illian01's picture
Add weights and config
3f3de7f
raw
history blame
80.8 kB
{
"metadata": {
"ParamSize": 175,
"ParamBytes": 2082955264.0,
"BitsPerParam": 4.50044525764654
},
"records": [
{
"dataPath": "params_shard_0.bin",
"format": "raw-shard",
"nbytes": 65536000,
"records": [
{
"name": "model.embed_tokens.q_weight",
"shape": [
32000,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 65536000,
"byteOffset": 0
}
],
"md5sum": "0c80f07c0e705a2e2c1cd1d241a4b609"
},
{
"dataPath": "params_shard_1.bin",
"format": "raw-shard",
"nbytes": 33357824,
"records": [
{
"name": "model.embed_tokens.q_scale",
"shape": [
32000,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192000,
"byteOffset": 0
},
{
"name": "model.layers.0.self_attn.qkv_proj.q_weight",
"shape": [
12288,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 8192000
}
],
"md5sum": "7cb2cf4d089efc4e8f0398043ee2d587"
},
{
"dataPath": "params_shard_2.bin",
"format": "raw-shard",
"nbytes": 45088768,
"records": [
{
"name": "model.layers.0.mlp.gate_up_proj.q_weight",
"shape": [
22016,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 45088768,
"byteOffset": 0
}
],
"md5sum": "caa1243424708896db6a17dfe758e06b"
},
{
"dataPath": "params_shard_3.bin",
"format": "raw-shard",
"nbytes": 22544384,
"records": [
{
"name": "model.layers.0.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 22544384,
"byteOffset": 0
}
],
"md5sum": "11240ff24505ab642aabdf77448f3d25"
},
{
"dataPath": "params_shard_4.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.1.self_attn.qkv_proj.q_weight",
"shape": [
12288,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "c6db109227d5e3f1659a6641f04510cf"
},
{
"dataPath": "params_shard_5.bin",
"format": "raw-shard",
"nbytes": 32587776,
"records": [
{
"name": "model.layers.0.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 0
},
{
"name": "model.layers.0.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 3145728
},
{
"name": "model.layers.0.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 11534336
},
{
"name": "model.layers.0.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 12582912
},
{
"name": "model.layers.0.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 18219008
},
{
"name": "model.layers.0.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21037056
},
{
"name": "model.layers.0.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21045248
},
{
"name": "model.layers.1.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 21053440
},
{
"name": "model.layers.1.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 24199168
}
],
"md5sum": "180a418bc044d5be3e3e3cbd969b7ac8"
},
{
"dataPath": "params_shard_6.bin",
"format": "raw-shard",
"nbytes": 45088768,
"records": [
{
"name": "model.layers.1.mlp.gate_up_proj.q_weight",
"shape": [
22016,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 45088768,
"byteOffset": 0
}
],
"md5sum": "21d1038acf0a42100d056bd7934e7114"
},
{
"dataPath": "params_shard_7.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.2.self_attn.qkv_proj.q_weight",
"shape": [
12288,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "74b85fe2af8fe0bd74a60cdef00dab56"
},
{
"dataPath": "params_shard_8.bin",
"format": "raw-shard",
"nbytes": 32063488,
"records": [
{
"name": "model.layers.1.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 0
},
{
"name": "model.layers.1.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 1048576
},
{
"name": "model.layers.1.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 22544384,
"byteOffset": 6684672
},
{
"name": "model.layers.1.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 29229056
},
{
"name": "model.layers.1.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 32047104
},
{
"name": "model.layers.1.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 32055296
}
],
"md5sum": "56643a500f2732bdee21c975ff084ae6"
},
{
"dataPath": "params_shard_9.bin",
"format": "raw-shard",
"nbytes": 45088768,
"records": [
{
"name": "model.layers.2.mlp.gate_up_proj.q_weight",
"shape": [
22016,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 45088768,
"byteOffset": 0
}
],
"md5sum": "f2f2ef6beb194aa2d8a974a4f83c1a1c"
},
{
"dataPath": "params_shard_10.bin",
"format": "raw-shard",
"nbytes": 22544384,
"records": [
{
"name": "model.layers.2.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 22544384,
"byteOffset": 0
}
],
"md5sum": "fc02a588f3f4fc8a9d61294c88150097"
},
{
