Qwen2.5-0.5B-Instruct-q0f16-MLC / ndarray-cache.json
riczhou's picture
Upload folder using huggingface_hub
2d58b01 verified
raw
history blame contribute delete
No virus
69.1 kB
{
"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": "f4f80996c9cf5596e0d51753b2b1f14e"
},
{
"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": "ed2ee8f3b2b709e4142ecb734685c80e"
},
{
"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": "86eea800d95c23f8400d320a5bec07bf"
},
{
"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": "51e8d2c38a90279f4c9fc7f365f70a92"
},
{
"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": "95afcbf0e5c95b599454aca0369dd054"
},
{
"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": "84d40e1ab0dbca5a96abc0a18047eb79"
},
{
"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": "db0da346747c05c02f6b9eb606338b6c"
},
{
"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": "a89c98d56f13486798ef976ff7c7f273"
},
{
"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": "1ec0984fe175304457fd0493059215d1"
},
{
"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": "0ff27638080f1f35dcbab2528f33bdb0"
},
{
"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": "71815ca01ee056d31d240f98b721d34d"
},
{
"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": "b0770fc0f98668eb92bf0c231f2284d9"
},
{
"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": "4ec257e595257af8449c096e4abcd332"
},
{
"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": "20f2e4f01272f0efc8eca69a1f9ca743"
},
{
"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": "821519b3fe61b23b5f42dc2adbe013aa"
},
{
"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": "34660994dffb8a58b695b3c9344dffaf"
},
{
"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": "9637483988b2da6a4dbcd82adf6ef893"
},
{
"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": "0a0493c09f6fa2865c25ccf2c7139589"
},
{
"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": "35000cbe3471848871dc981419eeabc0"
},
{
"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": "fef48ff9d1a7a2f05de05993cbc128cc"
},
{
"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": "53129459b1f22b22290a9994a59f42a0"
},
{
"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": "e531a0111b04447743b619fedce31583"
},
{
"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": "9f09f7c0f8b131b02a4a74f5315a5925"
},
{
"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": "cdfac362b9087dd6bd79f8b317225b63"
},
{
"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": "a37529efb826c1cc555fa13d4684b8d3"
}
]
}