Hugging Face's logo

mlc-ai
/
gorilla-openfunctions-v1-q4f16_1-MLC

MLC-LLM
web-llm
Model card Files Community
gorilla-openfunctions-v1-q4f16_1-MLC / ndarray-cache.json
riczhou's picture
riczhou
Upload folder using huggingface_hub
e0d2a9d verified
raw
history blame contribute delete
No virus
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": "9334601bbfe318357a96e411f8167de6"
},
{
"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.24.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 8192000
},
{
"name": "model.layers.24.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 22544384,
"byteOffset": 8200192
}
],
"md5sum": "6184d477c319444d58ee1e76ea8d6689"
},
{
"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": "1f28efccbcc24875742172c0619f4671"
},
{
"dataPath": "params_shard_3.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.24.self_attn.qkv_proj.q_weight",
"shape": [
12288,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "000128bc3bfa37365b7ffebe37b290e6"
},
{
"dataPath": "params_shard_4.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": "86446de85a791c6a5652f095414f40e5"
},
{
"dataPath": "params_shard_5.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": "3cd8ac1542fe618b7afba570c40e19fd"
},
{
"dataPath": "params_shard_6.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": "7e57b961f3168b833802afe7b7b67824"
},
{
"dataPath": "params_shard_7.bin",
"format": "raw-shard",
"nbytes": 32661504,
"records": [
{
"name": "model.layers.24.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 0
},
{
"name": "model.layers.24.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 2818048
},
{
"name": "model.layers.24.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 8454144
},
{
"name": "model.layers.24.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 8462336
},
{
"name": "model.layers.24.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 11608064
},
{
"name": "model.layers.24.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 19996672
},
{
"name": "model.layers.25.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21045248
},
{
"name": "model.layers.25.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 21053440
},
{
"name": "model.layers.25.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 23871488
},
{
"name": "model.layers.25.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 29507584
},
{
"name": "model.layers.25.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 29515776
}
],
"md5sum": "802bc19f0371ed00ef5a79cc83efee29"
},
{
"dataPath": "params_shard_8.bin",
"format": "raw-shard",
"nbytes": 31989760,
"records": [
{
"name": "model.layers.25.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 0
},
{
"name": "model.layers.25.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 8388608
},
{
"name": "model.layers.26.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 9437184
},
{
"name": "model.layers.26.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 22544384,
"byteOffset": 9445376
}
],
"md5sum": "b7b2d02193ee5b313dbe945915a5cd8b"
},
{
"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": "63b6f0e9f5c560a2cdb19b1d535e648a"
},
{
"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": "0e3f084db2bd5ad2b7c42540e4b86552"
},
{
"dataPath": "params_shard_11.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": "6c8979f45e5e6dd2f582ebb3f0dff016"
},
{
"dataPath": "params_shard_12.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": "92ef7bae0072e5df7317efb736a6090f"
},
{
"dataPath": "params_shard_13.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": "489ee1d6e0c1788dc10fc9259512de31"
},
{
"dataPath": "params_shard_14.bin",
"format": "raw-shard",
"nbytes": 32661504,
"records": [
{
"name": "model.layers.26.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 0
},
{
"name": "model.layers.26.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 2818048
},
{
"name": "model.layers.26.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 8454144
},
{
"name": "model.layers.26.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 8462336
},
{
"name": "model.layers.26.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 11608064
},
{
"name": "model.layers.26.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 19996672
},
{
"name": "model.layers.27.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21045248
},
{
"name": "model.layers.27.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 21053440
},
{
"name": "model.layers.27.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 23871488
},
{
"name": "model.layers.27.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 29507584
},
{
"name": "model.layers.27.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 29515776
}
],
"md5sum": "6564200bd6ed4122c1b62d343b6e1c2f"
},
{
"dataPath": "params_shard_15.bin",
"format": "raw-shard",
"nbytes": 31989760,
"records": [
{
"name": "model.layers.27.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 0
},
{
"name": "model.layers.27.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 8388608
},
{
"name": "model.layers.28.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 9437184
},
{
"name": "model.layers.28.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 22544384,
"byteOffset": 9445376
}
],
"md5sum": "d2c598a81748bde6fedde526c20cd35a"
},
{
"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": "d8161d4eecf9abe29458d7d98ef185e6"