"dataPath": "params_shard_11.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.3.self_attn.qkv_proj.q_weight",
"shape": [
12288,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "2f8c920884c554d1c068bd586bbaf716"
},
{
"dataPath": "params_shard_12.bin",
"format": "raw-shard",
"nbytes": 32587776,
"records": [
{
"name": "model.layers.2.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 0
},
{
"name": "model.layers.2.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 3145728
},
{
"name": "model.layers.2.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 11534336
},
{
"name": "model.layers.2.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 12582912
},
{
"name": "model.layers.2.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 18219008
},
{
"name": "model.layers.2.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21037056
},
{
"name": "model.layers.2.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21045248
},
{
"name": "model.layers.3.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 21053440
},
{
"name": "model.layers.3.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 24199168
}
],
"md5sum": "966951e3ee637b3d25f2ccf5c33962ee"
},
{
"dataPath": "params_shard_13.bin",
"format": "raw-shard",
"nbytes": 45088768,
"records": [
{
"name": "model.layers.3.mlp.gate_up_proj.q_weight",
"shape": [
22016,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 45088768,
"byteOffset": 0
}
],
"md5sum": "feb8d01187dde104bbc36b0015648647"
},
{
"dataPath": "params_shard_14.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.4.self_attn.qkv_proj.q_weight",
"shape": [
12288,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "cc381114da3cc1b73f351e768d9c78d0"
},
{
"dataPath": "params_shard_15.bin",
"format": "raw-shard",
"nbytes": 32063488,
"records": [
{
"name": "model.layers.3.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 0
},
{
"name": "model.layers.3.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 1048576
},
{
"name": "model.layers.3.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 22544384,
"byteOffset": 6684672
},
{
"name": "model.layers.3.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 29229056
},
{
"name": "model.layers.3.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 32047104
},
{
"name": "model.layers.3.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 32055296
}
],
"md5sum": "9c4f4401e504ff51a8670de6b8cd10c9"
},
{
"dataPath": "params_shard_16.bin",
"format": "raw-shard",
"nbytes": 45088768,
"records": [
{
"name": "model.layers.4.mlp.gate_up_proj.q_weight",
"shape": [
22016,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 45088768,
"byteOffset": 0
}
],
"md5sum": "969a13b8bd14af892f1a47de6f3bdf6f"
},
{
"dataPath": "params_shard_17.bin",
"format": "raw-shard",
"nbytes": 22544384,
"records": [
{
"name": "model.layers.4.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 22544384,
"byteOffset": 0
}
],
"md5sum": "bbd77d563bda4d127ad7a44a5234c72e"
},
{
"dataPath": "params_shard_18.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.5.self_attn.qkv_proj.q_weight",
"shape": [
12288,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "2f42b0fb6f06cdd44054e42926064765"
},
{
"dataPath": "params_shard_19.bin",
"format": "raw-shard",
"nbytes": 32587776,
"records": [
{
"name": "model.layers.4.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 0
},
{
"name": "model.layers.4.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 3145728
},
{
"name": "model.layers.4.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 11534336
},
{
"name": "model.layers.4.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 12582912
},
{
"name": "model.layers.4.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 18219008
},
{
"name": "model.layers.4.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21037056
},
{
"name": "model.layers.4.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21045248
},
{
"name": "model.layers.5.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 21053440
},
{
"name": "model.layers.5.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 24199168
}
],
"md5sum": "95fee31a0e963a5282a83fbf4903b056"
},
{
"dataPath": "params_shard_20.bin",
"format": "raw-shard",
"nbytes": 45088768,
"records": [
{
"name": "model.layers.5.mlp.gate_up_proj.q_weight",
"shape": [
22016,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 45088768,
"byteOffset": 0
}
],
"md5sum": "20f7954fd752aa89db92760d3191eddf"
