qwen-2-q0f16-MLC / ndarray-cache.json
geonmin-kim's picture
Upload folder using huggingface_hub
a78d3ba verified
raw
history blame
15.7 kB
{
"metadata": {
"ParamSize": 31,
"ParamBytes": 4044459008.0,
"BitsPerParam": 16.0
},
"records": [
{
"dataPath": "params_shard_0.bin",
"format": "raw-shard",
"nbytes": 1089994752,
"records": [
{
"name": "model.embed_tokens.weight",
"shape": [
152064,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1089994752,
"byteOffset": 0
}
],
"md5sum": "1096c3043fce52d07e686e7d70c5687e"
},
{
"dataPath": "params_shard_1.bin",
"format": "raw-shard",
"nbytes": 25690112,
"records": [
{
"name": "model.layers.0.self_attn.o_proj.weight",
"shape": [
3584,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 25690112,
"byteOffset": 0
}
],
"md5sum": "fa12518f256dab0e627e73cd62f21382"
},
{
"dataPath": "params_shard_2.bin",
"format": "raw-shard",
"nbytes": 271581184,
"records": [
{
"name": "model.layers.0.mlp.gate_up_proj.weight",
"shape": [
37888,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 271581184,
"byteOffset": 0
}
],
"md5sum": "7c93523d9c9ec575cc22618781e70be9"
},
{
"dataPath": "params_shard_3.bin",
"format": "raw-shard",
"nbytes": 135790592,
"records": [
{
"name": "model.layers.0.mlp.down_proj.weight",
"shape": [
3584,
18944
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 135790592,
"byteOffset": 0
}
],
"md5sum": "24b1add61255660dbf0e160b5f01eae0"
},
{
"dataPath": "params_shard_4.bin",
"format": "raw-shard",
"nbytes": 33030144,
"records": [
{
"name": "model.layers.1.self_attn.c_attn.weight",
"shape": [
4608,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 33030144,
"byteOffset": 0
}
],
"md5sum": "c0eb62c7ee3c6ab51d17be1cedd4f64f"
},
{
"dataPath": "params_shard_5.bin",
"format": "raw-shard",
"nbytes": 25690112,
"records": [
{
"name": "model.layers.1.self_attn.o_proj.weight",
"shape": [
3584,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 25690112,
"byteOffset": 0
}
],
"md5sum": "9722bac502585ec42f5af5a0a7b00046"
},
{
"dataPath": "params_shard_6.bin",
"format": "raw-shard",
"nbytes": 271581184,
"records": [
{
"name": "model.layers.1.mlp.gate_up_proj.weight",
"shape": [
37888,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 271581184,
"byteOffset": 0
}
],
"md5sum": "a19d16581a1cbb884505e130b635797e"
},
{
"dataPath": "params_shard_7.bin",
"format": "raw-shard",
"nbytes": 135790592,
"records": [
{
"name": "model.layers.1.mlp.down_proj.weight",
"shape": [
3584,
18944
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 135790592,
"byteOffset": 0
}
],
"md5sum": "14ccce743b3fc0660e2b0132db110ba5"
},
{
"dataPath": "params_shard_8.bin",
"format": "raw-shard",
"nbytes": 33030144,
"records": [
{
"name": "model.layers.2.self_attn.c_attn.weight",
"shape": [
4608,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 33030144,
"byteOffset": 0
}
],
"md5sum": "f2a26b2d7170a6ed2cf070f9c0815f33"
},
{
"dataPath": "params_shard_9.bin",
"format": "raw-shard",
"nbytes": 25690112,
"records": [
{
"name": "model.layers.2.self_attn.o_proj.weight",
"shape": [
3584,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 25690112,
"byteOffset": 0
}
],
"md5sum": "ff56b50721f25ec8693491f6776565bc"
},
{
"dataPath": "params_shard_10.bin",
"format": "raw-shard",
"nbytes": 271581184,
"records": [
{
"name": "model.layers.2.mlp.gate_up_proj.weight",
"shape": [
37888,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 271581184,
"byteOffset": 0
}
],
"md5sum": "1de3679fdbffb14849545694266a49a4"
},
{
"dataPath": "params_shard_11.bin",
"format": "raw-shard",
"nbytes": 135790592,
"records": [
{
"name": "model.layers.2.mlp.down_proj.weight",
"shape": [
3584,
18944
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 135790592,
"byteOffset": 0
}
],
"md5sum": "a1ac20b3b6a4dbac225c68dd1e484e0f"
},
{
"dataPath": "params_shard_12.bin",
"format": "raw-shard",
"nbytes": 33030144,
"records": [
{
"name": "model.layers.3.self_attn.c_attn.weight",
"shape": [
4608,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 33030144,
"byteOffset": 0
}
],
"md5sum": "b87a624913f69fc8783afa80e04d5655"
},
{
"dataPath": "params_shard_13.bin",
"format": "raw-shard",
"nbytes": 25690112,
"records": [
{
"name": "model.layers.3.self_attn.o_proj.weight",
"shape": [
3584,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 25690112,
"byteOffset": 0
}
],
"md5sum": "13d09067604b7f0c1d63c98937b4e174"
},
{
"dataPath": "params_shard_14.bin",
"format": "raw-shard",
"nbytes": 271581184,
"records": [
{
"name": "model.layers.3.mlp.gate_up_proj.weight",
"shape": [
37888,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 271581184,
"byteOffset": 0
}
],
"md5sum": "b6e2d8049e71f27bdd1a704f6e8f537a"
},
{
"dataPath": "params_shard_15.bin",
"format": "raw-shard",
"nbytes": 135790592,
"records": [
{
"name": "model.layers.3.mlp.down_proj.weight",
"shape": [
3584,
18944
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 135790592,
"byteOffset": 0
}
],
"md5sum": "165dc6852e9590980d6b93e38b55e09f"
},
{
"dataPath": "params_shard_16.bin",
"format": "raw-shard",
"nbytes": 1089994752,
"records": [
{
"name": "lm_head.weight",
"shape": [
152064,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1089994752,
"byteOffset": 0
}
],
"md5sum": "b0a68a612362cfcfb3d746bbd9bbb73d"
},
{
"dataPath": "params_shard_17.bin",
"format": "raw-shard",
"nbytes": 33131520,
"records": [
{
"name": "model.layers.0.self_attn.c_attn.weight",
"shape": [
4608,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 33030144,
"byteOffset": 0
},
{
"name": "model.layers.0.self_attn.c_attn.bias",
"shape": [
4608
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 9216,
"byteOffset": 33030144
},
{
"name": "model.layers.0.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 33039360
},
{
"name": "model.layers.0.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 33046528
},
{
"name": "model.layers.1.self_attn.c_attn.bias",
"shape": [
4608
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 9216,
"byteOffset": 33053696
},
{
"name": "model.layers.1.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 33062912
},
{
"name": "model.layers.1.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 33070080
},
{
"name": "model.layers.2.self_attn.c_attn.bias",
"shape": [
4608
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 9216,
"byteOffset": 33077248
},
{
"name": "model.layers.2.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 33086464
},
{
"name": "model.layers.2.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 33093632
},
{
"name": "model.layers.3.self_attn.c_attn.bias",
"shape": [
4608
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 9216,
"byteOffset": 33100800
},
{
"name": "model.layers.3.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 33110016
},
{
"name": "model.layers.3.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 33117184
},
{
"name": "model.norm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 33124352
}
],
"md5sum": "418e357fec9f143413cbad405043e1a3"
}
]
}