Hugging Face's logo

mlc-ai
/
CodeLlama-7b-Python-hf-q4f16_1-MLC

MLC-LLM
web-llm
Model card Files Community
CodeLlama-7b-Python-hf-q4f16_1-MLC / ndarray-cache.json
CharlieFRuan's picture
CharlieFRuan
Initial commit
6da7cc5 verified
raw
history blame
150 kB
{
"metadata": {
"ParamSize": 325,
"ParamBytes": 3790741504.0,
"BitsPerParam": 4.500454373872803
},
"records": [
{
"dataPath": "params_shard_0.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": "bfb87d014611dbe44a349c39fffb26c7"
},
{
"dataPath": "params_shard_1.bin",
"format": "raw-shard",
"nbytes": 30744576,
"records": [
{
"name": "lm_head.q_scale",
"shape": [
32000,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192000,
"byteOffset": 0
},
{
"name": "model.layers.23.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 8192000
},
{
"name": "model.layers.23.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 22544384,
"byteOffset": 8200192
}
],
"md5sum": "f126206451e9dad6437ea0c88b8a9a89"
},
{
"dataPath": "params_shard_2.bin",
"format": "raw-shard",
"nbytes": 45088768,
"records": [
{
"name": "model.layers.24.mlp.gate_up_proj.q_weight",
"shape": [
22016,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 45088768,
"byteOffset": 0
}
],
"md5sum": "554f3fd68ad377afdb3f87a2e166af67"
},
{
"dataPath": "params_shard_3.bin",
"format": "raw-shard",
"nbytes": 28196864,
"records": [
{
"name": "model.layers.23.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 0
},
{
"name": "model.layers.23.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 2818048
},
{
"name": "model.layers.24.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 2826240
},
{
"name": "model.layers.24.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 22544384,
"byteOffset": 2834432
},
{
"name": "model.layers.24.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 25378816
}
],
"md5sum": "d1e83b16c2804d0fb5f3d820124b920e"
},
{
"dataPath": "params_shard_4.bin",
"format": "raw-shard",
"nbytes": 30810112,
"records": [
{
"name": "model.layers.24.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 0
},
{
"name": "model.layers.24.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 5636096
},
{
"name": "model.layers.24.self_attn.qkv_proj.q_weight",
"shape": [
12288,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 5644288
}
],
"md5sum": "954a89a06190b4c07b90a6513f08f97b"
},
{
"dataPath": "params_shard_5.bin",
"format": "raw-shard",
"nbytes": 22544384,
"records": [
{
"name": "model.layers.25.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 22544384,
"byteOffset": 0
}
],
"md5sum": "252c59546ae7d452be554527b719b731"
},
{
"dataPath": "params_shard_6.bin",
"format": "raw-shard",
"nbytes": 45088768,
"records": [
{
"name": "model.layers.25.mlp.gate_up_proj.q_weight",
"shape": [
22016,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 45088768,
"byteOffset": 0
}
],
"md5sum": "7a1e00427a846ba6000eed0612ae1c3f"
},
{
"dataPath": "params_shard_7.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.25.self_attn.qkv_proj.q_weight",
"shape": [
12288,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "c40aa820cd0b58a66538f6ead242af2a"
},
{
"dataPath": "params_shard_8.bin",
"format": "raw-shard",
"nbytes": 32587776,
"records": [
{
"name": "model.layers.24.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 0
},
{
"name": "model.layers.24.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 3145728
},
{
"name": "model.layers.24.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 11534336
},
{
"name": "model.layers.25.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 12582912
},
{
"name": "model.layers.25.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 12591104
},
{
"name": "model.layers.25.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 15409152
},
{
"name": "model.layers.25.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21045248
},
{
"name": "model.layers.25.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 21053440
},
{
"name": "model.layers.25.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 24199168
}
],
"md5sum": "aa1eeb80d3d507b9328fb82ca2ec53fb"
},
{
"dataPath": "params_shard_9.bin",
"format": "raw-shard",
"nbytes": 45088768,
"records": [
{
"name": "model.layers.26.mlp.gate_up_proj.q_weight",
"shape": [
22016,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 45088768,
"byteOffset": 0
}
],
"md5sum": "82090581209817f673ae527edd66951d"
},
{
"dataPath": "params_shard_10.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.26.self_attn.qkv_proj.q_weight",
"shape": [
12288,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "7c921633a4d2fe5cacf7d73ec5f5e612"
},
{
"dataPath": "params_shard_11.bin",
"format": "raw-shard",
"nbytes": 32063488,
"records": [
{
"name": "model.layers.25.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 0
},
{
"name": "model.layers.26.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 1048576
},
{
"name": "model.layers.26.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 22544384,
"byteOffset": 1056768
},
{
"name": "model.layers.26.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 23601152
},
{
"name": "model.layers.26.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 26419200
},
{
"name": "model.layers.26.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 32055296
}
],
"md5sum": "5f32a8f67f9e5f9dcc4b3382ce208713"
},
{
