MeowFET
exp: update model weights, tools, and README
71ec309
{
"metadata": {
"ParamSize": 470,
"ParamBytes": 6220550656.0,
"BitsPerParam": 16.0
},
"records": [
{
"dataPath": "params_shard_0.bin",
"format": "raw-shard",
"nbytes": 698941440,
"records": [
{
"name": "model.embed_tokens.weight",
"shape": [
1185,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 698941440,
"byteOffset": 0
}
],
"md5sum": "10ca727fa119834a674e3b558aa9b47d"
},
{
"dataPath": "params_shard_1.bin",
"format": "raw-shard",
"nbytes": 53084160,
"records": [
{
"name": "model.layers.0.mlp.gate_up_proj.weight",
"shape": [
90,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 53084160,
"byteOffset": 0
}
],
"md5sum": "b2b7798ad551b16180cd977d54178226"
},
{
"dataPath": "params_shard_2.bin",
"format": "raw-shard",
"nbytes": 26542080,
"records": [
{
"name": "model.layers.0.mlp.down_proj.weight",
"shape": [
18,
5760,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 26542080,
"byteOffset": 0
}
],
"md5sum": "8fd72a671e76869aed05c859b6ba14e2"
},
{
"dataPath": "params_shard_3.bin",
"format": "raw-shard",
"nbytes": 26558464,
"records": [
{
"name": "model.layers.0.self_attn.wqkv_pack.weight",
"shape": [
27,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 15925248,
"byteOffset": 0
},
{
"name": "model.layers.0.self_attn.wqkv_pack.bias",
"shape": [
3456
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6912,
"byteOffset": 15925248
},
{
"name": "model.layers.0.self_attn.o_proj.weight",
"shape": [
18,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10616832,
"byteOffset": 15932160
},
{
"name": "model.layers.0.self_attn.q_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26548992
},
{
"name": "model.layers.0.self_attn.k_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26549120
},
{
"name": "model.layers.0.input_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26549248
},
{
"name": "model.layers.0.post_attention_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26553856
}
],
"md5sum": "a34af8d73ea66b4677e72514ee65730d"
},
{
"dataPath": "params_shard_4.bin",
"format": "raw-shard",
"nbytes": 53084160,
"records": [
{
"name": "model.layers.1.mlp.gate_up_proj.weight",
"shape": [
90,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 53084160,
"byteOffset": 0
}
],
"md5sum": "8352e04537ba8ea59506c6048b556d03"
},
{
"dataPath": "params_shard_5.bin",
"format": "raw-shard",
"nbytes": 26542080,
"records": [
{
"name": "model.layers.1.mlp.down_proj.weight",
"shape": [
18,
5760,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 26542080,
"byteOffset": 0
}
],
"md5sum": "ad8b98ad91495b58324ebe83e4f47b4a"
},
{
"dataPath": "params_shard_6.bin",
"format": "raw-shard",
"nbytes": 26558464,
"records": [
{
"name": "model.layers.1.self_attn.wqkv_pack.weight",
"shape": [
27,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 15925248,
"byteOffset": 0
},
{
"name": "model.layers.1.self_attn.wqkv_pack.bias",
"shape": [
3456
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6912,
"byteOffset": 15925248
},
{
"name": "model.layers.1.self_attn.o_proj.weight",
"shape": [
18,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10616832,
"byteOffset": 15932160
},
{
"name": "model.layers.1.self_attn.q_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26548992
},
{
"name": "model.layers.1.self_attn.k_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26549120
},
{
"name": "model.layers.1.input_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26549248
},
{
"name": "model.layers.1.post_attention_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26553856
}
],
"md5sum": "6a3e7f3d50b2c151ce66814b88adbebb"
},
{
"dataPath": "params_shard_7.bin",
"format": "raw-shard",
"nbytes": 53084160,
"records": [
{
"name": "model.layers.2.mlp.gate_up_proj.weight",
"shape": [
90,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 53084160,
"byteOffset": 0
}
],
"md5sum": "b88ab1961d2917ffa7a776ec4857151d"
},
{
"dataPath": "params_shard_8.bin",
"format": "raw-shard",
"nbytes": 26542080,
"records": [
{
"name": "model.layers.2.mlp.down_proj.weight",
"shape": [
18,
5760,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 26542080,
"byteOffset": 0
}
],
"md5sum": "d1ab5189e8ea43826a367086964539a1"
},
{
"dataPath": "params_shard_9.bin",
"format": "raw-shard",
"nbytes": 26558464,
"records": [
{
"name": "model.layers.2.self_attn.wqkv_pack.weight",
"shape": [
27,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 15925248,
"byteOffset": 0
},
{
"name": "model.layers.2.self_attn.wqkv_pack.bias",
"shape": [
3456
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6912,
"byteOffset": 15925248
},
{
"name": "model.layers.2.self_attn.o_proj.weight",
"shape": [
18,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10616832,
"byteOffset": 15932160
},
{
"name": "model.layers.2.self_attn.q_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26548992
},
{
"name": "model.layers.2.self_attn.k_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26549120
},
{
"name": "model.layers.2.input_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26549248
},
{
"name": "model.layers.2.post_attention_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26553856
}
],
"md5sum": "31a5e376dc6355d50405bef1b18154a0"
},
{
"dataPath": "params_shard_10.bin",
"format": "raw-shard",
"nbytes": 53084160,
"records": [
{
"name": "model.layers.3.mlp.gate_up_proj.weight",
"shape": [
90,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 53084160,
"byteOffset": 0
}
],
"md5sum": "6efc62345c7f09b0ddf12e55344df2a7"
},
{
"dataPath": "params_shard_11.bin",
"format": "raw-shard",
"nbytes": 26542080,
"records": [
{
"name": "model.layers.3.mlp.down_proj.weight",
"shape": [
18,
5760,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 26542080,
"byteOffset": 0
}
],
"md5sum": "77220b226468146055a1fa7550e645e0"
},
{
"dataPath": "params_shard_12.bin",
"format": "raw-shard",
"nbytes": 26558464,
"records": [
{
"name": "model.layers.3.self_attn.wqkv_pack.weight",
"shape": [
27,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 15925248,
"byteOffset": 0
},
{
"name": "model.layers.3.self_attn.wqkv_pack.bias",
"shape": [
3456
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6912,
"byteOffset": 15925248
},
{
"name": "model.layers.3.self_attn.o_proj.weight",
"shape": [
18,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10616832,
"byteOffset": 15932160
},
{
"name": "model.layers.3.self_attn.q_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26548992
},
{
"name": "model.layers.3.self_attn.k_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26549120
},
{
"name": "model.layers.3.input_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26549248
},
{
"name": "model.layers.3.post_attention_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26553856
}
],
"md5sum": "39b310dba007f2d19c56922fae7ed5b0"
},
{
"dataPath": "params_shard_13.bin",
"format": "raw-shard",
"nbytes": 53084160,
"records": [
{
"name": "model.layers.4.mlp.gate_up_proj.weight",
"shape": [
90,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 53084160,
"byteOffset": 0
}
],
"md5sum": "264b3f70f73122faed705c91f51388db"
},
{
"dataPath": "params_shard_14.bin",
"format": "raw-shard",
"nbytes": 26542080,
"records": [
{
"name": "model.layers.4.mlp.down_proj.weight",
"shape": [
18,
5760,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 26542080,
"byteOffset": 0
}
],
"md5sum": "50056449a9dcc72b4f608128d30aaab4"
},
{
"dataPath": "params_shard_15.bin",
"format": "raw-shard",
"nbytes": 26558464,
"records": [
{
"name": "model.layers.4.self_attn.wqkv_pack.weight",
"shape": [
27,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 15925248,
"byteOffset": 0
},
{
"name": "model.layers.4.self_attn.wqkv_pack.bias",
"shape": [
3456
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6912,
"byteOffset": 15925248
},
{
"name": "model.layers.4.self_attn.o_proj.weight",
"shape": [
18,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10616832,
"byteOffset": 15932160
},
{
"name": "model.layers.4.self_attn.q_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26548992
},
{
"name": "model.layers.4.self_attn.k_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26549120
},
{
"name": "model.layers.4.input_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26549248
},
{
"name": "model.layers.4.post_attention_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26553856
}
],
"md5sum": "0d1ab9913e897a8c9072f198d654be9e"
},
{
"dataPath": "params_shard_16.bin",
"format": "raw-shard",
"nbytes": 53084160,
"records": [
{
"name": "model.layers.5.mlp.gate_up_proj.weight",
"shape": [
90,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 53084160,
"byteOffset": 0
}
],
"md5sum": "e29e1799190e7807cce339cf223dc911"
},
{
"dataPath": "params_shard_17.bin",
"format": "raw-shard",
"nbytes": 26542080,
"records": [
{
"name": "model.layers.5.mlp.down_proj.weight",
"shape": [
18,
5760,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 26542080,
"byteOffset": 0
}
],
"md5sum": "6a0dd24637ced53c0582303feb667feb"
},
{
"dataPath": "params_shard_18.bin",
"format": "raw-shard",
"nbytes": 26558464,
"records": [
{
"name": "model.layers.5.self_attn.wqkv_pack.weight",
"shape": [
27,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 15925248,
"byteOffset": 0
},
{
"name": "model.layers.5.self_attn.wqkv_pack.bias",
"shape": [
3456
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6912,
"byteOffset": 15925248
},
{
"name": "model.layers.5.self_attn.o_proj.weight",
"shape": [
18,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10616832,
"byteOffset": 15932160
},
{
"name": "model.layers.5.self_attn.q_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26548992
},
{
"name": "model.layers.5.self_attn.k_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26549120
},
{
"name": "model.layers.5.input_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26549248
},
{
"name": "model.layers.5.post_attention_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26553856
}
],
"md5sum": "3b1b041395faecb9b9d7282a161bec49"
},
{
"dataPath": "params_shard_19.bin",
"format": "raw-shard",
"nbytes": 53084160,
"records": [
{
"name": "model.layers.6.mlp.gate_up_proj.weight",
"shape": [
90,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 53084160,
"byteOffset": 0
}
],
"md5sum": "7c2f25dab15ef369aaf4d67aa6823b23"
},
{
"dataPath": "params_shard_20.bin",
"format": "raw-shard",
"nbytes": 26542080,
"records": [
{
"name": "model.layers.6.mlp.down_proj.weight",
"shape": [
18,
5760,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 26542080,