},
{
"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": "c489a656333aedda04ee1cdeff7e1d1f"
},
{
"dataPath": "params_shard_18.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": "eaef1188be8e6e77e315538bbb8f7968"
},
{
"dataPath": "params_shard_19.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": "a7f12df5fd0d7635ecf057a68fc54c3e"
},
{
"dataPath": "params_shard_20.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": "36bfb27ea03d7b62e22d3725083cfe4c"
},
{
"dataPath": "params_shard_21.bin",
"format": "raw-shard",
"nbytes": 32661504,
"records": [
{
"name": "model.layers.28.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 0
},
{
"name": "model.layers.28.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 2818048
},
{
"name": "model.layers.28.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 8454144
},
{
"name": "model.layers.28.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 8462336
},
{
"name": "model.layers.28.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 11608064
},
{
"name": "model.layers.28.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 19996672
},
{
"name": "model.layers.29.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21045248
},
{
"name": "model.layers.29.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 21053440
},
{
"name": "model.layers.29.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 23871488
},
{
"name": "model.layers.29.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 29507584
},
{
"name": "model.layers.29.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 29515776
}
],
"md5sum": "69bf460309f3a0683e678f5bd860d556"
},
{
"dataPath": "params_shard_22.bin",
"format": "raw-shard",
"nbytes": 31989760,
"records": [
{
"name": "model.layers.29.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 0
},
{
"name": "model.layers.29.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 8388608
},
{
"name": "model.layers.30.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 9437184
},
{
"name": "model.layers.30.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 22544384,
"byteOffset": 9445376
}
],
"md5sum": "a72f890debe5e03080eb47ee93818d69"
},
{
"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": "458ae4e929d7012782b5a9827d7f6eb1"
},
{
"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": "aacb25713384d412541bb71fb14178da"
},
{
"dataPath": "params_shard_25.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": "efa4b7d77696d57988fcc2e1ec37820b"
},
{
"dataPath": "params_shard_26.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": "ed4404846e02e86303b5e15901bd68c7"
},
{
"dataPath": "params_shard_27.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": "961fc75663fc89a583ab623b9b9aef9f"
},
{
"dataPath": "params_shard_28.bin",
"format": "raw-shard",
"nbytes": 32661504,
"records": [
{
"name": "model.layers.30.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 0
},
{
"name": "model.layers.30.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 2818048
},
{
"name": "model.layers.30.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 8454144
},
{
"name": "model.layers.30.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 8462336
},
{
"name": "model.layers.30.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 11608064
},
{
"name": "model.layers.30.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 19996672
},
{
"name": "model.layers.31.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21045248
},
{
"name": "model.layers.31.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 21053440
},
{
"name": "model.layers.31.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 23871488
},
{
"name": "model.layers.31.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 29507584
},
{
"name": "model.layers.31.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 29515776
}
],
"md5sum": "276fdad4af6380774f6225de3ffc6d3a"
},
{
"dataPath": "params_shard_29.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": "5ea2512e36535a07503da8d045feacd5"
},
{
"dataPath": "params_shard_30.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": "9a882f2f25127c9ff1b65e347a755789"
},
{
"dataPath": "params_shard_31.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": "f5f11569f47b25c9216d8992eab17c43"
},
{
"dataPath": "params_shard_32.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": "18483e65fc76e159b044065a88fd96cc"
},
{
"dataPath": "params_shard_33.bin",
"format": "raw-shard",
"nbytes": 29253632,
"records": [
{
"name": "model.layers.31.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 0
},
{
"name": "model.layers.31.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 8388608
},
{
"name": "model.norm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 9437184
},
{
"name": "model.embed_tokens.q_scale",
"shape": [
32000,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192000,
"byteOffset": 9445376
},
{
"name": "model.layers.0.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 17637376
},
{
"name": "model.layers.0.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 17645568
},
{
"name": "model.layers.0.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 20463616
},
{
"name": "model.layers.0.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 26099712
},
{
"name": "model.layers.0.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 26107904