"dataPath": "params_shard_12.bin",
"format": "raw-shard",
"nbytes": 22544384,
"records": [
{
"name": "model.layers.27.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 22544384,
"byteOffset": 0
}
],
"md5sum": "75a6a8f8b024edd5168d77b1550a7c14"
},
{
"dataPath": "params_shard_13.bin",
"format": "raw-shard",
"nbytes": 45088768,
"records": [
{
"name": "model.layers.27.mlp.gate_up_proj.q_weight",
"shape": [
22016,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 45088768,
"byteOffset": 0
}
],
"md5sum": "e6bef57fce9dd9da9b6ce33c2f39d789"
},
{
"dataPath": "params_shard_14.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.27.self_attn.qkv_proj.q_weight",
"shape": [
12288,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "3e08c4b04dc8e2e03a26ecc1e3490af4"
},
{
"dataPath": "params_shard_15.bin",
"format": "raw-shard",
"nbytes": 32587776,
"records": [
{
"name": "model.layers.26.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 0
},
{
"name": "model.layers.26.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 3145728
},
{
"name": "model.layers.26.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 11534336
},
{
"name": "model.layers.27.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 12582912
},
{
"name": "model.layers.27.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 12591104
},
{
"name": "model.layers.27.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 15409152
},
{
"name": "model.layers.27.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21045248
},
{
"name": "model.layers.27.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 21053440
},
{
"name": "model.layers.27.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 24199168
}
],
"md5sum": "aed302b4359cb7521644c694b5ca0374"
},
{
"dataPath": "params_shard_16.bin",
"format": "raw-shard",
"nbytes": 45088768,
"records": [
{
"name": "model.layers.28.mlp.gate_up_proj.q_weight",
"shape": [
22016,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 45088768,
"byteOffset": 0
}
],
"md5sum": "d78693718d49a4e1409ce2a00fa91f3f"
},
{
"dataPath": "params_shard_17.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.28.self_attn.qkv_proj.q_weight",
"shape": [
12288,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "0da9d3eddaab4d6d845762c129319ffd"
},
{
"dataPath": "params_shard_18.bin",
"format": "raw-shard",
"nbytes": 32063488,
"records": [
{
"name": "model.layers.27.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 0
},
{
"name": "model.layers.28.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 1048576
},
{
"name": "model.layers.28.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 22544384,
"byteOffset": 1056768
},
{
"name": "model.layers.28.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 23601152
},
{
"name": "model.layers.28.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 26419200
},
{
"name": "model.layers.28.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 32055296
}
],
"md5sum": "3d1ee00c7d0ab78d6097966e54e58f25"
},
{
"dataPath": "params_shard_19.bin",
"format": "raw-shard",
"nbytes": 22544384,
"records": [
{
"name": "model.layers.29.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 22544384,
"byteOffset": 0
}
],
"md5sum": "da4d06af248ef5a43454c409a3f9ba42"
},
{
"dataPath": "params_shard_20.bin",
"format": "raw-shard",
"nbytes": 45088768,
"records": [
{
"name": "model.layers.29.mlp.gate_up_proj.q_weight",
"shape": [
22016,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 45088768,
"byteOffset": 0
}
],
"md5sum": "91c36afecc335e5ecf88e3a4a4bee227"
},
{
"dataPath": "params_shard_21.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.29.self_attn.qkv_proj.q_weight",
"shape": [
12288,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "a5e8eba5beb2a3ab8c265b145a342769"
},
{
"dataPath": "params_shard_22.bin",
"format": "raw-shard",
"nbytes": 32587776,
"records": [
{
"name": "model.layers.28.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 0
},
{
"name": "model.layers.28.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 3145728
},
{
"name": "model.layers.28.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 11534336
},
{
"name": "model.layers.29.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 12582912
},
{
"name": "model.layers.29.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 12591104
},
{
"name": "model.layers.29.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 15409152
},
{
"name": "model.layers.29.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21045248
},
{
"name": "model.layers.29.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 21053440
},
{
"name": "model.layers.29.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 24199168
}
],
"md5sum": "bf1c624e9c1fa2290810b20d5f80f481"
},
{
"dataPath": "params_shard_23.bin",
"format": "raw-shard",
"nbytes": 45088768,
"records": [
{
"name": "model.layers.30.mlp.gate_up_proj.q_weight",
"shape": [
22016,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 45088768,
"byteOffset": 0
}
],
"md5sum": "12ab6e2e6e90dc5e2efe84e58686ec2a"
},
{
"dataPath": "params_shard_24.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.30.self_attn.qkv_proj.q_weight",
"shape": [
12288,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "a5209115b3f63d1dcaa2c5b5e053cdbe"
},
{
"dataPath": "params_shard_25.bin",
"format": "raw-shard",
"nbytes": 32063488,
"records": [
{