"byteOffset": 0
}
],
"md5sum": "26de2a704f0e21b76218375f64bfe951"
},
{
"dataPath": "params_shard_21.bin",
"format": "raw-shard",
"nbytes": 26558464,
"records": [
{
"name": "model.layers.6.self_attn.wqkv_pack.weight",
"shape": [
27,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 15925248,
"byteOffset": 0
},
{
"name": "model.layers.6.self_attn.wqkv_pack.bias",
"shape": [
3456
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6912,
"byteOffset": 15925248
},
{
"name": "model.layers.6.self_attn.o_proj.weight",
"shape": [
18,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10616832,
"byteOffset": 15932160
},
{
"name": "model.layers.6.self_attn.q_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26548992
},
{
"name": "model.layers.6.self_attn.k_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26549120
},
{
"name": "model.layers.6.input_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26549248
},
{
"name": "model.layers.6.post_attention_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26553856
}
],
"md5sum": "dc6a0c7554328066638b1767a1cd1541"
},
{
"dataPath": "params_shard_22.bin",
"format": "raw-shard",
"nbytes": 53084160,
"records": [
{
"name": "model.layers.7.mlp.gate_up_proj.weight",
"shape": [
90,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 53084160,
"byteOffset": 0
}
],
"md5sum": "11ee5041a35a58aeecadff5d8ad504e1"
},
{
"dataPath": "params_shard_23.bin",
"format": "raw-shard",
"nbytes": 26542080,
"records": [
{
"name": "model.layers.7.mlp.down_proj.weight",
"shape": [
18,
5760,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 26542080,
"byteOffset": 0
}
],
"md5sum": "069f2396584c4de563c885e5e0358911"
},
{
"dataPath": "params_shard_24.bin",
"format": "raw-shard",
"nbytes": 26558464,
"records": [
{
"name": "model.layers.7.self_attn.wqkv_pack.weight",
"shape": [
27,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 15925248,
"byteOffset": 0
},
{
"name": "model.layers.7.self_attn.wqkv_pack.bias",
"shape": [
3456
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6912,
"byteOffset": 15925248
},
{
"name": "model.layers.7.self_attn.o_proj.weight",
"shape": [
18,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10616832,
"byteOffset": 15932160
},
{
"name": "model.layers.7.self_attn.q_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26548992
},
{
"name": "model.layers.7.self_attn.k_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26549120
},
{
"name": "model.layers.7.input_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26549248
},
{
"name": "model.layers.7.post_attention_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26553856
}
],
"md5sum": "0005fbb383ccf496db3337836a8d9453"
},
{
"dataPath": "params_shard_25.bin",
"format": "raw-shard",
"nbytes": 53084160,
"records": [
{
"name": "model.layers.8.mlp.gate_up_proj.weight",
"shape": [
90,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 53084160,
"byteOffset": 0
}
],
"md5sum": "aea7507daea0446116f6f6d685d6f913"
},
{
"dataPath": "params_shard_26.bin",
"format": "raw-shard",
"nbytes": 26542080,
"records": [
{
"name": "model.layers.8.mlp.down_proj.weight",
"shape": [
18,
5760,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 26542080,
"byteOffset": 0
}
],
"md5sum": "727eeb18ede4b771493a9a6eca99ac44"
},
{
"dataPath": "params_shard_27.bin",
"format": "raw-shard",
"nbytes": 26558464,
"records": [
{
"name": "model.layers.8.self_attn.wqkv_pack.weight",
"shape": [
27,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 15925248,
"byteOffset": 0
},
{
"name": "model.layers.8.self_attn.wqkv_pack.bias",
"shape": [
3456
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6912,
"byteOffset": 15925248
},
{
"name": "model.layers.8.self_attn.o_proj.weight",
"shape": [
18,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10616832,
"byteOffset": 15932160
},
{
"name": "model.layers.8.self_attn.q_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26548992
},
{
"name": "model.layers.8.self_attn.k_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26549120
},
{
"name": "model.layers.8.input_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26549248
},
{
"name": "model.layers.8.post_attention_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26553856
}
],
"md5sum": "383a440217093395a0a28492e64a8263"
},
{
"dataPath": "params_shard_28.bin",
"format": "raw-shard",
"nbytes": 53084160,
"records": [
{
"name": "model.layers.9.mlp.gate_up_proj.weight",
"shape": [
90,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 53084160,
"byteOffset": 0
}
],
"md5sum": "c2374550c2d0ca9f18da6585e66c2250"
},
{
"dataPath": "params_shard_29.bin",
"format": "raw-shard",
"nbytes": 26542080,
"records": [
{
"name": "model.layers.9.mlp.down_proj.weight",
"shape": [
18,
5760,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 26542080,
"byteOffset": 0
}
],
"md5sum": "24ef70e6697339816ceb060c9252e0fa"
},
{
"dataPath": "params_shard_30.bin",
"format": "raw-shard",
"nbytes": 26558464,
"records": [
{
"name": "model.layers.9.self_attn.wqkv_pack.weight",
"shape": [
27,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 15925248,
"byteOffset": 0
},
{
"name": "model.layers.9.self_attn.wqkv_pack.bias",
"shape": [
3456
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6912,
"byteOffset": 15925248
},
{
"name": "model.layers.9.self_attn.o_proj.weight",
"shape": [
18,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10616832,
"byteOffset": 15932160
},
{
"name": "model.layers.9.self_attn.q_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26548992
},
{
"name": "model.layers.9.self_attn.k_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26549120
},
{
"name": "model.layers.9.input_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26549248
},
{
"name": "model.layers.9.post_attention_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26553856
}
],
"md5sum": "8d2e4ecc75448ab17437330cfb9a5c4a"
},
{
"dataPath": "params_shard_31.bin",
"format": "raw-shard",
"nbytes": 53084160,
"records": [
{
"name": "model.layers.10.mlp.gate_up_proj.weight",
"shape": [
90,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 53084160,
"byteOffset": 0
}
],
"md5sum": "6ce1e6f0f4db822b8de4f8f6284e5d9a"
},
{
"dataPath": "params_shard_32.bin",
"format": "raw-shard",
"nbytes": 26542080,
"records": [
{
"name": "model.layers.10.mlp.down_proj.weight",
"shape": [
18,
5760,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 26542080,
"byteOffset": 0
}
],
"md5sum": "3e0b7259552f04dd5ad9973a735529e7"
},
{
"dataPath": "params_shard_33.bin",
"format": "raw-shard",
"nbytes": 26558464,
"records": [
{
"name": "model.layers.10.self_attn.wqkv_pack.weight",
"shape": [
27,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 15925248,
"byteOffset": 0
},
{
"name": "model.layers.10.self_attn.wqkv_pack.bias",
"shape": [
3456
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6912,
"byteOffset": 15925248
},
{
"name": "model.layers.10.self_attn.o_proj.weight",
"shape": [
18,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10616832,
"byteOffset": 15932160
},
{
"name": "model.layers.10.self_attn.q_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26548992
},
{
"name": "model.layers.10.self_attn.k_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26549120
},
{
"name": "model.layers.10.input_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26549248
},
{
"name": "model.layers.10.post_attention_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26553856
}
],
"md5sum": "00724cf0c5d8f7be78b37e7b19297a2f"
},
{
"dataPath": "params_shard_34.bin",
"format": "raw-shard",
"nbytes": 53084160,
"records": [
{
"name": "model.layers.11.mlp.gate_up_proj.weight",
"shape": [
90,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 53084160,
"byteOffset": 0
}
],
"md5sum": "869fb52b59a403dc24e7560170bc585b"
},
{
"dataPath": "params_shard_35.bin",
"format": "raw-shard",
"nbytes": 26542080,
"records": [
{
"name": "model.layers.11.mlp.down_proj.weight",
"shape": [
18,
5760,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 26542080,
"byteOffset": 0
}
],
"md5sum": "61c95b781ad048c7278d3e2dd3f66c2f"
},
{
"dataPath": "params_shard_36.bin",
"format": "raw-shard",
"nbytes": 26558464,
"records": [
{
"name": "model.layers.11.self_attn.wqkv_pack.weight",
"shape": [
27,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 15925248,
"byteOffset": 0
},
{
"name": "model.layers.11.self_attn.wqkv_pack.bias",
"shape": [
3456
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6912,
"byteOffset": 15925248
},
{
"name": "model.layers.11.self_attn.o_proj.weight",
"shape": [
18,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10616832,
"byteOffset": 15932160
},
{
"name": "model.layers.11.self_attn.q_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26548992
},
{
"name": "model.layers.11.self_attn.k_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26549120
},
{
"name": "model.layers.11.input_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26549248
},
{
"name": "model.layers.11.post_attention_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26553856
}
],
"md5sum": "cdf5269d41ce98fa0f378a660635c480"
},
{
"dataPath": "params_shard_37.bin",
"format": "raw-shard",
"nbytes": 53084160,
"records": [
{
"name": "model.layers.12.mlp.gate_up_proj.weight",
"shape": [
90,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 53084160,
"byteOffset": 0
}
],
"md5sum": "b809342b4f6da334c4c2d6f95e48bcac"
},
{
"dataPath": "params_shard_38.bin",
"format": "raw-shard",
"nbytes": 26542080,
"records": [
{
"name": "model.layers.12.mlp.down_proj.weight",
"shape": [
18,
5760,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 26542080,
"byteOffset": 0
}
],
"md5sum": "92b1b101abdb8659462200361f87a217"
},
{
"dataPath": "params_shard_39.bin",
"format": "raw-shard",
"nbytes": 26558464,
"records": [
{
"name": "model.layers.12.self_attn.wqkv_pack.weight",
"shape": [
27,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 15925248,
"byteOffset": 0
},
{
"name": "model.layers.12.self_attn.wqkv_pack.bias",
"shape": [
3456
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6912,
"byteOffset": 15925248
},
{
"name": "model.layers.12.self_attn.o_proj.weight",
"shape": [
18,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10616832,
"byteOffset": 15932160
},
{
"name": "model.layers.12.self_attn.q_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26548992
},
{
"name": "model.layers.12.self_attn.k_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26549120
},
{
"name": "model.layers.12.input_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26549248