}
],
"md5sum": "b03e24ca56eb24cd66ae46f85605d82d"
},
{
"dataPath": "params_shard_34.bin",
"format": "raw-shard",
"nbytes": 31989760,
"records": [
{
"name": "model.layers.0.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 0
},
{
"name": "model.layers.0.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 8388608
},
{
"name": "model.layers.1.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 9437184
},
{
"name": "model.layers.1.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 22544384,
"byteOffset": 9445376
}
],
"md5sum": "78f82095a0e5fcbb1e941c43748624ce"
},
{
"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": "e437ecfa0f2b6d5a1eba3de81c71cf12"
},
{
"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": "d670b06b564c15431f4a24178de4b193"
},
{
"dataPath": "params_shard_37.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": "9ff18e518ba56805da5a68ae0f534f29"
},
{
"dataPath": "params_shard_38.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": "b426e65da2c4acaddb54986e30e08ba0"
},
{
"dataPath": "params_shard_39.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": "fac877b8dfa0e50476afa598c30d14d5"
},
{
"dataPath": "params_shard_40.bin",
"format": "raw-shard",
"nbytes": 32661504,
"records": [
{
"name": "model.layers.1.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 0
},
{
"name": "model.layers.1.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 2818048
},
{
"name": "model.layers.1.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 8454144
},
{
"name": "model.layers.1.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 8462336
},
{
"name": "model.layers.1.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 11608064
},
{
"name": "model.layers.1.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 19996672
},
{
"name": "model.layers.10.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21045248
},
{
"name": "model.layers.10.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 21053440
},
{
"name": "model.layers.10.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 23871488
},
{
"name": "model.layers.10.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 29507584
},
{
"name": "model.layers.10.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 29515776
}
],
"md5sum": "b987fff0b005b38c69e0a5d2040f301e"
},
{
"dataPath": "params_shard_41.bin",
"format": "raw-shard",
"nbytes": 31989760,
"records": [
{
"name": "model.layers.10.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 0
},
{
"name": "model.layers.10.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": "2db6518e5f8fb570908673eae7537dd9"
},
{
"dataPath": "params_shard_42.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": "e0604966d78d132df4d7e21604308cb4"
},
{
"dataPath": "params_shard_43.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": "aba27098f8577adb1e2e1bac3afde24f"
},
{
"dataPath": "params_shard_44.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": "f9fab525a9bcacd0b6f5e6ae6be4bb1c"
},
{
"dataPath": "params_shard_45.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": "47bf61c24f9b8db3cf7df31fda28bdab"
},
{
"dataPath": "params_shard_46.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": "cb83fc17636f65475b00f982fce1d0c7"
},
{
"dataPath": "params_shard_47.bin",
"format": "raw-shard",
"nbytes": 32661504,
"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.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 2818048
},
{
"name": "model.layers.11.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 8454144
},
{
"name": "model.layers.11.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 8462336
},
{
"name": "model.layers.11.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 11608064
},
{
"name": "model.layers.11.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 19996672
},
{
"name": "model.layers.12.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21045248
},
{
"name": "model.layers.12.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 21053440
},
{
"name": "model.layers.12.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 23871488
},
{
"name": "model.layers.12.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 29507584
},
{
"name": "model.layers.12.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 29515776
}
],
"md5sum": "9ac58e912b65369e27ffaa4dd87ab2ac"
},
{
"dataPath": "params_shard_48.bin",
"format": "raw-shard",
"nbytes": 31989760,
"records": [
{
"name": "model.layers.12.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 0
},
{
"name": "model.layers.12.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 8388608
},
{
"name": "model.layers.13.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 9437184
},
{
"name": "model.layers.13.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 22544384,
"byteOffset": 9445376
}
],
"md5sum": "0c14d8a5b32bbd03ed7a01198e9cc0f1"
},
{
"dataPath": "params_shard_49.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": "02536b25a5e9f0429bf4eccfed5f2f32"
},
{
"dataPath": "params_shard_50.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": "ffbaad885f68fd30e656f2856020cb4d"
},
{
"dataPath": "params_shard_51.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": "38a8584bf0be1fe6dda67d7cfd29d86e"
},
{
"dataPath": "params_shard_52.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": "03dde7a0cec7c6e3be75353b9b5e7f02"
},