"name": "model.layers.29.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 0
},
{
"name": "model.layers.30.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 1048576
},
{
"name": "model.layers.30.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 22544384,
"byteOffset": 1056768
},
{
"name": "model.layers.30.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 23601152
},
{
"name": "model.layers.30.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 26419200
},
{
"name": "model.layers.30.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 32055296
}
],
"md5sum": "6340c99885e63bab896ca56776cf41bf"
},
{
"dataPath": "params_shard_26.bin",
"format": "raw-shard",
"nbytes": 22544384,
"records": [
{
"name": "model.layers.31.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 22544384,
"byteOffset": 0
}
],
"md5sum": "8dff2a72c81eab63b44e03b13567022a"
},
{
"dataPath": "params_shard_27.bin",
"format": "raw-shard",
"nbytes": 45088768,
"records": [
{
"name": "model.layers.31.mlp.gate_up_proj.q_weight",
"shape": [
22016,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 45088768,
"byteOffset": 0
}
],
"md5sum": "f7f490556e0e213bf1b2e5675a71d38b"
},
{
"dataPath": "params_shard_28.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.31.self_attn.qkv_proj.q_weight",
"shape": [
12288,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "2f83cb984c059ed89bf011efa3cf3e7b"
},
{
"dataPath": "params_shard_29.bin",
"format": "raw-shard",
"nbytes": 32587776,
"records": [
{
"name": "model.layers.30.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 0
},
{
"name": "model.layers.30.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 3145728
},
{
"name": "model.layers.30.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 11534336
},
{
"name": "model.layers.31.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 12582912
},
{
"name": "model.layers.31.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 12591104
},
{
"name": "model.layers.31.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 15409152
},
{
"name": "model.layers.31.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21045248
},
{
"name": "model.layers.31.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 21053440
},
{
"name": "model.layers.31.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 24199168
}
],
"md5sum": "61ab49f4cd5b611e344ad34765394faf"
},
{
"dataPath": "params_shard_30.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": "e9086f23fe7efc4a40c6595f8a8fbf4d"
},
{
"dataPath": "params_shard_31.bin",
"format": "raw-shard",
"nbytes": 31801344,
"records": [
{
"name": "model.layers.31.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 0
},
{
"name": "model.norm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 1048576
},
{
"name": "model.embed_tokens.q_scale",
"shape": [
32000,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192000,
"byteOffset": 1056768
},
{
"name": "model.layers.0.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 9248768
},
{
"name": "model.layers.0.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 22544384,
"byteOffset": 9256960
}
],
"md5sum": "30ba1b3a88ae5c755f21bbcf4c559195"
},
{
"dataPath": "params_shard_32.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": "7f69feb4121fa2f371c358cdce0cd0c4"
},
{
"dataPath": "params_shard_33.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.0.self_attn.qkv_proj.q_weight",
"shape": [
12288,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "cfb35726ec0d7b42ab3f1479784da1c4"
},
{
"dataPath": "params_shard_34.bin",
"format": "raw-shard",
"nbytes": 22544384,
"records": [
{
"name": "model.layers.1.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 22544384,
"byteOffset": 0
}
],
"md5sum": "5bc6d1c4c76baeb1f5a41770930a0537"
},
{
"dataPath": "params_shard_35.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": "bada632b4cffbce3be3958f2b0e254ee"
},
{
"dataPath": "params_shard_36.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": "f33ba9729886ea42e9754209afe16de2"
},
{
"dataPath": "params_shard_37.bin",
"format": "raw-shard",
"nbytes": 32661504,
"records": [
{
"name": "model.layers.0.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 0
},
{
"name": "model.layers.0.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 2818048
},
{
"name": "model.layers.0.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 8454144
},
{
"name": "model.layers.0.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 8462336
},
{
"name": "model.layers.0.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 11608064
},
{
"name": "model.layers.0.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 19996672
},
{
"name": "model.layers.1.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21045248
},
{
"name": "model.layers.1.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 21053440
},
{
"name": "model.layers.1.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 23871488
},
{
"name": "model.layers.1.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 29507584
},
{
"name": "model.layers.1.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 29515776
}
],
"md5sum": "63b083d3802bd73ff1ed51883b5e7264"
},
{
"dataPath": "params_shard_38.bin",
"format": "raw-shard",
"nbytes": 31989760,
"records": [
{
"name": "model.layers.1.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 0
},
{