},
{
"name": "model.layers.12.post_attention_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26553856
}
],
"md5sum": "1f26220eb2e5218e6eddaea808f48906"
},
{
"dataPath": "params_shard_40.bin",
"format": "raw-shard",
"nbytes": 53084160,
"records": [
{
"name": "model.layers.13.mlp.gate_up_proj.weight",
"shape": [
90,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 53084160,
"byteOffset": 0
}
],
"md5sum": "8f7d579dbd3896b0c9d8494e2c09eebf"
},
{
"dataPath": "params_shard_41.bin",
"format": "raw-shard",
"nbytes": 26542080,
"records": [
{
"name": "model.layers.13.mlp.down_proj.weight",
"shape": [
18,
5760,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 26542080,
"byteOffset": 0
}
],
"md5sum": "2a0b1ad1f526b5f9470c817375c5076d"
},
{
"dataPath": "params_shard_42.bin",
"format": "raw-shard",
"nbytes": 26558464,
"records": [
{
"name": "model.layers.13.self_attn.wqkv_pack.weight",
"shape": [
27,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 15925248,
"byteOffset": 0
},
{
"name": "model.layers.13.self_attn.wqkv_pack.bias",
"shape": [
3456
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6912,
"byteOffset": 15925248
},
{
"name": "model.layers.13.self_attn.o_proj.weight",
"shape": [
18,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10616832,
"byteOffset": 15932160
},
{
"name": "model.layers.13.self_attn.q_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26548992
},
{
"name": "model.layers.13.self_attn.k_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26549120
},
{
"name": "model.layers.13.input_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26549248
},
{
"name": "model.layers.13.post_attention_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26553856
}
],
"md5sum": "d522f399e9ccfd0a2f58a7a6a0c6e462"
},
{
"dataPath": "params_shard_43.bin",
"format": "raw-shard",
"nbytes": 53084160,
"records": [
{
"name": "model.layers.14.mlp.gate_up_proj.weight",
"shape": [
90,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 53084160,
"byteOffset": 0
}
],
"md5sum": "c6676fadd0632de78bfe771174beab8f"
},
{
"dataPath": "params_shard_44.bin",
"format": "raw-shard",
"nbytes": 26542080,
"records": [
{
"name": "model.layers.14.mlp.down_proj.weight",
"shape": [
18,
5760,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 26542080,
"byteOffset": 0
}
],
"md5sum": "3661b070dd1ce346158fe37712343dc9"
},
{
"dataPath": "params_shard_45.bin",
"format": "raw-shard",
"nbytes": 26558464,
"records": [
{
"name": "model.layers.14.self_attn.wqkv_pack.weight",
"shape": [
27,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 15925248,
"byteOffset": 0
},
{
"name": "model.layers.14.self_attn.wqkv_pack.bias",
"shape": [
3456
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6912,
"byteOffset": 15925248
},
{
"name": "model.layers.14.self_attn.o_proj.weight",
"shape": [
18,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10616832,
"byteOffset": 15932160
},
{
"name": "model.layers.14.self_attn.q_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26548992
},
{
"name": "model.layers.14.self_attn.k_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26549120
},
{
"name": "model.layers.14.input_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26549248
},
{
"name": "model.layers.14.post_attention_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26553856
}
],
"md5sum": "246547e55187bb51c535ebe86e3bb372"
},
{
"dataPath": "params_shard_46.bin",
"format": "raw-shard",
"nbytes": 53084160,
"records": [
{
"name": "model.layers.15.mlp.gate_up_proj.weight",
"shape": [
90,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 53084160,
"byteOffset": 0
}
],
"md5sum": "9ce899f8c2d657574735a59d716e8c1c"
},
{
"dataPath": "params_shard_47.bin",
"format": "raw-shard",
"nbytes": 26542080,
"records": [
{
"name": "model.layers.15.mlp.down_proj.weight",
"shape": [
18,
5760,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 26542080,
"byteOffset": 0
}
],
"md5sum": "ba08ef438f054198bdbc7585c4ce41d4"
},
{
"dataPath": "params_shard_48.bin",
"format": "raw-shard",
"nbytes": 26558464,
"records": [
{
"name": "model.layers.15.self_attn.wqkv_pack.weight",
"shape": [
27,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 15925248,
"byteOffset": 0
},
{
"name": "model.layers.15.self_attn.wqkv_pack.bias",
"shape": [
3456
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6912,
"byteOffset": 15925248
},
{
"name": "model.layers.15.self_attn.o_proj.weight",
"shape": [
18,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10616832,
"byteOffset": 15932160
},
{
"name": "model.layers.15.self_attn.q_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26548992
},
{
"name": "model.layers.15.self_attn.k_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26549120
},
{
"name": "model.layers.15.input_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26549248
},
{
"name": "model.layers.15.post_attention_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26553856
}
],
"md5sum": "6dfac609e502c0c105885c2fd5e8c2d8"
},
{
"dataPath": "params_shard_49.bin",
"format": "raw-shard",
"nbytes": 53084160,
"records": [
{
"name": "model.layers.16.mlp.gate_up_proj.weight",
"shape": [
90,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 53084160,
"byteOffset": 0
}
],
"md5sum": "c275f2697847e268b9247bade0c9f0f7"
},
{
"dataPath": "params_shard_50.bin",
"format": "raw-shard",
"nbytes": 26542080,
"records": [
{
"name": "model.layers.16.mlp.down_proj.weight",
"shape": [
18,
5760,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 26542080,
"byteOffset": 0
}
],
"md5sum": "72a5cb8a3c3f6d29092373adb2986cbd"
},
{
"dataPath": "params_shard_51.bin",
"format": "raw-shard",
"nbytes": 26558464,
"records": [
{
"name": "model.layers.16.self_attn.wqkv_pack.weight",
"shape": [
27,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 15925248,
"byteOffset": 0
},
{
"name": "model.layers.16.self_attn.wqkv_pack.bias",
"shape": [
3456
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6912,
"byteOffset": 15925248
},
{
"name": "model.layers.16.self_attn.o_proj.weight",
"shape": [
18,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10616832,
"byteOffset": 15932160
},
{
"name": "model.layers.16.self_attn.q_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26548992
},
{
"name": "model.layers.16.self_attn.k_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26549120
},
{
"name": "model.layers.16.input_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26549248
},
{
"name": "model.layers.16.post_attention_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26553856
}
],
"md5sum": "cc7a26b6e087aee4454259a8886779eb"
},
{
"dataPath": "params_shard_52.bin",
"format": "raw-shard",
"nbytes": 53084160,
"records": [
{
"name": "model.layers.17.mlp.gate_up_proj.weight",
"shape": [
90,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 53084160,
"byteOffset": 0
}
],
"md5sum": "4c9b5d50dbb7f79af445566b8704f67a"
},
{
"dataPath": "params_shard_53.bin",
"format": "raw-shard",
"nbytes": 26542080,
"records": [
{
"name": "model.layers.17.mlp.down_proj.weight",
"shape": [
18,
5760,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 26542080,
"byteOffset": 0
}
],
"md5sum": "d7eb3e656935e1f03d3900f4c43712d6"
},
{
"dataPath": "params_shard_54.bin",
"format": "raw-shard",
"nbytes": 26558464,
"records": [
{
"name": "model.layers.17.self_attn.wqkv_pack.weight",
"shape": [
27,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 15925248,
"byteOffset": 0
},
{
"name": "model.layers.17.self_attn.wqkv_pack.bias",
"shape": [
3456
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6912,
"byteOffset": 15925248
},
{
"name": "model.layers.17.self_attn.o_proj.weight",
"shape": [
18,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10616832,
"byteOffset": 15932160
},
{
"name": "model.layers.17.self_attn.q_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26548992
},
{
"name": "model.layers.17.self_attn.k_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26549120
},
{
"name": "model.layers.17.input_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26549248
},
{
"name": "model.layers.17.post_attention_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26553856
}
],
"md5sum": "e38b6776283187bccba898f2e14f9d07"
},
{
"dataPath": "params_shard_55.bin",
"format": "raw-shard",
"nbytes": 53084160,
"records": [
{
"name": "model.layers.18.mlp.gate_up_proj.weight",
"shape": [
90,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 53084160,
"byteOffset": 0
}
],
"md5sum": "79459b9878ebf4a7319db8e48e363085"
},
{
"dataPath": "params_shard_56.bin",
"format": "raw-shard",
"nbytes": 26542080,
"records": [
{
"name": "model.layers.18.mlp.down_proj.weight",
"shape": [
18,
5760,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 26542080,
"byteOffset": 0
}
],
"md5sum": "4ccad088e94f33dab7984c1f11d93b35"
},
{
"dataPath": "params_shard_57.bin",
"format": "raw-shard",
"nbytes": 26558464,
"records": [
{
"name": "model.layers.18.self_attn.wqkv_pack.weight",
"shape": [
27,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 15925248,
"byteOffset": 0
},
{
"name": "model.layers.18.self_attn.wqkv_pack.bias",
"shape": [
3456
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6912,
"byteOffset": 15925248
},
{
"name": "model.layers.18.self_attn.o_proj.weight",
"shape": [
18,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10616832,
"byteOffset": 15932160
},
{
"name": "model.layers.18.self_attn.q_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26548992
},
{
"name": "model.layers.18.self_attn.k_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26549120
},
{
"name": "model.layers.18.input_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26549248
},
{
"name": "model.layers.18.post_attention_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26553856
}
],
"md5sum": "9e0b3d2b3859dc4c75fcb23538d6a896"
},
{
"dataPath": "params_shard_58.bin",
"format": "raw-shard",
"nbytes": 53084160,
"records": [
{
"name": "model.layers.19.mlp.gate_up_proj.weight",
"shape": [
90,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 53084160,
"byteOffset": 0
}
],
"md5sum": "bd7d9ef55bc311d9e9c5b276cb534e38"
},
{
"dataPath": "params_shard_59.bin",
"format": "raw-shard",
"nbytes": 26542080,
"records": [
{
"name": "model.layers.19.mlp.down_proj.weight",
"shape": [
18,
5760,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 26542080,
"byteOffset": 0
}
],
"md5sum": "db4a7469a94496bee8ee68dd7aa9c148"
},
{
"dataPath": "params_shard_60.bin",
"format": "raw-shard",
"nbytes": 26558464,
"records": [
{