{
"dataPath": "params_shard_53.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": "b9d905a4cbfff912527573becd353372"
},
{
"dataPath": "params_shard_54.bin",
"format": "raw-shard",
"nbytes": 32661504,
"records": [
{
"name": "model.layers.13.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 0
},
{
"name": "model.layers.13.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 2818048
},
{
"name": "model.layers.13.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 8454144
},
{
"name": "model.layers.13.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 8462336
},
{
"name": "model.layers.13.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 11608064
},
{
"name": "model.layers.13.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 19996672
},
{
"name": "model.layers.14.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21045248
},
{
"name": "model.layers.14.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 21053440
},
{
"name": "model.layers.14.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 23871488
},
{
"name": "model.layers.14.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 29507584
},
{
"name": "model.layers.14.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 29515776
}
],
"md5sum": "ae5ab2809da2196de55465b8b5c39e62"
},
{
"dataPath": "params_shard_55.bin",
"format": "raw-shard",
"nbytes": 31989760,
"records": [
{
"name": "model.layers.14.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 0
},
{
"name": "model.layers.14.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 8388608
},
{
"name": "model.layers.15.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 9437184
},
{
"name": "model.layers.15.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 22544384,
"byteOffset": 9445376
}
],
"md5sum": "91072461c6b0184c6b4be86b14b2ded5"
},
{
"dataPath": "params_shard_56.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": "3a14a9c2348c89840e14f295e925554b"
},
{
"dataPath": "params_shard_57.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": "dbf7e46747bab0f138befd6da72fb587"
},
{
"dataPath": "params_shard_58.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": "527f650c28a653726e31ea45ced26a67"
},
{
"dataPath": "params_shard_59.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": "b5c7a0b31c4158e69d824d00bf2c970f"
},
{
"dataPath": "params_shard_60.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": "9efdd4325376710f3ea20cb28616ca0d"
},
{
"dataPath": "params_shard_61.bin",
"format": "raw-shard",
"nbytes": 32661504,
"records": [
{
"name": "model.layers.15.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 0
},
{
"name": "model.layers.15.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 2818048
},
{
"name": "model.layers.15.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 8454144
},
{
"name": "model.layers.15.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 8462336
},
{
"name": "model.layers.15.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 11608064
},
{
"name": "model.layers.15.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 19996672
},
{
"name": "model.layers.16.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21045248
},
{
"name": "model.layers.16.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 21053440
},
{
"name": "model.layers.16.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 23871488
},
{
"name": "model.layers.16.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 29507584
},
{
"name": "model.layers.16.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 29515776
}
],
"md5sum": "d90c8dbfc5f27ce0b78bf3632384915b"
},
{
"dataPath": "params_shard_62.bin",
"format": "raw-shard",
"nbytes": 31989760,
"records": [
{
"name": "model.layers.16.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 0
},
{
"name": "model.layers.16.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 8388608
},
{
"name": "model.layers.17.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 9437184
},
{
"name": "model.layers.17.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 22544384,
"byteOffset": 9445376
}
],
"md5sum": "7f1936c7d8c38f806230dca1ac315dfd"
},
{
"dataPath": "params_shard_63.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": "0aa767c50a5c1b26361bbb40ae6dbbb7"
},
{
"dataPath": "params_shard_64.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": "8cb3a4b3328f6381624da7c4324c33f5"
},
{
"dataPath": "params_shard_65.bin",
"format": "raw-shard",
"nbytes": 22544384,
"records": [
{
"name": "model.layers.18.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 22544384,
"byteOffset": 0
}
],
"md5sum": "1798af9f0e5a28cb1d84c82f4b82725b"
},
{
"dataPath": "params_shard_66.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": "ea1ddc8b133e855d2e2252dfeaa9dde0"
},
{
"dataPath": "params_shard_67.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": "753b1d87c152d969710c148f46a787fd"
},
{
"dataPath": "params_shard_68.bin",
"format": "raw-shard",
"nbytes": 32661504,
"records": [
{
"name": "model.layers.17.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 0
},
{
"name": "model.layers.17.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 2818048
},
{
"name": "model.layers.17.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 8454144
},
{
"name": "model.layers.17.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 8462336
},
{
