|
1152 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2304, |
|
"byteOffset": 26150656 |
|
}, |
|
{ |
|
"name": "model.layers.9.self_attn.c_attn.weight", |
|
"shape": [ |
|
1152, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 2064384, |
|
"byteOffset": 26152960 |
|
}, |
|
{ |
|
"name": "model.layers.9.self_attn.o_proj.weight", |
|
"shape": [ |
|
896, |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1605632, |
|
"byteOffset": 28217344 |
|
}, |
|
{ |
|
"name": "model.norm.weight", |
|
"shape": [ |
|
896 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1792, |
|
"byteOffset": 29822976 |
|
} |
|
], |
|
"md5sum": "68d1f5a59a35a7aa6a48e6276ea3eb22" |
|
} |
|
] |
|
} |