"name": "model.layers.19.self_attn.wqkv_pack.weight",
"shape": [
27,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 15925248,
"byteOffset": 0
},
{
"name": "model.layers.19.self_attn.wqkv_pack.bias",
"shape": [
3456
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6912,
"byteOffset": 15925248
},
{
"name": "model.layers.19.self_attn.o_proj.weight",
"shape": [
18,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10616832,
"byteOffset": 15932160
},
{
"name": "model.layers.19.self_attn.q_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26548992
},
{
"name": "model.layers.19.self_attn.k_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26549120
},
{
"name": "model.layers.19.input_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26549248
},
{
"name": "model.layers.19.post_attention_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26553856
}
],
"md5sum": "6d0fc88a3784ec33544e68fbf7f9b4f8"
},
{
"dataPath": "params_shard_61.bin",
"format": "raw-shard",
"nbytes": 53084160,
"records": [
{
"name": "model.layers.20.mlp.gate_up_proj.weight",
"shape": [
90,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 53084160,
"byteOffset": 0
}
],
"md5sum": "ba927b0c6d6760dc005757dac781d7d5"
},
{
"dataPath": "params_shard_62.bin",
"format": "raw-shard",
"nbytes": 26542080,
"records": [
{
"name": "model.layers.20.mlp.down_proj.weight",
"shape": [
18,
5760,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 26542080,
"byteOffset": 0
}
],
"md5sum": "dff9c6708c3ba41992e06e6174793a3d"
},
{
"dataPath": "params_shard_63.bin",
"format": "raw-shard",
"nbytes": 26558464,
"records": [
{
"name": "model.layers.20.self_attn.wqkv_pack.weight",
"shape": [
27,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 15925248,
"byteOffset": 0
},
{
"name": "model.layers.20.self_attn.wqkv_pack.bias",
"shape": [
3456
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6912,
"byteOffset": 15925248
},
{
"name": "model.layers.20.self_attn.o_proj.weight",
"shape": [
18,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10616832,
"byteOffset": 15932160
},
{
"name": "model.layers.20.self_attn.q_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26548992
},
{
"name": "model.layers.20.self_attn.k_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26549120
},
{
"name": "model.layers.20.input_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26549248
},
{
"name": "model.layers.20.post_attention_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26553856
}
],
"md5sum": "b3ab38d6e058abb322b3287a242ae42a"
},
{
"dataPath": "params_shard_64.bin",
"format": "raw-shard",
"nbytes": 53084160,
"records": [
{
"name": "model.layers.21.mlp.gate_up_proj.weight",
"shape": [
90,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 53084160,
"byteOffset": 0
}
],
"md5sum": "9e0d0d730dba5d0e0c90d1fd6bde988f"
},
{
"dataPath": "params_shard_65.bin",
"format": "raw-shard",
"nbytes": 26542080,
"records": [
{
"name": "model.layers.21.mlp.down_proj.weight",
"shape": [
18,
5760,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 26542080,
"byteOffset": 0
}
],
"md5sum": "629e70cd777288ab4b97d4fb91e915bb"
},
{
"dataPath": "params_shard_66.bin",
"format": "raw-shard",
"nbytes": 26558464,
"records": [
{
"name": "model.layers.21.self_attn.wqkv_pack.weight",
"shape": [
27,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 15925248,
"byteOffset": 0
},
{
"name": "model.layers.21.self_attn.wqkv_pack.bias",
"shape": [
3456
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6912,
"byteOffset": 15925248
},
{
"name": "model.layers.21.self_attn.o_proj.weight",
"shape": [
18,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10616832,
"byteOffset": 15932160
},
{
"name": "model.layers.21.self_attn.q_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26548992
},
{
"name": "model.layers.21.self_attn.k_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26549120
},
{
"name": "model.layers.21.input_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26549248
},
{
"name": "model.layers.21.post_attention_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26553856
}
],
"md5sum": "0d77eb414fb2b96cbd308e8688fb1ab2"
},
{
"dataPath": "params_shard_67.bin",
"format": "raw-shard",
"nbytes": 53084160,
"records": [
{
"name": "model.layers.22.mlp.gate_up_proj.weight",
"shape": [
90,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 53084160,
"byteOffset": 0
}
],
"md5sum": "caa575faa36289686d51457ac83fc935"
},
{
"dataPath": "params_shard_68.bin",
"format": "raw-shard",
"nbytes": 26542080,
"records": [
{
"name": "model.layers.22.mlp.down_proj.weight",
"shape": [
18,
5760,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 26542080,
"byteOffset": 0
}
],
"md5sum": "8e102a68ecfad554323dc75678b948e5"
},
{
"dataPath": "params_shard_69.bin",
"format": "raw-shard",
"nbytes": 26558464,
"records": [
{
"name": "model.layers.22.self_attn.wqkv_pack.weight",
"shape": [
27,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 15925248,
"byteOffset": 0
},
{
"name": "model.layers.22.self_attn.wqkv_pack.bias",
"shape": [
3456
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6912,
"byteOffset": 15925248
},
{
"name": "model.layers.22.self_attn.o_proj.weight",
"shape": [
18,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10616832,
"byteOffset": 15932160
},
{
"name": "model.layers.22.self_attn.q_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26548992
},
{
"name": "model.layers.22.self_attn.k_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26549120
},
{
"name": "model.layers.22.input_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26549248
},
{
"name": "model.layers.22.post_attention_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26553856
}
],
"md5sum": "483363a6a64146f8ccc79e6889f220e1"
},
{
"dataPath": "params_shard_70.bin",
"format": "raw-shard",
"nbytes": 53084160,
"records": [
{
"name": "model.layers.23.mlp.gate_up_proj.weight",
"shape": [
90,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 53084160,
"byteOffset": 0
}
],
"md5sum": "e361049c58cea5250b73b95fbf57fec1"
},
{
"dataPath": "params_shard_71.bin",
"format": "raw-shard",
"nbytes": 26542080,
"records": [
{
"name": "model.layers.23.mlp.down_proj.weight",
"shape": [
18,
5760,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 26542080,
"byteOffset": 0
}
],
"md5sum": "2a37b42f271d984c02f33986cdc546ec"
},
{
"dataPath": "params_shard_72.bin",
"format": "raw-shard",
"nbytes": 26558464,
"records": [
{
"name": "model.layers.23.self_attn.wqkv_pack.weight",
"shape": [
27,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 15925248,
"byteOffset": 0
},
{
"name": "model.layers.23.self_attn.wqkv_pack.bias",
"shape": [
3456
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6912,
"byteOffset": 15925248
},
{
"name": "model.layers.23.self_attn.o_proj.weight",
"shape": [
18,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10616832,
"byteOffset": 15932160
},
{
"name": "model.layers.23.self_attn.q_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26548992
},
{
"name": "model.layers.23.self_attn.k_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26549120
},
{
"name": "model.layers.23.input_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26549248
},
{
"name": "model.layers.23.post_attention_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26553856
}
],
"md5sum": "ae4b220a01e6371dfd63c7bf32a6d8fc"
},
{
"dataPath": "params_shard_73.bin",
"format": "raw-shard",
"nbytes": 53084160,
"records": [
{
"name": "model.layers.24.mlp.gate_up_proj.weight",
"shape": [
90,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 53084160,
"byteOffset": 0
}
],
"md5sum": "9f9be8674496ec3058a070e08850acc2"
},
{
"dataPath": "params_shard_74.bin",
"format": "raw-shard",
"nbytes": 26542080,
"records": [
{
"name": "model.layers.24.mlp.down_proj.weight",
"shape": [
18,
5760,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 26542080,
"byteOffset": 0
}
],
"md5sum": "d956b4b0518d7760c83f3687646180bf"
},
{
"dataPath": "params_shard_75.bin",
"format": "raw-shard",
"nbytes": 26558464,
"records": [
{
"name": "model.layers.24.self_attn.wqkv_pack.weight",
"shape": [
27,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 15925248,
"byteOffset": 0
},
{
"name": "model.layers.24.self_attn.wqkv_pack.bias",
"shape": [
3456
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6912,
"byteOffset": 15925248
},
{
"name": "model.layers.24.self_attn.o_proj.weight",
"shape": [
18,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10616832,
"byteOffset": 15932160
},
{
"name": "model.layers.24.self_attn.q_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26548992
},
{
"name": "model.layers.24.self_attn.k_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26549120
},
{
"name": "model.layers.24.input_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26549248
},
{
"name": "model.layers.24.post_attention_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26553856
}
],
"md5sum": "76382836c253a1a62436c762d2fcf268"
},
{
"dataPath": "params_shard_76.bin",
"format": "raw-shard",
"nbytes": 53084160,
"records": [
{
"name": "model.layers.25.mlp.gate_up_proj.weight",
"shape": [
90,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 53084160,
"byteOffset": 0
}
],
"md5sum": "d11abf7988d3cc8dd4c4ec43cb70b5fb"
},
{
"dataPath": "params_shard_77.bin",
"format": "raw-shard",
"nbytes": 26542080,
"records": [
{
"name": "model.layers.25.mlp.down_proj.weight",
"shape": [
18,
5760,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 26542080,
"byteOffset": 0
}
],
"md5sum": "eb8375d3e7a5f91881f0935703a6ac70"
},
{
"dataPath": "params_shard_78.bin",
"format": "raw-shard",
"nbytes": 26558464,
"records": [
{
"name": "model.layers.25.self_attn.wqkv_pack.weight",
"shape": [
27,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 15925248,
"byteOffset": 0
},
{
"name": "model.layers.25.self_attn.wqkv_pack.bias",
"shape": [
3456
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6912,
"byteOffset": 15925248
},
{
"name": "model.layers.25.self_attn.o_proj.weight",
"shape": [
18,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10616832,
"byteOffset": 15932160
},
{
"name": "model.layers.25.self_attn.q_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26548992
},
{
"name": "model.layers.25.self_attn.k_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26549120
},
{
"name": "model.layers.25.input_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26549248
},
{
"name": "model.layers.25.post_attention_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26553856
}
],