"name": "model.layers.1.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 8388608
},
{
"name": "model.layers.10.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 9437184
},
{
"name": "model.layers.10.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 22544384,
"byteOffset": 9445376
}
],
"md5sum": "6728c8a85b27b2e730db69679c2c0249"
},
{
"dataPath": "params_shard_39.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": "cc68267a35d3cb3b1b791318457041d3"
},
{
"dataPath": "params_shard_40.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": "19d6bda211d92aad7459cdc77ec44576"
},
{
"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": "dd761a17ba6b23b43288aa918e536b2c"
},
{
"dataPath": "params_shard_42.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": "8528aa2edd06357a4b59cd983b7fd41d"
},
{
"dataPath": "params_shard_43.bin",
"format": "raw-shard",
"nbytes": 29827072,
"records": [
{
"name": "model.layers.10.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 0
},
{
"name": "model.layers.10.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 2818048
},
{
"name": "model.layers.10.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 8454144
},
{
"name": "model.layers.10.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 8462336
},
{
"name": "model.layers.10.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 11608064
},
{
"name": "model.layers.10.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 19996672
},
{
"name": "model.layers.11.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 21045248
},
{
"name": "model.layers.11.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 26681344
}
],
"md5sum": "2f7ccdd3b0b39aba1a1afb86b26e0987"
},
{
"dataPath": "params_shard_44.bin",
"format": "raw-shard",
"nbytes": 31989760,
"records": [
{
"name": "model.layers.11.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 0
},
{
"name": "model.layers.11.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 8388608
},
{
"name": "model.layers.2.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 9437184
},
{
"name": "model.layers.2.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 22544384,
"byteOffset": 9445376
}
],
"md5sum": "e34b74ce25167892d1b9c1daa32f5b58"
},
{
"dataPath": "params_shard_45.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": "8225a051e4cb8b02cdea7024c62116cf"
},
{
"dataPath": "params_shard_46.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": "f43cc29f196985e7fb70f7cb435b4b58"
},
{
"dataPath": "params_shard_47.bin",
"format": "raw-shard",
"nbytes": 22544384,
"records": [
{
"name": "model.layers.3.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 22544384,
"byteOffset": 0
}
],
"md5sum": "5107a238b1ccbc6d08ae5277c26b07b5"
},
{
"dataPath": "params_shard_48.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": "c73b79062a7d63ae4141e955510d0f6a"
},
{
"dataPath": "params_shard_49.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": "68be1b5f3fe8091459fcd679a9b100a7"
},
{
"dataPath": "params_shard_50.bin",
"format": "raw-shard",
"nbytes": 32661504,
"records": [
{
"name": "model.layers.2.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 0
},
{
"name": "model.layers.2.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 2818048
},
{
"name": "model.layers.2.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 8454144
},
{
"name": "model.layers.2.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 8462336
},
{
"name": "model.layers.2.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 11608064
},
{
"name": "model.layers.2.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 19996672
},
{
"name": "model.layers.3.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21045248
},
{
"name": "model.layers.3.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 21053440
},
{
"name": "model.layers.3.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 23871488
},
{
"name": "model.layers.3.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 29507584
},
{
"name": "model.layers.3.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 29515776
}
],
"md5sum": "f3c9dcab949fcda2074f2e9013ef42c8"
},
{
"dataPath": "params_shard_51.bin",
"format": "raw-shard",
"nbytes": 31989760,
"records": [
{
"name": "model.layers.3.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 0
},
{
"name": "model.layers.3.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 8388608
},
{
"name": "model.layers.4.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 9437184
},
{
"name": "model.layers.4.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 22544384,
"byteOffset": 9445376
}
],
"md5sum": "6cb77611aa69190d3b9808f822e65813"
},
{
"dataPath": "params_shard_52.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": "6fbb8dc308e4c65413e7c680e537bdcc"
},
{
"dataPath": "params_shard_53.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": "5911acc5aaeeef3b1da43adb52ec1b11"
},
{
"dataPath": "params_shard_54.bin",
"format": "raw-shard",
"nbytes": 22544384,
"records": [
{
"name": "model.layers.5.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 22544384,
"byteOffset": 0
}
],
"md5sum": "c6b83bafb7aabc8669ee51984569c396"
},
{
"dataPath": "params_shard_55.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": "0675a85da804e0a7775441f82dae35dd"
},
{
"dataPath": "params_shard_56.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": "0e2bc1af1b9f5824668ac3c2d5d13761"