"name": "model.layers.17.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 11608064
},
{
"name": "model.layers.17.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 19996672
},
{
"name": "model.layers.18.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21045248
},
{
"name": "model.layers.18.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 21053440
},
{
"name": "model.layers.18.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 23871488
},
{
"name": "model.layers.18.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 29507584
},
{
"name": "model.layers.18.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 29515776
}
],
"md5sum": "1d94c1ec52e1c1067c86612f207ec05d"
},
{
"dataPath": "params_shard_69.bin",
"format": "raw-shard",
"nbytes": 31989760,
"records": [
{
"name": "model.layers.18.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 0
},
{
"name": "model.layers.18.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 8388608
},
{
"name": "model.layers.19.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 9437184
},
{
"name": "model.layers.19.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 22544384,
"byteOffset": 9445376
}
],
"md5sum": "7e65e1a576c5dac1587c7b385ef1cdbd"
},
{
"dataPath": "params_shard_70.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": "6ee802a916cae4e0cbf41b940fb54508"
},
{
"dataPath": "params_shard_71.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": "e2948c5755cb7d68efeae19ae664a86e"
},
{
"dataPath": "params_shard_72.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": "9ffc8034064277666023a1b69ba9182e"
},
{
"dataPath": "params_shard_73.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": "94d3ac3d3726533fbaed2ccdde1840d2"
},
{
"dataPath": "params_shard_74.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": "7f1a7800ea9258b3f901307257c748cf"
},
{
"dataPath": "params_shard_75.bin",
"format": "raw-shard",
"nbytes": 32661504,
"records": [
{
"name": "model.layers.19.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 0
},
{
"name": "model.layers.19.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 2818048
},
{
"name": "model.layers.19.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 8454144
},
{
"name": "model.layers.19.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 8462336
},
{
"name": "model.layers.19.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 11608064
},
{
"name": "model.layers.19.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 19996672
},
{
"name": "model.layers.2.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21045248
},
{
"name": "model.layers.2.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 21053440
},
{
"name": "model.layers.2.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 23871488
},
{
"name": "model.layers.2.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 29507584
},
{
"name": "model.layers.2.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 29515776
}
],
"md5sum": "94e2fbb777aba06e5b8d4626a2fa9f65"
},
{
"dataPath": "params_shard_76.bin",
"format": "raw-shard",
"nbytes": 31989760,
"records": [
{
"name": "model.layers.2.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 0
},
{
"name": "model.layers.2.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 8388608
},
{
"name": "model.layers.20.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 9437184
},
{
"name": "model.layers.20.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 22544384,
"byteOffset": 9445376
}
],
"md5sum": "caaccb647e7712e7ca83d43c268217b5"
},
{
"dataPath": "params_shard_77.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": "abcc79a87b2f50ba1d6f0185400c327c"
},
{
"dataPath": "params_shard_78.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": "b96dd37c8afafaa2cc1607b78dec3dab"
},
{
"dataPath": "params_shard_79.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": "bb5b9ff0b3d8cf527320489f32b9325c"
},
{
"dataPath": "params_shard_80.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": "7a37df2e26f68f4974a30362a970aeeb"
},
{
"dataPath": "params_shard_81.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": "c97e37fd77f229acc0790f340cbe07ba"
},
{
"dataPath": "params_shard_82.bin",
"format": "raw-shard",
"nbytes": 32661504,
"records": [
{
"name": "model.layers.20.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 0
},
{
"name": "model.layers.20.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 2818048
},
{
"name": "model.layers.20.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 8454144
},
{
"name": "model.layers.20.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 8462336
},
{
"name": "model.layers.20.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 11608064
},
{
"name": "model.layers.20.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 19996672
},
{
"name": "model.layers.21.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21045248
},
{
"name": "model.layers.21.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 21053440
},
{
"name": "model.layers.21.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 23871488
},
{
"name": "model.layers.21.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 29507584
},
{
"name": "model.layers.21.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 29515776
}
],
"md5sum": "ef59a6e46bec2c878929be0709637337"
},
{
"dataPath": "params_shard_83.bin",
"format": "raw-shard",
"nbytes": 31989760,