"md5sum": "c48ed2d90fb4a7533c8d5a43009c567a"
},
{
"dataPath": "params_shard_79.bin",
"format": "raw-shard",
"nbytes": 53084160,
"records": [
{
"name": "model.layers.26.mlp.gate_up_proj.weight",
"shape": [
90,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 53084160,
"byteOffset": 0
}
],
"md5sum": "7c77d9d534ff83575dec661b2ddacdd7"
},
{
"dataPath": "params_shard_80.bin",
"format": "raw-shard",
"nbytes": 26542080,
"records": [
{
"name": "model.layers.26.mlp.down_proj.weight",
"shape": [
18,
5760,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 26542080,
"byteOffset": 0
}
],
"md5sum": "6205311e54c1795e2fdea2e35b2e147d"
},
{
"dataPath": "params_shard_81.bin",
"format": "raw-shard",
"nbytes": 26558464,
"records": [
{
"name": "model.layers.26.self_attn.wqkv_pack.weight",
"shape": [
27,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 15925248,
"byteOffset": 0
},
{
"name": "model.layers.26.self_attn.wqkv_pack.bias",
"shape": [
3456
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6912,
"byteOffset": 15925248
},
{
"name": "model.layers.26.self_attn.o_proj.weight",
"shape": [
18,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10616832,
"byteOffset": 15932160
},
{
"name": "model.layers.26.self_attn.q_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26548992
},
{
"name": "model.layers.26.self_attn.k_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26549120
},
{
"name": "model.layers.26.input_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26549248
},
{
"name": "model.layers.26.post_attention_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26553856
}
],
"md5sum": "1072cf06f6fdb2fe4605eb6c689910bf"
},
{
"dataPath": "params_shard_82.bin",
"format": "raw-shard",
"nbytes": 53084160,
"records": [
{
"name": "model.layers.27.mlp.gate_up_proj.weight",
"shape": [
90,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 53084160,
"byteOffset": 0
}
],
"md5sum": "9e4e8b79f9daae76b5ffd834d039780e"
},
{
"dataPath": "params_shard_83.bin",
"format": "raw-shard",
"nbytes": 26542080,
"records": [
{
"name": "model.layers.27.mlp.down_proj.weight",
"shape": [
18,
5760,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 26542080,
"byteOffset": 0
}
],
"md5sum": "85909e335659878f76729604d3582607"
},
{
"dataPath": "params_shard_84.bin",
"format": "raw-shard",
"nbytes": 26558464,
"records": [
{
"name": "model.layers.27.self_attn.wqkv_pack.weight",
"shape": [
27,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 15925248,
"byteOffset": 0
},
{
"name": "model.layers.27.self_attn.wqkv_pack.bias",
"shape": [
3456
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6912,
"byteOffset": 15925248
},
{
"name": "model.layers.27.self_attn.o_proj.weight",
"shape": [
18,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10616832,
"byteOffset": 15932160
},
{
"name": "model.layers.27.self_attn.q_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26548992
},
{
"name": "model.layers.27.self_attn.k_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26549120
},
{
"name": "model.layers.27.input_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26549248
},
{
"name": "model.layers.27.post_attention_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26553856
}
],
"md5sum": "25dcc058ac7c3a40e442530d259d36c8"
},
{
"dataPath": "params_shard_85.bin",
"format": "raw-shard",
"nbytes": 53084160,
"records": [
{
"name": "model.layers.28.mlp.gate_up_proj.weight",
"shape": [
90,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 53084160,
"byteOffset": 0
}
],
"md5sum": "48f80950335a0b951dee3276ec443bf4"
},
{
"dataPath": "params_shard_86.bin",
"format": "raw-shard",
"nbytes": 26542080,
"records": [
{
"name": "model.layers.28.mlp.down_proj.weight",
"shape": [
18,
5760,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 26542080,
"byteOffset": 0
}
],
"md5sum": "98dd8e97ff619a80580894f4214b5c6a"
},
{
"dataPath": "params_shard_87.bin",
"format": "raw-shard",
"nbytes": 26558464,
"records": [
{
"name": "model.layers.28.self_attn.wqkv_pack.weight",
"shape": [
27,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 15925248,
"byteOffset": 0
},
{
"name": "model.layers.28.self_attn.wqkv_pack.bias",
"shape": [
3456
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6912,
"byteOffset": 15925248
},
{
"name": "model.layers.28.self_attn.o_proj.weight",
"shape": [
18,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10616832,
"byteOffset": 15932160
},
{
"name": "model.layers.28.self_attn.q_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26548992
},
{
"name": "model.layers.28.self_attn.k_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26549120
},
{
"name": "model.layers.28.input_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26549248
},
{
"name": "model.layers.28.post_attention_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26553856
}
],
"md5sum": "a22ec67acfe6cbcb2497dffad6a9cf4d"
},
{
"dataPath": "params_shard_88.bin",
"format": "raw-shard",
"nbytes": 53084160,
"records": [
{
"name": "model.layers.29.mlp.gate_up_proj.weight",
"shape": [
90,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 53084160,
"byteOffset": 0
}
],
"md5sum": "b16bce7494665760f4ac18f14375fa4d"
},
{
"dataPath": "params_shard_89.bin",
"format": "raw-shard",
"nbytes": 26542080,
"records": [
{
"name": "model.layers.29.mlp.down_proj.weight",
"shape": [
18,
5760,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 26542080,
"byteOffset": 0
}
],
"md5sum": "0e8fe2e5322812016be52da8f3993fe0"
},
{
"dataPath": "params_shard_90.bin",
"format": "raw-shard",
"nbytes": 26558464,
"records": [
{
"name": "model.layers.29.self_attn.wqkv_pack.weight",
"shape": [
27,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 15925248,
"byteOffset": 0
},
{
"name": "model.layers.29.self_attn.wqkv_pack.bias",
"shape": [
3456
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6912,
"byteOffset": 15925248
},
{
"name": "model.layers.29.self_attn.o_proj.weight",
"shape": [
18,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10616832,
"byteOffset": 15932160
},
{
"name": "model.layers.29.self_attn.q_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26548992
},
{
"name": "model.layers.29.self_attn.k_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26549120
},
{
"name": "model.layers.29.input_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26549248
},
{
"name": "model.layers.29.post_attention_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26553856
}
],
"md5sum": "5775462c018641678b39fa117f709b35"
},
{
"dataPath": "params_shard_91.bin",
"format": "raw-shard",
"nbytes": 53084160,
"records": [
{
"name": "model.layers.30.mlp.gate_up_proj.weight",
"shape": [
90,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 53084160,
"byteOffset": 0
}
],
"md5sum": "e5733d57f58480120e28c6224ed8b937"
},
{
"dataPath": "params_shard_92.bin",
"format": "raw-shard",
"nbytes": 26542080,
"records": [
{
"name": "model.layers.30.mlp.down_proj.weight",
"shape": [
18,
5760,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 26542080,
"byteOffset": 0
}
],
"md5sum": "67c2dc4f7671056881f425348c63ae6b"
},
{
"dataPath": "params_shard_93.bin",
"format": "raw-shard",
"nbytes": 26558464,
"records": [
{
"name": "model.layers.30.self_attn.wqkv_pack.weight",
"shape": [
27,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 15925248,
"byteOffset": 0
},
{
"name": "model.layers.30.self_attn.wqkv_pack.bias",
"shape": [
3456
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6912,
"byteOffset": 15925248
},
{
"name": "model.layers.30.self_attn.o_proj.weight",
"shape": [
18,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10616832,
"byteOffset": 15932160
},
{
"name": "model.layers.30.self_attn.q_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26548992
},
{
"name": "model.layers.30.self_attn.k_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26549120
},
{
"name": "model.layers.30.input_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26549248
},
{
"name": "model.layers.30.post_attention_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26553856
}
],
"md5sum": "57a6dc175184fda2aa35e7f0c6fd2c9f"
},
{
"dataPath": "params_shard_94.bin",
"format": "raw-shard",
"nbytes": 53084160,
"records": [
{
"name": "model.layers.31.mlp.gate_up_proj.weight",
"shape": [
90,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 53084160,
"byteOffset": 0
}
],
"md5sum": "f77dd52fc50f15add1744fc3711fdae2"
},
{
"dataPath": "params_shard_95.bin",
"format": "raw-shard",
"nbytes": 26542080,
"records": [
{
"name": "model.layers.31.mlp.down_proj.weight",
"shape": [
18,
5760,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 26542080,
"byteOffset": 0
}
],
"md5sum": "2956253c32bb4a22b0b9b9ad7a5c54b1"
},
{
"dataPath": "params_shard_96.bin",
"format": "raw-shard",
"nbytes": 26558464,
"records": [
{
"name": "model.layers.31.self_attn.wqkv_pack.weight",
"shape": [
27,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 15925248,
"byteOffset": 0
},
{
"name": "model.layers.31.self_attn.wqkv_pack.bias",
"shape": [
3456
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6912,
"byteOffset": 15925248
},
{
"name": "model.layers.31.self_attn.o_proj.weight",
"shape": [
18,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10616832,
"byteOffset": 15932160
},
{
"name": "model.layers.31.self_attn.q_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26548992
},
{
"name": "model.layers.31.self_attn.k_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26549120
},
{
"name": "model.layers.31.input_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26549248
},
{
"name": "model.layers.31.post_attention_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26553856
}
],
"md5sum": "93781e6b51b095b4587863900a1bf550"
},
{
"dataPath": "params_shard_97.bin",
"format": "raw-shard",
"nbytes": 53084160,
"records": [
{
"name": "model.layers.32.mlp.gate_up_proj.weight",
"shape": [
90,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 53084160,
"byteOffset": 0
}
],
"md5sum": "ecf71575931fe643d5e9ae291d51ef5b"
},
{
"dataPath": "params_shard_98.bin",
"format": "raw-shard",
"nbytes": 26542080,
"records": [
{
"name": "model.layers.32.mlp.down_proj.weight",
"shape": [
18,
5760,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 26542080,
"byteOffset": 0
}
],
"md5sum": "49e4ff78febf30823b75d444def9b802"
},
{
"dataPath": "params_shard_99.bin",
"format": "raw-shard",
"nbytes": 26558464,
"records": [
{
"name": "model.layers.32.self_attn.wqkv_pack.weight",
"shape": [
27,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 15925248,
"byteOffset": 0