},
{
"dataPath": "params_shard_57.bin",
"format": "raw-shard",
"nbytes": 32661504,
"records": [
{
"name": "model.layers.4.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 0
},
{
"name": "model.layers.4.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 2818048
},
{
"name": "model.layers.4.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 8454144
},
{
"name": "model.layers.4.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 8462336
},
{
"name": "model.layers.4.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 11608064
},
{
"name": "model.layers.4.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 19996672
},
{
"name": "model.layers.5.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21045248
},
{
"name": "model.layers.5.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 21053440
},
{
"name": "model.layers.5.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 23871488
},
{
"name": "model.layers.5.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 29507584
},
{
"name": "model.layers.5.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 29515776
}
],
"md5sum": "22830a35344cd2bea92b431e93dc5a6d"
},
{
"dataPath": "params_shard_58.bin",
"format": "raw-shard",
"nbytes": 31989760,
"records": [
{
"name": "model.layers.5.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 0
},
{
"name": "model.layers.5.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 8388608
},
{
"name": "model.layers.6.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 9437184
},
{
"name": "model.layers.6.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 22544384,
"byteOffset": 9445376
}
],
"md5sum": "439c54e8bf994d3d55eedddeac29fb13"
},
{
"dataPath": "params_shard_59.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": "23ef8ea533a3c5eb3bc9fca30ab7f427"
},
{
"dataPath": "params_shard_60.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": "671f591c594e66864a06e590f5d3aa1c"
},
{
"dataPath": "params_shard_61.bin",
"format": "raw-shard",
"nbytes": 22544384,
"records": [
{
"name": "model.layers.7.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 22544384,
"byteOffset": 0
}
],
"md5sum": "9cf50bcb3bdad6a7177906f1467e1490"
},
{
"dataPath": "params_shard_62.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": "ff09063c7a0a6a28075f76cead333018"
},
{
"dataPath": "params_shard_63.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": "5bdfdc75dca0fbd2b8356a5432a7296a"
},
{
"dataPath": "params_shard_64.bin",
"format": "raw-shard",
"nbytes": 32661504,
"records": [
{
"name": "model.layers.6.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 0
},
{
"name": "model.layers.6.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 2818048
},
{
"name": "model.layers.6.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 8454144
},
{
"name": "model.layers.6.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 8462336
},
{
"name": "model.layers.6.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 11608064
},
{
"name": "model.layers.6.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 19996672
},
{
"name": "model.layers.7.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21045248
},
{
"name": "model.layers.7.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 21053440
},
{
"name": "model.layers.7.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 23871488
},
{
"name": "model.layers.7.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 29507584
},
{
"name": "model.layers.7.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 29515776
}
],
"md5sum": "f5ed72b73b2687eb60c6a41adc057111"
},
{
"dataPath": "params_shard_65.bin",
"format": "raw-shard",
"nbytes": 31989760,
"records": [
{
"name": "model.layers.7.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 0
},
{
"name": "model.layers.7.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 8388608
},
{
"name": "model.layers.8.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 9437184
},
{
"name": "model.layers.8.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 22544384,
"byteOffset": 9445376
}
],
"md5sum": "5be2341cb0474e6e6cc1d0f2242172e0"
},
{
"dataPath": "params_shard_66.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": "2082ed75bf11476ad85e942028859e6b"
},
{
"dataPath": "params_shard_67.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": "aecb45d5b538fdfbc56b16c2b4f3528e"
},
{
"dataPath": "params_shard_68.bin",
"format": "raw-shard",
"nbytes": 22544384,
"records": [
{
"name": "model.layers.9.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 22544384,
"byteOffset": 0
}
],
"md5sum": "afc9e31d26a8f798d44f9291c33aafb4"
},
{
"dataPath": "params_shard_69.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": "3bd96e043f993533d29f1303c2a891e4"
},
{
"dataPath": "params_shard_70.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": "daedfa7a21fabb38841a7f3524ca2cf2"
},
{
"dataPath": "params_shard_71.bin",
"format": "raw-shard",
"nbytes": 32661504,
"records": [
{
"name": "model.layers.8.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 0
},
{
"name": "model.layers.8.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 2818048
},
{
"name": "model.layers.8.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 8454144
},
{
"name": "model.layers.8.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 8462336
},
{