},
{
"dataPath": "params_shard_21.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.6.self_attn.qkv_proj.q_weight",
"shape": [
12288,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "05d71f8b2fd3719876737bfba90ee4c0"
},
{
"dataPath": "params_shard_22.bin",
"format": "raw-shard",
"nbytes": 32063488,
"records": [
{
"name": "model.layers.5.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 0
},
{
"name": "model.layers.5.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 1048576
},
{
"name": "model.layers.5.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 22544384,
"byteOffset": 6684672
},
{
"name": "model.layers.5.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 29229056
},
{
"name": "model.layers.5.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 32047104
},
{
"name": "model.layers.5.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 32055296
}
],
"md5sum": "1f64e37be45d052fe3d264fd700fb53c"
},
{
"dataPath": "params_shard_23.bin",
"format": "raw-shard",
"nbytes": 45088768,
"records": [
{
"name": "model.layers.6.mlp.gate_up_proj.q_weight",
"shape": [
22016,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 45088768,
"byteOffset": 0
}
],
"md5sum": "2ef9699b390d6e8706188197ec40c8f1"
},
{
"dataPath": "params_shard_24.bin",
"format": "raw-shard",
"nbytes": 22544384,
"records": [
{
"name": "model.layers.6.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 22544384,
"byteOffset": 0
}
],
"md5sum": "6cd3ca07a86d12f62ee11ccf2379d86d"
},
{
"dataPath": "params_shard_25.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.7.self_attn.qkv_proj.q_weight",
"shape": [
12288,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "ae283ce0ce29814081b952312f0e181c"
},
{
"dataPath": "params_shard_26.bin",
"format": "raw-shard",
"nbytes": 32587776,
"records": [
{
"name": "model.layers.6.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 0
},
{
"name": "model.layers.6.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 3145728
},
{
"name": "model.layers.6.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 11534336
},
{
"name": "model.layers.6.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 12582912
},
{
"name": "model.layers.6.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 18219008
},
{
"name": "model.layers.6.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21037056
},
{
"name": "model.layers.6.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21045248
},
{
"name": "model.layers.7.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 21053440
},
{
"name": "model.layers.7.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 24199168
}
],
"md5sum": "fcba23e82341dce9cb3ad860da7d2f3f"
},
{
"dataPath": "params_shard_27.bin",
"format": "raw-shard",
"nbytes": 45088768,
"records": [
{
"name": "model.layers.7.mlp.gate_up_proj.q_weight",
"shape": [
22016,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 45088768,
"byteOffset": 0
}
],
"md5sum": "699b46d2d1f5da456315aa38db192157"
},
{
"dataPath": "params_shard_28.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.8.self_attn.qkv_proj.q_weight",
"shape": [
12288,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "bd62335afdfb632a45cc2e6c91f1b44b"
},
{
"dataPath": "params_shard_29.bin",
"format": "raw-shard",
"nbytes": 32063488,
"records": [
{
"name": "model.layers.7.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 0
},
{
"name": "model.layers.7.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 1048576
},
{
"name": "model.layers.7.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 22544384,
"byteOffset": 6684672
},
{
"name": "model.layers.7.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 29229056
},
{
"name": "model.layers.7.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 32047104
},
{
"name": "model.layers.7.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 32055296
}
],
"md5sum": "74c0d61cfa83c3e7082da4f40da88746"
},
{
"dataPath": "params_shard_30.bin",
"format": "raw-shard",
"nbytes": 45088768,
"records": [
{
"name": "model.layers.8.mlp.gate_up_proj.q_weight",
"shape": [
22016,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 45088768,
"byteOffset": 0
}
],
"md5sum": "3ef2125e3d6ad0ba41b0d52d4a935cd0"
},
{
"dataPath": "params_shard_31.bin",
"format": "raw-shard",
"nbytes": 22544384,
"records": [
{
"name": "model.layers.8.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 22544384,
"byteOffset": 0
}
],