},
{
"name": "model.layers.32.self_attn.wqkv_pack.bias",
"shape": [
3456
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6912,
"byteOffset": 15925248
},
{
"name": "model.layers.32.self_attn.o_proj.weight",
"shape": [
18,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10616832,
"byteOffset": 15932160
},
{
"name": "model.layers.32.self_attn.q_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26548992
},
{
"name": "model.layers.32.self_attn.k_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26549120
},
{
"name": "model.layers.32.input_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26549248
},
{
"name": "model.layers.32.post_attention_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26553856
}
],
"md5sum": "ec8290191b8b377aa7ef5dff6a9190c2"
},
{
"dataPath": "params_shard_100.bin",
"format": "raw-shard",
"nbytes": 53084160,
"records": [
{
"name": "model.layers.33.mlp.gate_up_proj.weight",
"shape": [
90,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 53084160,
"byteOffset": 0
}
],
"md5sum": "662098a8ed0c194ee4dac0d3d3563eb4"
},
{
"dataPath": "params_shard_101.bin",
"format": "raw-shard",
"nbytes": 26542080,
"records": [
{
"name": "model.layers.33.mlp.down_proj.weight",
"shape": [
18,
5760,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 26542080,
"byteOffset": 0
}
],
"md5sum": "f4d8921af5ba8c72eda4517a4775f1fd"
},
{
"dataPath": "params_shard_102.bin",
"format": "raw-shard",
"nbytes": 26558464,
"records": [
{
"name": "model.layers.33.self_attn.wqkv_pack.weight",
"shape": [
27,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 15925248,
"byteOffset": 0
},
{
"name": "model.layers.33.self_attn.wqkv_pack.bias",
"shape": [
3456
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6912,
"byteOffset": 15925248
},
{
"name": "model.layers.33.self_attn.o_proj.weight",
"shape": [
18,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10616832,
"byteOffset": 15932160
},
{
"name": "model.layers.33.self_attn.q_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26548992
},
{
"name": "model.layers.33.self_attn.k_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26549120
},
{
"name": "model.layers.33.input_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26549248
},
{
"name": "model.layers.33.post_attention_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26553856
}
],
"md5sum": "0fc91bfb07024cb7e52038ed0eb405e3"
},
{
"dataPath": "params_shard_103.bin",
"format": "raw-shard",
"nbytes": 53084160,
"records": [
{
"name": "model.layers.34.mlp.gate_up_proj.weight",
"shape": [
90,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 53084160,
"byteOffset": 0
}
],
"md5sum": "ee42f7e06c5e030af2e9060bec00b07e"
},
{
"dataPath": "params_shard_104.bin",
"format": "raw-shard",
"nbytes": 26542080,
"records": [
{
"name": "model.layers.34.mlp.down_proj.weight",
"shape": [
18,
5760,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 26542080,
"byteOffset": 0
}
],
"md5sum": "37851961d593aec1293af31e3863bb09"
},
{
"dataPath": "params_shard_105.bin",
"format": "raw-shard",
"nbytes": 26558464,
"records": [
{
"name": "model.layers.34.self_attn.wqkv_pack.weight",
"shape": [
27,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 15925248,
"byteOffset": 0
},
{
"name": "model.layers.34.self_attn.wqkv_pack.bias",
"shape": [
3456
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6912,
"byteOffset": 15925248
},
{
"name": "model.layers.34.self_attn.o_proj.weight",
"shape": [
18,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10616832,
"byteOffset": 15932160
},
{
"name": "model.layers.34.self_attn.q_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26548992
},
{
"name": "model.layers.34.self_attn.k_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26549120
},
{
"name": "model.layers.34.input_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26549248
},
{
"name": "model.layers.34.post_attention_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26553856
}
],
"md5sum": "fa179e7167e9987fdc8fd87a00e5b157"
},
{
"dataPath": "params_shard_106.bin",
"format": "raw-shard",
"nbytes": 53084160,
"records": [
{
"name": "model.layers.35.mlp.gate_up_proj.weight",
"shape": [
90,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 53084160,
"byteOffset": 0
}
],
"md5sum": "8110c074d89ab2450d6bdf7cbd934d5a"
},
{
"dataPath": "params_shard_107.bin",
"format": "raw-shard",
"nbytes": 26542080,
"records": [
{
"name": "model.layers.35.mlp.down_proj.weight",
"shape": [
18,
5760,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 26542080,
"byteOffset": 0
}
],
"md5sum": "a6431de1ef25b2e2002170c672027233"
},
{
"dataPath": "params_shard_108.bin",
"format": "raw-shard",
"nbytes": 26558464,
"records": [
{
"name": "model.layers.35.self_attn.wqkv_pack.weight",
"shape": [
27,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 15925248,
"byteOffset": 0
},
{
"name": "model.layers.35.self_attn.wqkv_pack.bias",
"shape": [
3456
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6912,
"byteOffset": 15925248
},
{
"name": "model.layers.35.self_attn.o_proj.weight",
"shape": [
18,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10616832,
"byteOffset": 15932160
},
{
"name": "model.layers.35.self_attn.q_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26548992
},
{
"name": "model.layers.35.self_attn.k_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26549120
},
{
"name": "model.layers.35.input_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26549248
},
{
"name": "model.layers.35.post_attention_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26553856
}
],
"md5sum": "3ace05f99fe6ee154d1f8d6932fc1e91"
},
{
"dataPath": "params_shard_109.bin",
"format": "raw-shard",
"nbytes": 53084160,
"records": [
{
"name": "model.layers.36.mlp.gate_up_proj.weight",
"shape": [
90,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 53084160,
"byteOffset": 0
}
],
"md5sum": "3427cf89f591ea7feade8973f84c88cf"
},
{
"dataPath": "params_shard_110.bin",
"format": "raw-shard",
"nbytes": 26542080,
"records": [
{
"name": "model.layers.36.mlp.down_proj.weight",
"shape": [
18,
5760,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 26542080,
"byteOffset": 0
}
],
"md5sum": "13b4c4175befdec1edcd21fc143d1144"
},
{
"dataPath": "params_shard_111.bin",
"format": "raw-shard",
"nbytes": 26558464,
"records": [
{
"name": "model.layers.36.self_attn.wqkv_pack.weight",
"shape": [
27,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 15925248,
"byteOffset": 0
},
{
"name": "model.layers.36.self_attn.wqkv_pack.bias",
"shape": [
3456
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6912,
"byteOffset": 15925248
},
{
"name": "model.layers.36.self_attn.o_proj.weight",
"shape": [
18,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10616832,
"byteOffset": 15932160
},
{
"name": "model.layers.36.self_attn.q_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26548992
},
{
"name": "model.layers.36.self_attn.k_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26549120
},
{
"name": "model.layers.36.input_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26549248
},
{
"name": "model.layers.36.post_attention_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26553856
}
],
"md5sum": "5466aa1db4c7be054f8b3621f1c4aee0"
},
{
"dataPath": "params_shard_112.bin",
"format": "raw-shard",
"nbytes": 53084160,
"records": [
{
"name": "model.layers.37.mlp.gate_up_proj.weight",
"shape": [
90,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 53084160,
"byteOffset": 0
}
],
"md5sum": "cbb4d16f02b88014d43a407746ef86a8"
},
{
"dataPath": "params_shard_113.bin",
"format": "raw-shard",
"nbytes": 26542080,
"records": [
{
"name": "model.layers.37.mlp.down_proj.weight",
"shape": [
18,
5760,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 26542080,
"byteOffset": 0
}
],
"md5sum": "620e82519973787c6337e7ce53bf67f3"
},
{
"dataPath": "params_shard_114.bin",
"format": "raw-shard",
"nbytes": 26558464,
"records": [
{
"name": "model.layers.37.self_attn.wqkv_pack.weight",
"shape": [
27,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 15925248,
"byteOffset": 0
},
{
"name": "model.layers.37.self_attn.wqkv_pack.bias",
"shape": [
3456
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6912,
"byteOffset": 15925248
},
{
"name": "model.layers.37.self_attn.o_proj.weight",
"shape": [
18,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10616832,
"byteOffset": 15932160
},
{
"name": "model.layers.37.self_attn.q_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26548992
},
{
"name": "model.layers.37.self_attn.k_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26549120
},
{
"name": "model.layers.37.input_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26549248
},
{
"name": "model.layers.37.post_attention_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26553856
}
],
"md5sum": "a6f8775657d221cd38422e5e1cac3c65"
},
{
"dataPath": "params_shard_115.bin",
"format": "raw-shard",
"nbytes": 53084160,
"records": [
{
"name": "model.layers.38.mlp.gate_up_proj.weight",
"shape": [
90,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 53084160,
"byteOffset": 0
}
],
"md5sum": "a51e4cf5ee7a46418ba61b758114a32b"
},
{
"dataPath": "params_shard_116.bin",
"format": "raw-shard",
"nbytes": 26542080,
"records": [
{
"name": "model.layers.38.mlp.down_proj.weight",
"shape": [
18,
5760,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 26542080,
"byteOffset": 0
}
],
"md5sum": "8f522f0dfb10a3b2e5aa79f71d8aa484"
},
{
"dataPath": "params_shard_117.bin",
"format": "raw-shard",
"nbytes": 26558464,
"records": [
{
"name": "model.layers.38.self_attn.wqkv_pack.weight",
"shape": [
27,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 15925248,
"byteOffset": 0
},
{
"name": "model.layers.38.self_attn.wqkv_pack.bias",
"shape": [
3456
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6912,
"byteOffset": 15925248
},
{
"name": "model.layers.38.self_attn.o_proj.weight",
"shape": [
18,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10616832,
"byteOffset": 15932160
},
{
"name": "model.layers.38.self_attn.q_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26548992
},
{
"name": "model.layers.38.self_attn.k_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26549120
},
{
"name": "model.layers.38.input_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26549248
},
{
"name": "model.layers.38.post_attention_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26553856
}
],
"md5sum": "41a67979340df891bf9d7654eca90dd2"
},
{
"dataPath": "params_shard_118.bin",
"format": "raw-shard",
"nbytes": 53084160,
