reach-vb's picture
reach-vb HF staff
Upload folder using huggingface_hub
e657a80 verified
raw
history blame contribute delete
No virus
78.2 kB
{
"metadata": {
"ParamSize": 194,
"ParamBytes": 1447284480.0,
"BitsPerParam": 32.0
},
"records": [
{
"dataPath": "params_shard_0.bin",
"format": "raw-shard",
"nbytes": 94371840,
"records": [
{
"name": "model.embed_tokens.weight",
"shape": [
49152,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 94371840,
"byteOffset": 0
}
],
"md5sum": "8ced7786f9085966ac77c426e20daac7"
},
{
"dataPath": "params_shard_1.bin",
"format": "raw-shard",
"nbytes": 24581760,
"records": [
{
"name": "model.layers.0.input_layernorm.weight",
"shape": [
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1920,
"byteOffset": 0
},
{
"name": "model.layers.0.mlp.down_proj.weight",
"shape": [
960,
2560
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 1920
},
{
"name": "model.layers.0.mlp.gate_up_proj.weight",
"shape": [
5120,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 9830400,
"byteOffset": 4917120
},
{
"name": "model.layers.0.post_attention_layernorm.weight",
"shape": [
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1920,
"byteOffset": 14747520
},
{
"name": "model.layers.0.self_attn.qkv_proj.weight",
"shape": [
1600,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 3072000,
"byteOffset": 14749440
},
{
"name": "model.layers.0.self_attn.o_proj.weight",
"shape": [
960,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1843200,
"byteOffset": 17821440
},
{
"name": "model.layers.1.input_layernorm.weight",
"shape": [
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1920,
"byteOffset": 19664640
},
{
"name": "model.layers.1.mlp.down_proj.weight",
"shape": [
960,
2560
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 19666560
}
],
"md5sum": "b88130dcd5663a7235047cd985eb3bf3"
},
{
"dataPath": "params_shard_2.bin",
"format": "raw-shard",
"nbytes": 32568960,
"records": [
{
"name": "model.layers.1.mlp.gate_up_proj.weight",
"shape": [
5120,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 9830400,
"byteOffset": 0
},
{
"name": "model.layers.1.post_attention_layernorm.weight",
"shape": [
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1920,
"byteOffset": 9830400
},
{
"name": "model.layers.1.self_attn.qkv_proj.weight",
"shape": [
1600,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 3072000,
"byteOffset": 9832320
},
{
"name": "model.layers.1.self_attn.o_proj.weight",
"shape": [
960,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1843200,
"byteOffset": 12904320
},
{
"name": "model.layers.10.input_layernorm.weight",
"shape": [
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1920,
"byteOffset": 14747520
},
{
"name": "model.layers.10.mlp.down_proj.weight",
"shape": [
960,
2560
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 14749440
},
{
"name": "model.layers.10.mlp.gate_up_proj.weight",
"shape": [
5120,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 9830400,
"byteOffset": 19664640
},
{
"name": "model.layers.10.post_attention_layernorm.weight",
"shape": [
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1920,
"byteOffset": 29495040
},
{
"name": "model.layers.10.self_attn.qkv_proj.weight",
"shape": [
1600,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 3072000,
"byteOffset": 29496960
}
],
"md5sum": "a6ee7a4cc595bd687b98259a333a4b4d"
},
{
"dataPath": "params_shard_3.bin",
"format": "raw-shard",
"nbytes": 26424960,
"records": [
{
"name": "model.layers.10.self_attn.o_proj.weight",
"shape": [
960,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1843200,
"byteOffset": 0
},
{
"name": "model.layers.11.input_layernorm.weight",
"shape": [
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1920,
"byteOffset": 1843200
},
{
"name": "model.layers.11.mlp.down_proj.weight",
"shape": [
960,
2560
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 1845120
},
{
"name": "model.layers.11.mlp.gate_up_proj.weight",
"shape": [
5120,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 9830400,
"byteOffset": 6760320
},
{
"name": "model.layers.11.post_attention_layernorm.weight",
"shape": [
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1920,
"byteOffset": 16590720
},
{
"name": "model.layers.11.self_attn.qkv_proj.weight",
"shape": [
1600,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 3072000,
"byteOffset": 16592640
},
{
"name": "model.layers.11.self_attn.o_proj.weight",
"shape": [
960,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1843200,
"byteOffset": 19664640
},
{
"name": "model.layers.12.input_layernorm.weight",
"shape": [
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1920,
"byteOffset": 21507840
},
{
"name": "model.layers.12.mlp.down_proj.weight",
"shape": [
960,
2560
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 21509760
}
],
"md5sum": "fd536728c17a9fd856a3e896ceb2e8fd"
},
{
"dataPath": "params_shard_4.bin",
"format": "raw-shard",
"nbytes": 32568960,
"records": [
{
"name": "model.layers.12.mlp.gate_up_proj.weight",
"shape": [
5120,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 9830400,
"byteOffset": 0
},
{
"name": "model.layers.12.post_attention_layernorm.weight",