"records": [
{
"name": "model.layers.21.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 0
},
{
"name": "model.layers.21.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 8388608
},
{
"name": "model.layers.22.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 9437184
},
{
"name": "model.layers.22.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 22544384,
"byteOffset": 9445376
}
],
"md5sum": "6796e898d1ee28ccdbb0e34b4d8c0176"
},
{
"dataPath": "params_shard_84.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": "4e5bb5f063db7ab7c5b3f3e5cd961b0a"
},
{
"dataPath": "params_shard_85.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": "e1c7d358d7f12d530a0a8b9f084f9e6a"
},
{
"dataPath": "params_shard_86.bin",
"format": "raw-shard",
"nbytes": 22544384,
"records": [
{
"name": "model.layers.23.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 22544384,
"byteOffset": 0
}
],
"md5sum": "567718c8d783bd448ac397ac1bdd8343"
},
{
"dataPath": "params_shard_87.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": "26b13c9dcf2162c7914985ae29fcc58e"
},
{
"dataPath": "params_shard_88.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": "252dec4f6ec185cc0ac116e2b68ce4ee"
},
{
"dataPath": "params_shard_89.bin",
"format": "raw-shard",
"nbytes": 32661504,
"records": [
{
"name": "model.layers.22.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 0
},
{
"name": "model.layers.22.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 2818048
},
{
"name": "model.layers.22.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 8454144
},
{
"name": "model.layers.22.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 8462336
},
{
"name": "model.layers.22.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 11608064
},
{
"name": "model.layers.22.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 19996672
},
{
"name": "model.layers.23.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21045248
},
{
"name": "model.layers.23.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 21053440
},
{
"name": "model.layers.23.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 23871488
},
{
"name": "model.layers.23.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 29507584
},
{
"name": "model.layers.23.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 29515776
}
],
"md5sum": "a66c5f4ac9b1579678763f9424c1f912"
},
{
"dataPath": "params_shard_90.bin",
"format": "raw-shard",
"nbytes": 31989760,
"records": [
{
"name": "model.layers.23.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 0
},
{
"name": "model.layers.23.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 8388608
},
{
"name": "model.layers.3.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 9437184
},
{
"name": "model.layers.3.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 22544384,
"byteOffset": 9445376
}
],
"md5sum": "77de37a78d8b9bbeaf4c510b0dd4a796"
},
{
"dataPath": "params_shard_91.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": "ddc0fe4878c95ff70974ddb82b32be13"
},
{
"dataPath": "params_shard_92.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": "02cb1d5b1025c75649a44aeb3a38abfe"
},
{
"dataPath": "params_shard_93.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": "995f40ffec3c1286d3f76305cb0f7d61"
},
{
"dataPath": "params_shard_94.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": "9d448ae38f4dd2fc305bdfae2399102e"
},
{
"dataPath": "params_shard_95.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": "2c4e9d9d118aed57797ef1fbd97a0676"
},
{
"dataPath": "params_shard_96.bin",
"format": "raw-shard",
"nbytes": 32661504,
"records": [
{
"name": "model.layers.3.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 0
},
{
"name": "model.layers.3.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 2818048
},
{
"name": "model.layers.3.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 8454144
},
{
"name": "model.layers.3.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 8462336
},
{
"name": "model.layers.3.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 11608064
},
{
"name": "model.layers.3.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 19996672
},
{
"name": "model.layers.4.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21045248
},
{
"name": "model.layers.4.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 21053440
},
{
"name": "model.layers.4.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 23871488
},
{
"name": "model.layers.4.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 29507584
},
{
"name": "model.layers.4.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 29515776
}
],
"md5sum": "2248ea2374a7bed4c0f69f05b5d39ab3"
},
{
"dataPath": "params_shard_97.bin",
"format": "raw-shard",
"nbytes": 31989760,
"records": [
{
"name": "model.layers.4.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 0
},
{
"name": "model.layers.4.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 8388608
},
{
"name": "model.layers.5.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 9437184
},
{
"name": "model.layers.5.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 22544384,
"byteOffset": 9445376
}
],
"md5sum": "1cc76d099e7d58b9befd98ee916e39a5"
},
{
"dataPath": "params_shard_98.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": "d33c3211f9f52805cb257b4428e3eea1"
},
{