"name": "model.layers.8.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 11608064
},
{
"name": "model.layers.8.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 19996672
},
{
"name": "model.layers.9.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21045248
},
{
"name": "model.layers.9.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 21053440
},
{
"name": "model.layers.9.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 23871488
},
{
"name": "model.layers.9.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 29507584
},
{
"name": "model.layers.9.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 29515776
}
],
"md5sum": "9c896e52ee391c4f57317666a82b6504"
},
{
"dataPath": "params_shard_72.bin",
"format": "raw-shard",
"nbytes": 31989760,
"records": [
{
"name": "model.layers.9.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 0
},
{
"name": "model.layers.9.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 8388608
},
{
"name": "model.layers.11.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 9437184
},
{
"name": "model.layers.11.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 22544384,
"byteOffset": 9445376
}
],
"md5sum": "54068f5d29003a3320640bd9ed35155c"
},
{
"dataPath": "params_shard_73.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": "3066339397cefec487593002fc4e233a"
},
{
"dataPath": "params_shard_74.bin",
"format": "raw-shard",
"nbytes": 28196864,
"records": [
{
"name": "model.layers.11.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 0
},
{
"name": "model.layers.11.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 2818048
},
{
"name": "model.layers.12.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 2826240
},
{
"name": "model.layers.12.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 22544384,
"byteOffset": 2834432
},
{
"name": "model.layers.12.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 25378816
}
],
"md5sum": "c9843e7aca21bcfc82030606bbc03bcb"
},
{
"dataPath": "params_shard_75.bin",
"format": "raw-shard",
"nbytes": 30810112,
"records": [
{
"name": "model.layers.12.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 0
},
{
"name": "model.layers.12.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 5636096
},
{
"name": "model.layers.12.self_attn.qkv_proj.q_weight",
"shape": [
12288,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 5644288
}
],
"md5sum": "6f773c8b4902ab978e55c430b6b4c119"
},
{
"dataPath": "params_shard_76.bin",
"format": "raw-shard",
"nbytes": 22544384,
"records": [
{
"name": "model.layers.13.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 22544384,
"byteOffset": 0
}
],
"md5sum": "06313a4f4efdfdaecf09efc70967b8c8"
},
{
"dataPath": "params_shard_77.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": "7076394667f9ff83aedff0666dfe3c2b"
},
{
"dataPath": "params_shard_78.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": "b70f832c9293c79b3737fb44d91e1d09"
},
{
"dataPath": "params_shard_79.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.13.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 12582912
},
{
"name": "model.layers.13.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 12591104
},
{
"name": "model.layers.13.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 15409152
},
{
"name": "model.layers.13.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": "87124c1475e0b3986535389f50b7e9e6"
},
{
"dataPath": "params_shard_80.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": "c17a94aba060b27b0f3905709d2cd96d"
},
{
"dataPath": "params_shard_81.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": "5b0e4361d4c3373c47fe07046df5fe6d"
},
{
"dataPath": "params_shard_82.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.14.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 1048576
},
{
"name": "model.layers.14.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 22544384,
"byteOffset": 1056768
},
{
"name": "model.layers.14.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 23601152
},
{
"name": "model.layers.14.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 26419200
},
{
"name": "model.layers.14.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 32055296
}
],
"md5sum": "75e1943f2e612c09a3e991719f33ea4f"
},
{
"dataPath": "params_shard_83.bin",
"format": "raw-shard",
"nbytes": 22544384,
"records": [
{
"name": "model.layers.15.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 22544384,
"byteOffset": 0
}
],
"md5sum": "d3c64d8f700de7b2b4f0f728a2cecc0d"
},
{
"dataPath": "params_shard_84.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": "c5a1bf5476fd8e86792a92a307b7efba"
},
{
"dataPath": "params_shard_85.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": "5f7b96694f03a8be58c8e244d9682185"
},
{
"dataPath": "params_shard_86.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.15.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 12582912
},
{
"name": "model.layers.15.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 12591104
},
{
"name": "model.layers.15.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 15409152
},
{
"name": "model.layers.15.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": "bafc0197c5a261cdcdcee751918159d3"
},
{
"dataPath": "params_shard_87.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": "f408d44de3cc562f7253103cefc8ef00"
},
{