"records": [
{
"name": "model.layers.39.mlp.gate_up_proj.weight",
"shape": [
90,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 53084160,
"byteOffset": 0
}
],
"md5sum": "98de39d715ce5fe46b8262fc8737672f"
},
{
"dataPath": "params_shard_119.bin",
"format": "raw-shard",
"nbytes": 26542080,
"records": [
{
"name": "model.layers.39.mlp.down_proj.weight",
"shape": [
18,
5760,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 26542080,
"byteOffset": 0
}
],
"md5sum": "72f407b7352d86cd3c8b8bb6ca55366a"
},
{
"dataPath": "params_shard_120.bin",
"format": "raw-shard",
"nbytes": 26558464,
"records": [
{
"name": "model.layers.39.self_attn.wqkv_pack.weight",
"shape": [
27,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 15925248,
"byteOffset": 0
},
{
"name": "model.layers.39.self_attn.wqkv_pack.bias",
"shape": [
3456
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6912,
"byteOffset": 15925248
},
{
"name": "model.layers.39.self_attn.o_proj.weight",
"shape": [
18,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10616832,
"byteOffset": 15932160
},
{
"name": "model.layers.39.self_attn.q_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26548992
},
{
"name": "model.layers.39.self_attn.k_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26549120
},
{
"name": "model.layers.39.input_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26549248
},
{
"name": "model.layers.39.post_attention_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26553856
}
],
"md5sum": "b741247f0f11e3e0da10d831ab3a7487"
},
{
"dataPath": "params_shard_121.bin",
"format": "raw-shard",
"nbytes": 53084160,
"records": [
{
"name": "model.layers.40.mlp.gate_up_proj.weight",
"shape": [
90,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 53084160,
"byteOffset": 0
}
],
"md5sum": "ee47ffabcc4a80eb7fc825d510220e9b"
},
{
"dataPath": "params_shard_122.bin",
"format": "raw-shard",
"nbytes": 26542080,
"records": [
{
"name": "model.layers.40.mlp.down_proj.weight",
"shape": [
18,
5760,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 26542080,
"byteOffset": 0
}
],
"md5sum": "03d7934168188df230bd36ec838b97c2"
},
{
"dataPath": "params_shard_123.bin",
"format": "raw-shard",
"nbytes": 26558464,
"records": [
{
"name": "model.layers.40.self_attn.wqkv_pack.weight",
"shape": [
27,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 15925248,
"byteOffset": 0
},
{
"name": "model.layers.40.self_attn.wqkv_pack.bias",
"shape": [
3456
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6912,
"byteOffset": 15925248
},
{
"name": "model.layers.40.self_attn.o_proj.weight",
"shape": [
18,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10616832,
"byteOffset": 15932160
},
{
"name": "model.layers.40.self_attn.q_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26548992
},
{
"name": "model.layers.40.self_attn.k_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26549120
},
{
"name": "model.layers.40.input_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26549248
},
{
"name": "model.layers.40.post_attention_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26553856
}
],
"md5sum": "93e73f3e143079a89115d91c26a7dc63"
},
{
"dataPath": "params_shard_124.bin",
"format": "raw-shard",
"nbytes": 53084160,
"records": [
{
"name": "model.layers.41.mlp.gate_up_proj.weight",
"shape": [
90,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 53084160,
"byteOffset": 0
}
],
"md5sum": "296836b587a32c2582502a2b37c75ac6"
},
{
"dataPath": "params_shard_125.bin",
"format": "raw-shard",
"nbytes": 26542080,
"records": [
{
"name": "model.layers.41.mlp.down_proj.weight",
"shape": [
18,
5760,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 26542080,
"byteOffset": 0
}
],
"md5sum": "721d7b768fa1a9bf27810fb8b5052f63"
},
{
"dataPath": "params_shard_126.bin",
"format": "raw-shard",
"nbytes": 26558464,
"records": [
{
"name": "model.layers.41.self_attn.wqkv_pack.weight",
"shape": [
27,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 15925248,
"byteOffset": 0
},
{
"name": "model.layers.41.self_attn.wqkv_pack.bias",
"shape": [
3456
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6912,
"byteOffset": 15925248
},
{
"name": "model.layers.41.self_attn.o_proj.weight",
"shape": [
18,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10616832,
"byteOffset": 15932160
},
{
"name": "model.layers.41.self_attn.q_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26548992
},
{
"name": "model.layers.41.self_attn.k_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26549120
},
{
"name": "model.layers.41.input_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26549248
},
{
"name": "model.layers.41.post_attention_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26553856
}
],
"md5sum": "86885fe73453642a44f1d631736dd1a8"
},
{
"dataPath": "params_shard_127.bin",
"format": "raw-shard",
"nbytes": 53084160,
"records": [
{
"name": "model.layers.42.mlp.gate_up_proj.weight",
"shape": [
90,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 53084160,
"byteOffset": 0
}
],
"md5sum": "da0257f208c1ada5e05a1cf5f2f6c5d6"
},
{
"dataPath": "params_shard_128.bin",
"format": "raw-shard",
"nbytes": 26542080,
"records": [
{
"name": "model.layers.42.mlp.down_proj.weight",
"shape": [
18,
5760,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 26542080,
"byteOffset": 0
}
],
"md5sum": "baf61197f1557e2e1ff37bcf380b6610"
},
{
"dataPath": "params_shard_129.bin",
"format": "raw-shard",
"nbytes": 26558464,
"records": [
{
"name": "model.layers.42.self_attn.wqkv_pack.weight",
"shape": [
27,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 15925248,
"byteOffset": 0
},
{
"name": "model.layers.42.self_attn.wqkv_pack.bias",
"shape": [
3456
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6912,
"byteOffset": 15925248
},
{
"name": "model.layers.42.self_attn.o_proj.weight",
"shape": [
18,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10616832,
"byteOffset": 15932160
},
{
"name": "model.layers.42.self_attn.q_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26548992
},
{
"name": "model.layers.42.self_attn.k_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26549120
},
{
"name": "model.layers.42.input_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26549248
},
{
"name": "model.layers.42.post_attention_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26553856
}
],
"md5sum": "d007a7f9f4fad954b41f286436cb1a97"
},
{
"dataPath": "params_shard_130.bin",
"format": "raw-shard",
"nbytes": 53084160,
"records": [
{
"name": "model.layers.43.mlp.gate_up_proj.weight",
"shape": [
90,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 53084160,
"byteOffset": 0
}
],
"md5sum": "9a524cfec5855788648c9244f4da2b9f"
},
{
"dataPath": "params_shard_131.bin",
"format": "raw-shard",
"nbytes": 26542080,
"records": [
{
"name": "model.layers.43.mlp.down_proj.weight",
"shape": [
18,
5760,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 26542080,
"byteOffset": 0
}
],
"md5sum": "260b68dfa238b509251c22d8d08192c6"
},
{
"dataPath": "params_shard_132.bin",
"format": "raw-shard",
"nbytes": 26558464,
"records": [
{
"name": "model.layers.43.self_attn.wqkv_pack.weight",
"shape": [
27,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 15925248,
"byteOffset": 0
},
{
"name": "model.layers.43.self_attn.wqkv_pack.bias",
"shape": [
3456
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6912,
"byteOffset": 15925248
},
{
"name": "model.layers.43.self_attn.o_proj.weight",
"shape": [
18,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10616832,
"byteOffset": 15932160
},
{
"name": "model.layers.43.self_attn.q_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26548992
},
{
"name": "model.layers.43.self_attn.k_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26549120
},
{
"name": "model.layers.43.input_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26549248
},
{
"name": "model.layers.43.post_attention_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26553856
}
],
"md5sum": "50c9fd65189fb634ebaa2e4a5d2ef0e2"
},
{
"dataPath": "params_shard_133.bin",
"format": "raw-shard",
"nbytes": 53084160,
"records": [
{
"name": "model.layers.44.mlp.gate_up_proj.weight",
"shape": [
90,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 53084160,
"byteOffset": 0
}
],
"md5sum": "124e4ce41ca518c5bb5dbeed5f075e51"
},
{
"dataPath": "params_shard_134.bin",
"format": "raw-shard",
"nbytes": 26542080,
"records": [
{
"name": "model.layers.44.mlp.down_proj.weight",
"shape": [
18,
5760,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 26542080,
"byteOffset": 0
}
],
"md5sum": "115fb369207d68ab23324e4192dc8896"
},
{
"dataPath": "params_shard_135.bin",
"format": "raw-shard",
"nbytes": 26558464,
"records": [
{
"name": "model.layers.44.self_attn.wqkv_pack.weight",
"shape": [
27,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 15925248,
"byteOffset": 0
},
{
"name": "model.layers.44.self_attn.wqkv_pack.bias",
"shape": [
3456
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6912,
"byteOffset": 15925248
},
{
"name": "model.layers.44.self_attn.o_proj.weight",
"shape": [
18,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10616832,
"byteOffset": 15932160
},
{
"name": "model.layers.44.self_attn.q_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26548992
},
{
"name": "model.layers.44.self_attn.k_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26549120
},
{
"name": "model.layers.44.input_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26549248
},
{
"name": "model.layers.44.post_attention_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26553856
}
],
"md5sum": "291e158a175f78ec536af06e9f53580f"
},
{
"dataPath": "params_shard_136.bin",
"format": "raw-shard",
"nbytes": 53084160,
"records": [
{
"name": "model.layers.45.mlp.gate_up_proj.weight",
"shape": [
90,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 53084160,
"byteOffset": 0
}
],
"md5sum": "47b5ebed20a02f2b00fe7d8a38bb2c32"
},
{
"dataPath": "params_shard_137.bin",
"format": "raw-shard",
"nbytes": 26542080,
"records": [
{
"name": "model.layers.45.mlp.down_proj.weight",
"shape": [
18,
5760,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 26542080,
"byteOffset": 0
}
],
"md5sum": "5c9d8122da6125a203abe3af80aeaaa3"
},
{
"dataPath": "params_shard_138.bin",
"format": "raw-shard",
"nbytes": 26558464,
"records": [
{
"name": "model.layers.45.self_attn.wqkv_pack.weight",
"shape": [
27,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 15925248,
"byteOffset": 0
},
{
"name": "model.layers.45.self_attn.wqkv_pack.bias",
"shape": [
3456
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6912,