"md5sum": "2e32a84420247b18d1543a2e2cbb5ca6"
},
{
"dataPath": "params_shard_32.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.9.self_attn.qkv_proj.q_weight",
"shape": [
12288,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "7219fa6ba4178ab2468e66b64eb925a6"
},
{
"dataPath": "params_shard_33.bin",
"format": "raw-shard",
"nbytes": 32587776,
"records": [
{
"name": "model.layers.8.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 0
},
{
"name": "model.layers.8.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 3145728
},
{
"name": "model.layers.8.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 11534336
},
{
"name": "model.layers.8.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 12582912
},
{
"name": "model.layers.8.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 18219008
},
{
"name": "model.layers.8.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21037056
},
{
"name": "model.layers.8.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21045248
},
{
"name": "model.layers.9.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 21053440
},
{
"name": "model.layers.9.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 24199168
}
],
"md5sum": "4ba50eb46a4852cc6eea12850222bef7"
},
{
"dataPath": "params_shard_34.bin",
"format": "raw-shard",
"nbytes": 45088768,
"records": [
{
"name": "model.layers.9.mlp.gate_up_proj.q_weight",
"shape": [
22016,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 45088768,
"byteOffset": 0
}
],
"md5sum": "e8a62f76bd551abcd10c3e3e125b7c5b"
},
{
"dataPath": "params_shard_35.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.10.self_attn.qkv_proj.q_weight",
"shape": [
12288,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "2302523927b4273eeb18c56c1976f8cc"
},
{
"dataPath": "params_shard_36.bin",
"format": "raw-shard",
"nbytes": 32063488,
"records": [
{
"name": "model.layers.9.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 0
},
{
"name": "model.layers.9.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 1048576
},
{
"name": "model.layers.9.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 22544384,
"byteOffset": 6684672
},
{
"name": "model.layers.9.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 29229056
},
{
"name": "model.layers.9.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 32047104
},
{
"name": "model.layers.9.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 32055296
}
],
"md5sum": "873054a18b28147ccbc0bb8ec58c2201"
},
{
"dataPath": "params_shard_37.bin",
"format": "raw-shard",
"nbytes": 45088768,
"records": [
{
"name": "model.layers.10.mlp.gate_up_proj.q_weight",
"shape": [
22016,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 45088768,
"byteOffset": 0
}
],
"md5sum": "4e7af0f5b05a0f9c399088231cd684ee"
},
{
"dataPath": "params_shard_38.bin",
"format": "raw-shard",
"nbytes": 22544384,
"records": [
{
"name": "model.layers.10.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 22544384,
"byteOffset": 0
}
],
"md5sum": "5993975a2b6771cbcda9d79ee7f31245"
},
{
"dataPath": "params_shard_39.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.11.self_attn.qkv_proj.q_weight",
"shape": [
12288,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "1951fdb99a782b3dbc318d4f15bd63fa"
},
{
"dataPath": "params_shard_40.bin",
"format": "raw-shard",
"nbytes": 32587776,
"records": [
{
"name": "model.layers.10.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 0
},
{
"name": "model.layers.10.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 3145728
},
{
"name": "model.layers.10.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 11534336
},
{
"name": "model.layers.10.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 12582912
},
{
"name": "model.layers.10.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 18219008
},
{
"name": "model.layers.10.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21037056
},
{
"name": "model.layers.10.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21045248
},
{
"name": "model.layers.11.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 21053440
},
{
"name": "model.layers.11.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 24199168
}
],
"md5sum": "fd6c4c9bbb84ef263171a5614daa76cc"
},
{
"dataPath": "params_shard_41.bin",
"format": "raw-shard",
"nbytes": 45088768,
"records": [
{
"name": "model.layers.11.mlp.gate_up_proj.q_weight",
"shape": [
22016,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 45088768,