"dataPath": "params_shard_99.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": "c767443864767299b3827584001c39ec"
},
{
"dataPath": "params_shard_100.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": "3a3a374204d0900005d525221b2e7fba"
},
{
"dataPath": "params_shard_101.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": "6459e28417e2dcf6912dbfaa6baae256"
},
{
"dataPath": "params_shard_102.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": "f037352bf2e57687d4e889927e4317fe"
},
{
"dataPath": "params_shard_103.bin",
"format": "raw-shard",
"nbytes": 32661504,
"records": [
{
"name": "model.layers.5.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 0
},
{
"name": "model.layers.5.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 2818048
},
{
"name": "model.layers.5.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 8454144
},
{
"name": "model.layers.5.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 8462336
},
{
"name": "model.layers.5.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 11608064
},
{
"name": "model.layers.5.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 19996672
},
{
"name": "model.layers.6.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21045248
},
{
"name": "model.layers.6.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 21053440
},
{
"name": "model.layers.6.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 23871488
},
{
"name": "model.layers.6.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 29507584
},
{
"name": "model.layers.6.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 29515776
}
],
"md5sum": "b36c461fc1f8f94e49f5ebcfefdd1077"
},
{
"dataPath": "params_shard_104.bin",
"format": "raw-shard",
"nbytes": 31989760,
"records": [
{
"name": "model.layers.6.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 0
},
{
"name": "model.layers.6.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 8388608
},
{
"name": "model.layers.7.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 9437184
},
{
"name": "model.layers.7.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 22544384,
"byteOffset": 9445376
}
],
"md5sum": "a9aa59b32b424d8a1cc062de20cf2f3d"
},
{
"dataPath": "params_shard_105.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": "f595d583a38a85d03872bdc183fd1a8e"
},
{
"dataPath": "params_shard_106.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": "93acf6bb17301488dfc3e47d8b58eddc"
},
{
"dataPath": "params_shard_107.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": "8122367c83159a8bc65e4b15f61a1538"
},
{
"dataPath": "params_shard_108.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": "4f29264b7e65c4d3d89cb070473bef8f"
},
{
"dataPath": "params_shard_109.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": "bde747bc9d5dee1f5898cdf4e36ff99b"
},
{
"dataPath": "params_shard_110.bin",
"format": "raw-shard",
"nbytes": 32661504,
"records": [
{
"name": "model.layers.7.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 0
},
{
"name": "model.layers.7.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 2818048
},
{
"name": "model.layers.7.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 8454144
},
{
"name": "model.layers.7.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 8462336
},
{
"name": "model.layers.7.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 11608064
},
{
"name": "model.layers.7.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 19996672
},
{
"name": "model.layers.8.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21045248
},
{
"name": "model.layers.8.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 21053440
},
{
"name": "model.layers.8.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 23871488
},
{
"name": "model.layers.8.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 29507584
},
{
"name": "model.layers.8.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 29515776
}
],
"md5sum": "8639f9e156b02ddba16974ae79a56e71"
},
{
"dataPath": "params_shard_111.bin",
"format": "raw-shard",
"nbytes": 31989760,
"records": [
{
"name": "model.layers.8.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 0
},
{
"name": "model.layers.8.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 8388608
},
{
"name": "model.layers.9.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 9437184
},
{
"name": "model.layers.9.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 22544384,
"byteOffset": 9445376
}
],
"md5sum": "d946355a8d1e6a4278c18f0190f0efcf"
},
{
"dataPath": "params_shard_112.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": "c89d629c34ef02a1d1355844d3098bcb"
},
{
"dataPath": "params_shard_113.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": "3ddc743bd10fbc8f8f28a58362247978"
},
{
"dataPath": "params_shard_114.bin",
"format": "raw-shard",
"nbytes": 21045248,
"records": [
{
"name": "model.layers.9.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 0
},
{
"name": "model.layers.9.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 2818048
},
{
"name": "model.layers.9.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 8454144
},
{
"name": "model.layers.9.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 8462336
},
{
"name": "model.layers.9.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 11608064
},
{
"name": "model.layers.9.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 19996672
}
],
"md5sum": "0f58a152cf6a3e1fa8a374df830451e8"
}
]
}