"byteOffset": 15925248
},
{
"name": "model.layers.45.self_attn.o_proj.weight",
"shape": [
18,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10616832,
"byteOffset": 15932160
},
{
"name": "model.layers.45.self_attn.q_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26548992
},
{
"name": "model.layers.45.self_attn.k_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26549120
},
{
"name": "model.layers.45.input_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26549248
},
{
"name": "model.layers.45.post_attention_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26553856
}
],
"md5sum": "53a2e8c6d0112f6418300e5a01d9c1b5"
},
{
"dataPath": "params_shard_139.bin",
"format": "raw-shard",
"nbytes": 53084160,
"records": [
{
"name": "model.layers.46.mlp.gate_up_proj.weight",
"shape": [
90,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 53084160,
"byteOffset": 0
}
],
"md5sum": "b6ad6ec0b6eddc529e1bfffd87de49d4"
},
{
"dataPath": "params_shard_140.bin",
"format": "raw-shard",
"nbytes": 26542080,
"records": [
{
"name": "model.layers.46.mlp.down_proj.weight",
"shape": [
18,
5760,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 26542080,
"byteOffset": 0
}
],
"md5sum": "f1044e16390c33bf62e7344080c223ef"
},
{
"dataPath": "params_shard_141.bin",
"format": "raw-shard",
"nbytes": 26558464,
"records": [
{
"name": "model.layers.46.self_attn.wqkv_pack.weight",
"shape": [
27,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 15925248,
"byteOffset": 0
},
{
"name": "model.layers.46.self_attn.wqkv_pack.bias",
"shape": [
3456
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6912,
"byteOffset": 15925248
},
{
"name": "model.layers.46.self_attn.o_proj.weight",
"shape": [
18,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10616832,
"byteOffset": 15932160
},
{
"name": "model.layers.46.self_attn.q_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26548992
},
{
"name": "model.layers.46.self_attn.k_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26549120
},
{
"name": "model.layers.46.input_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26549248
},
{
"name": "model.layers.46.post_attention_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26553856
}
],
"md5sum": "9b498f275ebaa2c5805e54afc9c1448f"
},
{
"dataPath": "params_shard_142.bin",
"format": "raw-shard",
"nbytes": 53084160,
"records": [
{
"name": "model.layers.47.mlp.gate_up_proj.weight",
"shape": [
90,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 53084160,
"byteOffset": 0
}
],
"md5sum": "b170ef009f14a8f1b766c1f1a468e6be"
},
{
"dataPath": "params_shard_143.bin",
"format": "raw-shard",
"nbytes": 26542080,
"records": [
{
"name": "model.layers.47.mlp.down_proj.weight",
"shape": [
18,
5760,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 26542080,
"byteOffset": 0
}
],
"md5sum": "8252517b14a26d59c30b4b3ba349c96b"
},
{
"dataPath": "params_shard_144.bin",
"format": "raw-shard",
"nbytes": 26558464,
"records": [
{
"name": "model.layers.47.self_attn.wqkv_pack.weight",
"shape": [
27,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 15925248,
"byteOffset": 0
},
{
"name": "model.layers.47.self_attn.wqkv_pack.bias",
"shape": [
3456
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6912,
"byteOffset": 15925248
},
{
"name": "model.layers.47.self_attn.o_proj.weight",
"shape": [
18,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10616832,
"byteOffset": 15932160
},
{
"name": "model.layers.47.self_attn.q_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26548992
},
{
"name": "model.layers.47.self_attn.k_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26549120
},
{
"name": "model.layers.47.input_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26549248
},
{
"name": "model.layers.47.post_attention_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26553856
}
],
"md5sum": "4559d757f6b5276049b05089d86ae3c4"
},
{
"dataPath": "params_shard_145.bin",
"format": "raw-shard",
"nbytes": 53084160,
"records": [
{
"name": "model.layers.48.mlp.gate_up_proj.weight",
"shape": [
90,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 53084160,
"byteOffset": 0
}
],
"md5sum": "3935be25181b4b90108ab92fe7f3c78e"
},
{
"dataPath": "params_shard_146.bin",
"format": "raw-shard",
"nbytes": 26542080,
"records": [
{
"name": "model.layers.48.mlp.down_proj.weight",
"shape": [
18,
5760,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 26542080,
"byteOffset": 0
}
],
"md5sum": "fbec991e910c60b08321a536c87e6fe5"
},
{
"dataPath": "params_shard_147.bin",
"format": "raw-shard",
"nbytes": 26558464,
"records": [
{
"name": "model.layers.48.self_attn.wqkv_pack.weight",
"shape": [
27,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 15925248,
"byteOffset": 0
},
{
"name": "model.layers.48.self_attn.wqkv_pack.bias",
"shape": [
3456
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6912,
"byteOffset": 15925248
},
{
"name": "model.layers.48.self_attn.o_proj.weight",
"shape": [
18,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10616832,
"byteOffset": 15932160
},
{
"name": "model.layers.48.self_attn.q_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26548992
},
{
"name": "model.layers.48.self_attn.k_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26549120
},
{
"name": "model.layers.48.input_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26549248
},
{
"name": "model.layers.48.post_attention_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26553856
}
],
"md5sum": "fc3fbbce684689189c9250c49c52a85b"
},
{
"dataPath": "params_shard_148.bin",
"format": "raw-shard",
"nbytes": 53084160,
"records": [
{
"name": "model.layers.49.mlp.gate_up_proj.weight",
"shape": [
90,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 53084160,
"byteOffset": 0
}
],
"md5sum": "2fd359033db9141df631b383579ecbb2"
},
{
"dataPath": "params_shard_149.bin",
"format": "raw-shard",
"nbytes": 26542080,
"records": [
{
"name": "model.layers.49.mlp.down_proj.weight",
"shape": [
18,
5760,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 26542080,
"byteOffset": 0
}
],
"md5sum": "c100ce1397c81c53ad414bbd58f24021"
},
{
"dataPath": "params_shard_150.bin",
"format": "raw-shard",
"nbytes": 26558464,
"records": [
{
"name": "model.layers.49.self_attn.wqkv_pack.weight",
"shape": [
27,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 15925248,
"byteOffset": 0
},
{
"name": "model.layers.49.self_attn.wqkv_pack.bias",
"shape": [
3456
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6912,
"byteOffset": 15925248
},
{
"name": "model.layers.49.self_attn.o_proj.weight",
"shape": [
18,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10616832,
"byteOffset": 15932160
},
{
"name": "model.layers.49.self_attn.q_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26548992
},
{
"name": "model.layers.49.self_attn.k_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26549120
},
{
"name": "model.layers.49.input_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26549248
},
{
"name": "model.layers.49.post_attention_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26553856
}
],
"md5sum": "32ca1d09ab0ea105c0a5158a4e8a6779"
},
{
"dataPath": "params_shard_151.bin",
"format": "raw-shard",
"nbytes": 53084160,
"records": [
{
"name": "model.layers.50.mlp.gate_up_proj.weight",
"shape": [
90,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 53084160,
"byteOffset": 0
}
],
"md5sum": "f8cfb4a137ce8f6f9d5bb9079407cbf9"
},
{
"dataPath": "params_shard_152.bin",
"format": "raw-shard",
"nbytes": 26542080,
"records": [
{
"name": "model.layers.50.mlp.down_proj.weight",
"shape": [
18,
5760,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 26542080,
"byteOffset": 0
}
],
"md5sum": "697e789cdd6f7bdabed3dace30605517"
},
{
"dataPath": "params_shard_153.bin",
"format": "raw-shard",
"nbytes": 26558464,
"records": [
{
"name": "model.layers.50.self_attn.wqkv_pack.weight",
"shape": [
27,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 15925248,
"byteOffset": 0
},
{
"name": "model.layers.50.self_attn.wqkv_pack.bias",
"shape": [
3456
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6912,
"byteOffset": 15925248
},
{
"name": "model.layers.50.self_attn.o_proj.weight",
"shape": [
18,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10616832,
"byteOffset": 15932160
},
{
"name": "model.layers.50.self_attn.q_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26548992
},
{
"name": "model.layers.50.self_attn.k_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26549120
},
{
"name": "model.layers.50.input_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26549248
},
{
"name": "model.layers.50.post_attention_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26553856
}
],
"md5sum": "10d9295ec0d7bc093668831769b084a3"
},
{
"dataPath": "params_shard_154.bin",
"format": "raw-shard",
"nbytes": 53084160,
"records": [
{
"name": "model.layers.51.mlp.gate_up_proj.weight",
"shape": [
90,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 53084160,
"byteOffset": 0
}
],
"md5sum": "81d3fe0c19ffabbac405c1d5f4a2463f"
},
{
"dataPath": "params_shard_155.bin",
"format": "raw-shard",
"nbytes": 26542080,
"records": [
{
"name": "model.layers.51.mlp.down_proj.weight",
"shape": [
18,
5760,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 26542080,
"byteOffset": 0
}
],
"md5sum": "283392b9a27feb8c4b902ad7debd6d97"
},
{
"dataPath": "params_shard_156.bin",
"format": "raw-shard",
"nbytes": 26563072,
"records": [
{
"name": "model.layers.51.self_attn.wqkv_pack.weight",
"shape": [
27,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 15925248,
"byteOffset": 0
},
{
"name": "model.layers.51.self_attn.wqkv_pack.bias",
"shape": [
3456
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6912,
"byteOffset": 15925248
},
{
"name": "model.layers.51.self_attn.o_proj.weight",
"shape": [
18,
2304,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10616832,
"byteOffset": 15932160
},
{
"name": "model.layers.51.self_attn.q_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26548992
},
{
"name": "model.layers.51.self_attn.k_norm.weight",
"shape": [
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 128,
"byteOffset": 26549120
},
{
"name": "model.layers.51.input_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26549248
},
{
"name": "model.layers.51.post_attention_layernorm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26553856
},
{
"name": "model.norm.weight",
"shape": [
2304
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4608,
"byteOffset": 26558464
}
],
"md5sum": "194e5d4075ab2782d9479bc1df591928"
}
]
}