"byteOffset": 0
}
],
"md5sum": "2cd319ee56313a3ea29c7bfc4dfa2ad3"
},
{
"dataPath": "params_shard_42.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.12.self_attn.qkv_proj.q_weight",
"shape": [
12288,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "9fdb9ea9168460346d1deafa5115a282"
},
{
"dataPath": "params_shard_43.bin",
"format": "raw-shard",
"nbytes": 32063488,
"records": [
{
"name": "model.layers.11.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 0
},
{
"name": "model.layers.11.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 1048576
},
{
"name": "model.layers.11.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 22544384,
"byteOffset": 6684672
},
{
"name": "model.layers.11.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 29229056
},
{
"name": "model.layers.11.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 32047104
},
{
"name": "model.layers.11.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 32055296
}
],
"md5sum": "4af071255a901797d8e8803f2771596d"
},
{
"dataPath": "params_shard_44.bin",
"format": "raw-shard",
"nbytes": 45088768,
"records": [
{
"name": "model.layers.12.mlp.gate_up_proj.q_weight",
"shape": [
22016,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 45088768,
"byteOffset": 0
}
],
"md5sum": "1e23819b13809c063c314faee8f945ac"
},
{
"dataPath": "params_shard_45.bin",
"format": "raw-shard",
"nbytes": 22544384,
"records": [
{
"name": "model.layers.12.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 22544384,
"byteOffset": 0
}
],
"md5sum": "6807ab8932573414e3fd161fe9ab91c7"
},
{
"dataPath": "params_shard_46.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.13.self_attn.qkv_proj.q_weight",
"shape": [
12288,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "31ef0402d240b00fc38c442fb07d3c9c"
},
{
"dataPath": "params_shard_47.bin",
"format": "raw-shard",
"nbytes": 32587776,
"records": [
{
"name": "model.layers.12.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 0
},
{
"name": "model.layers.12.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 3145728
},
{
"name": "model.layers.12.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 11534336
},
{
"name": "model.layers.12.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 12582912
},
{
"name": "model.layers.12.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 18219008
},
{
"name": "model.layers.12.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21037056
},
{
"name": "model.layers.12.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21045248
},
{
"name": "model.layers.13.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 21053440
},
{
"name": "model.layers.13.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 24199168
}
],
"md5sum": "c0eef17b98c90131d5b0628775bfbffa"
},
{
"dataPath": "params_shard_48.bin",
"format": "raw-shard",
"nbytes": 45088768,
"records": [
{
"name": "model.layers.13.mlp.gate_up_proj.q_weight",
"shape": [
22016,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 45088768,
"byteOffset": 0
}
],
"md5sum": "7233db81dba12add6ddd1ea9dfe9c3dd"
},
{
"dataPath": "params_shard_49.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.14.self_attn.qkv_proj.q_weight",
"shape": [
12288,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "02a22884484fa383e5cafd9c7dfea8f5"
},
{
"dataPath": "params_shard_50.bin",
"format": "raw-shard",
"nbytes": 32063488,
"records": [
{
"name": "model.layers.13.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 0
},
{
"name": "model.layers.13.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 1048576
},
{
"name": "model.layers.13.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 22544384,
"byteOffset": 6684672
},
{
"name": "model.layers.13.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 29229056
},
{
"name": "model.layers.13.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 32047104
},
{
"name": "model.layers.13.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 32055296
}
],
"md5sum": "7e0e19e0c2512dff82f2a8c442a16ec8"
},
{
"dataPath": "params_shard_51.bin",
"format": "raw-shard",
"nbytes": 45088768,
"records": [
{
"name": "model.layers.14.mlp.gate_up_proj.q_weight",
"shape": [
22016,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 45088768,
"byteOffset": 0
}
],
"md5sum": "1a5169035ab977aaf0e031f1e80dbf06"
},
{
"dataPath": "params_shard_52.bin",
"format": "raw-shard",
"nbytes": 22544384,
"records": [
{