"dataPath": "params_shard_88.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": "e520f8c3d851336325c9055209262980"
},
{
"dataPath": "params_shard_89.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.16.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 1048576
},
{
"name": "model.layers.16.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 22544384,
"byteOffset": 1056768
},
{
"name": "model.layers.16.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 23601152
},
{
"name": "model.layers.16.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 26419200
},
{
"name": "model.layers.16.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 32055296
}
],
"md5sum": "27a7982eeea7957bb342b4616eb28787"
},
{
"dataPath": "params_shard_90.bin",
"format": "raw-shard",
"nbytes": 22544384,
"records": [
{
"name": "model.layers.17.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 22544384,
"byteOffset": 0
}
],
"md5sum": "681dcb2b15361e567c559ce8acb83293"
},
{
"dataPath": "params_shard_91.bin",
"format": "raw-shard",
"nbytes": 45088768,
"records": [
{
"name": "model.layers.17.mlp.gate_up_proj.q_weight",
"shape": [
22016,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 45088768,
"byteOffset": 0
}
],
"md5sum": "5af773051480cd96c955e57a465277be"
},
{
"dataPath": "params_shard_92.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.17.self_attn.qkv_proj.q_weight",
"shape": [
12288,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "cff9fc9e4c92e8371294da6e257bee29"
},
{
"dataPath": "params_shard_93.bin",
"format": "raw-shard",
"nbytes": 32587776,
"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.17.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 12582912
},
{
"name": "model.layers.17.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 12591104
},
{
"name": "model.layers.17.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 15409152
},
{
"name": "model.layers.17.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21045248
},
{
"name": "model.layers.17.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 21053440
},
{
"name": "model.layers.17.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 24199168
}
],
"md5sum": "4c45d2f18167b916b516a3153124d3e9"
},
{
"dataPath": "params_shard_94.bin",
"format": "raw-shard",
"nbytes": 45088768,
"records": [
{
"name": "model.layers.18.mlp.gate_up_proj.q_weight",
"shape": [
22016,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 45088768,
"byteOffset": 0
}
],
"md5sum": "cfd80ca81750124ff06a8ae8bdd3b9bc"
},
{
"dataPath": "params_shard_95.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.18.self_attn.qkv_proj.q_weight",
"shape": [
12288,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "1ff83935e5ca71fbc3c5e36e288f2ac0"
},
{
"dataPath": "params_shard_96.bin",
"format": "raw-shard",
"nbytes": 32063488,
"records": [
{
"name": "model.layers.17.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 0
},
{
"name": "model.layers.18.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 1048576
},
{
"name": "model.layers.18.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 22544384,
"byteOffset": 1056768
},
{
"name": "model.layers.18.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 23601152
},
{
"name": "model.layers.18.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 26419200
},
{
"name": "model.layers.18.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 32055296
}
],
"md5sum": "b2ba3dee87b29e8d2f42fec1f4581f1e"
},
{
"dataPath": "params_shard_97.bin",
"format": "raw-shard",
"nbytes": 22544384,
"records": [
{
"name": "model.layers.19.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 22544384,
"byteOffset": 0
}
],
"md5sum": "975dde8f263dd5aaa2003201983809a1"
},
{
"dataPath": "params_shard_98.bin",
"format": "raw-shard",
"nbytes": 45088768,
"records": [
{
"name": "model.layers.19.mlp.gate_up_proj.q_weight",
"shape": [
22016,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 45088768,
"byteOffset": 0
}
],
"md5sum": "485ca015a4112e8da33bb06e93caf081"
},
{
"dataPath": "params_shard_99.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.19.self_attn.qkv_proj.q_weight",
"shape": [
12288,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "42ab65ef3b3dff9a01913b6351d9e248"
},
{
"dataPath": "params_shard_100.bin",
"format": "raw-shard",
"nbytes": 32587776,
"records": [
{
"name": "model.layers.18.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 0
},
{
"name": "model.layers.18.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 3145728
},
{
"name": "model.layers.18.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 11534336
},
{
"name": "model.layers.19.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 12582912
},
{
"name": "model.layers.19.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 12591104
},
{
"name": "model.layers.19.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 15409152
},
{
"name": "model.layers.19.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21045248
},
{
"name": "model.layers.19.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 21053440
},
{
"name": "model.layers.19.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 24199168
}
],
"md5sum": "3dc740578c75abad072d5f0f8094829f"
},
{
"dataPath": "params_shard_101.bin",
"format": "raw-shard",
"nbytes": 45088768,
"records": [
{
"name": "model.layers.20.mlp.gate_up_proj.q_weight",
"shape": [
22016,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 45088768,