"name": "model.layers.14.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 22544384,
"byteOffset": 0
}
],
"md5sum": "a523a61ca293169dad379555f513f77b"
},
{
"dataPath": "params_shard_53.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.15.self_attn.qkv_proj.q_weight",
"shape": [
12288,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "7f47a4a5ba0c5b1ffc169d4a0210d6e6"
},
{
"dataPath": "params_shard_54.bin",
"format": "raw-shard",
"nbytes": 32587776,
"records": [
{
"name": "model.layers.14.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 0
},
{
"name": "model.layers.14.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 3145728
},
{
"name": "model.layers.14.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 11534336
},
{
"name": "model.layers.14.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 12582912
},
{
"name": "model.layers.14.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 18219008
},
{
"name": "model.layers.14.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21037056
},
{
"name": "model.layers.14.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21045248
},
{
"name": "model.layers.15.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 21053440
},
{
"name": "model.layers.15.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 24199168
}
],
"md5sum": "e5046b82ae71b7ee0b3c13cd8ad87d59"
},
{
"dataPath": "params_shard_55.bin",
"format": "raw-shard",
"nbytes": 45088768,
"records": [
{
"name": "model.layers.15.mlp.gate_up_proj.q_weight",
"shape": [
22016,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 45088768,
"byteOffset": 0
}
],
"md5sum": "858f179d9f31284e20a148ea0cd8c754"
},
{
"dataPath": "params_shard_56.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.16.self_attn.qkv_proj.q_weight",
"shape": [
12288,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "ed50be593ce20d306d147e344640a81c"
},
{
"dataPath": "params_shard_57.bin",
"format": "raw-shard",
"nbytes": 32063488,
"records": [
{
"name": "model.layers.15.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 0
},
{
"name": "model.layers.15.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 1048576
},
{
"name": "model.layers.15.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 22544384,
"byteOffset": 6684672
},
{
"name": "model.layers.15.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 29229056
},
{
"name": "model.layers.15.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 32047104
},
{
"name": "model.layers.15.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 32055296
}
],
"md5sum": "12e022e015e09ec4c17cb20bd7c68b16"
},
{
"dataPath": "params_shard_58.bin",
"format": "raw-shard",
"nbytes": 45088768,
"records": [
{
"name": "model.layers.16.mlp.gate_up_proj.q_weight",
"shape": [
22016,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 45088768,
"byteOffset": 0
}
],
"md5sum": "de337359b182b6121fdc9801a084428e"
},
{
"dataPath": "params_shard_59.bin",
"format": "raw-shard",
"nbytes": 22544384,
"records": [
{
"name": "model.layers.16.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 22544384,
"byteOffset": 0
}
],
"md5sum": "a6d679ed3c77a771938b7162f0bb5dd5"
},
{
"dataPath": "params_shard_60.bin",
"format": "raw-shard",
"nbytes": 65536000,
"records": [
{
"name": "lm_head.q_weight",
"shape": [
32000,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 65536000,
"byteOffset": 0
}
],
"md5sum": "024e3785e7a04546cbb7709a95ac89b1"
},
{
"dataPath": "params_shard_61.bin",
"format": "raw-shard",
"nbytes": 29253632,
"records": [
{
"name": "model.layers.16.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 0
},
{
"name": "model.layers.16.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 3145728
},
{
"name": "model.layers.16.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 11534336
},
{
"name": "model.layers.16.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 12582912
},
{
"name": "model.layers.16.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 18219008
},
{
"name": "model.layers.16.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21037056
},
{
"name": "model.layers.16.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21045248
},
{
"name": "model.norm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21053440
},
{
"name": "lm_head.q_scale",
"shape": [
32000,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192000,
"byteOffset": 21061632
}
],
"md5sum": "e81c1bc7f90ff777240bee6be0140d49"
}
]
}