"byteOffset": 0
}
],
"md5sum": "e9cb5892193ef302eb9eccce4d65a568"
},
{
"dataPath": "params_shard_102.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.20.self_attn.qkv_proj.q_weight",
"shape": [
12288,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "bda45183f12512ef1e0b7efccbdfd2b1"
},
{
"dataPath": "params_shard_103.bin",
"format": "raw-shard",
"nbytes": 32063488,
"records": [
{
"name": "model.layers.19.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 0
},
{
"name": "model.layers.20.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 1048576
},
{
"name": "model.layers.20.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 22544384,
"byteOffset": 1056768
},
{
"name": "model.layers.20.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 23601152
},
{
"name": "model.layers.20.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 26419200
},
{
"name": "model.layers.20.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 32055296
}
],
"md5sum": "4c177526de243331d81c1d296e279c08"
},
{
"dataPath": "params_shard_104.bin",
"format": "raw-shard",
"nbytes": 22544384,
"records": [
{
"name": "model.layers.21.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 22544384,
"byteOffset": 0
}
],
"md5sum": "9a45da8d468fc983fb2be37694c0db30"
},
{
"dataPath": "params_shard_105.bin",
"format": "raw-shard",
"nbytes": 45088768,
"records": [
{
"name": "model.layers.21.mlp.gate_up_proj.q_weight",
"shape": [
22016,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 45088768,
"byteOffset": 0
}
],
"md5sum": "7dbee2146d869784c2f68107e69507aa"
},
{
"dataPath": "params_shard_106.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.21.self_attn.qkv_proj.q_weight",
"shape": [
12288,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "8d4d796993bef5511e996e14643671e4"
},
{
"dataPath": "params_shard_107.bin",
"format": "raw-shard",
"nbytes": 32587776,
"records": [
{
"name": "model.layers.20.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 0
},
{
"name": "model.layers.20.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 3145728
},
{
"name": "model.layers.20.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 11534336
},
{
"name": "model.layers.21.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 12582912
},
{
"name": "model.layers.21.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 12591104
},
{
"name": "model.layers.21.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 15409152
},
{
"name": "model.layers.21.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21045248
},
{
"name": "model.layers.21.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 21053440
},
{
"name": "model.layers.21.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 24199168
}
],
"md5sum": "1af82c727ab2ff4dd4a7dd24e16eb347"
},
{
"dataPath": "params_shard_108.bin",
"format": "raw-shard",
"nbytes": 45088768,
"records": [
{
"name": "model.layers.22.mlp.gate_up_proj.q_weight",
"shape": [
22016,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 45088768,
"byteOffset": 0
}
],
"md5sum": "790ffe2588c6df489dc7a0009cdf9404"
},
{
"dataPath": "params_shard_109.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.22.self_attn.qkv_proj.q_weight",
"shape": [
12288,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "8d7df04ddcb884062e3d806e83bf42e7"
},
{
"dataPath": "params_shard_110.bin",
"format": "raw-shard",
"nbytes": 32063488,
"records": [
{
"name": "model.layers.21.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 0
},
{
"name": "model.layers.22.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 1048576
},
{
"name": "model.layers.22.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 22544384,
"byteOffset": 1056768
},
{
"name": "model.layers.22.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 23601152
},
{
"name": "model.layers.22.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 26419200
},
{
"name": "model.layers.22.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 32055296
}
],
"md5sum": "a10acbfc764596a1c1324d283cf10128"
},
{
"dataPath": "params_shard_111.bin",
"format": "raw-shard",
"nbytes": 45088768,
"records": [
{
"name": "model.layers.23.mlp.gate_up_proj.q_weight",
"shape": [
22016,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 45088768,
"byteOffset": 0
}
],
"md5sum": "a5b1ecc2fd9b825d88b659d5c079ce1c"
},
{
"dataPath": "params_shard_112.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.23.self_attn.qkv_proj.q_weight",
"shape": [
12288,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "0c38840ca48ad6bc70915a517dd14c48"
},
{
"dataPath": "params_shard_113.bin",
"format": "raw-shard",
"nbytes": 30801920,
"records": [
{
"name": "model.layers.22.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 0
},
{
"name": "model.layers.22.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 3145728
},
{
"name": "model.layers.22.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 11534336
},
{
"name": "model.layers.23.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 12582912
},
{
"name": "model.layers.23.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 18219008
},
{
"name": "model.layers.23.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 21364736
},
{
"name": "model.layers.23.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 29753344
}
],
"md5sum": "a85aba296926db76be1cf91201761904"
}
]
}