"shape": [
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1920,
"byteOffset": 9830400
},
{
"name": "model.layers.12.self_attn.qkv_proj.weight",
"shape": [
1600,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 3072000,
"byteOffset": 9832320
},
{
"name": "model.layers.12.self_attn.o_proj.weight",
"shape": [
960,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1843200,
"byteOffset": 12904320
},
{
"name": "model.layers.13.input_layernorm.weight",
"shape": [
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1920,
"byteOffset": 14747520
},
{
"name": "model.layers.13.mlp.down_proj.weight",
"shape": [
960,
2560
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 14749440
},
{
"name": "model.layers.13.mlp.gate_up_proj.weight",
"shape": [
5120,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 9830400,
"byteOffset": 19664640
},
{
"name": "model.layers.13.post_attention_layernorm.weight",
"shape": [
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1920,
"byteOffset": 29495040
},
{
"name": "model.layers.13.self_attn.qkv_proj.weight",
"shape": [
1600,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 3072000,
"byteOffset": 29496960
}
],
"md5sum": "be31bda70c67df8e7155923b8d1ee50f"
},
{
"dataPath": "params_shard_5.bin",
"format": "raw-shard",
"nbytes": 26424960,
"records": [
{
"name": "model.layers.13.self_attn.o_proj.weight",
"shape": [
960,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1843200,
"byteOffset": 0
},
{
"name": "model.layers.14.input_layernorm.weight",
"shape": [
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1920,
"byteOffset": 1843200
},
{
"name": "model.layers.14.mlp.down_proj.weight",
"shape": [
960,
2560
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 1845120
},
{
"name": "model.layers.14.mlp.gate_up_proj.weight",
"shape": [
5120,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 9830400,
"byteOffset": 6760320
},
{
"name": "model.layers.14.post_attention_layernorm.weight",
"shape": [
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1920,
"byteOffset": 16590720
},
{
"name": "model.layers.14.self_attn.qkv_proj.weight",
"shape": [
1600,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 3072000,
"byteOffset": 16592640
},
{
"name": "model.layers.14.self_attn.o_proj.weight",
"shape": [
960,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1843200,
"byteOffset": 19664640
},
{
"name": "model.layers.15.input_layernorm.weight",
"shape": [
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1920,
"byteOffset": 21507840
},
{
"name": "model.layers.15.mlp.down_proj.weight",
"shape": [
960,
2560
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 21509760
}
],
"md5sum": "659c9397f5347a18e4d599b2e391ff5b"
},
{
"dataPath": "params_shard_6.bin",
"format": "raw-shard",
"nbytes": 32568960,
"records": [
{
"name": "model.layers.15.mlp.gate_up_proj.weight",
"shape": [
5120,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 9830400,
"byteOffset": 0
},
{
"name": "model.layers.15.post_attention_layernorm.weight",
"shape": [
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1920,
"byteOffset": 9830400
},
{
"name": "model.layers.15.self_attn.qkv_proj.weight",
"shape": [
1600,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 3072000,
"byteOffset": 9832320
},
{
"name": "model.layers.15.self_attn.o_proj.weight",
"shape": [
960,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1843200,
"byteOffset": 12904320
},
{
"name": "model.layers.16.input_layernorm.weight",
"shape": [
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1920,
"byteOffset": 14747520
},
{
"name": "model.layers.16.mlp.down_proj.weight",
"shape": [
960,
2560
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 14749440
},
{
"name": "model.layers.16.mlp.gate_up_proj.weight",
"shape": [
5120,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 9830400,
"byteOffset": 19664640
},
{
"name": "model.layers.16.post_attention_layernorm.weight",
"shape": [
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1920,
"byteOffset": 29495040
},
{
"name": "model.layers.16.self_attn.qkv_proj.weight",
"shape": [
1600,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 3072000,
"byteOffset": 29496960
}
],
"md5sum": "74a7f4f9b0c5ef2859fed22a919295c5"
},
{
"dataPath": "params_shard_7.bin",
"format": "raw-shard",
"nbytes": 26424960,
"records": [
{
"name": "model.layers.16.self_attn.o_proj.weight",
"shape": [
960,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1843200,
"byteOffset": 0
},
{
"name": "model.layers.17.input_layernorm.weight",
"shape": [
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1920,
"byteOffset": 1843200
},
{
"name": "model.layers.17.mlp.down_proj.weight",
"shape": [
960,
2560
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 1845120
},
{
"name": "model.layers.17.mlp.gate_up_proj.weight",
"shape": [
5120,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 9830400,
"byteOffset": 6760320
},
{
"name": "model.layers.17.post_attention_layernorm.weight",
"shape": [
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1920,
"byteOffset": 16590720
},
{
"name": "model.layers.17.self_attn.qkv_proj.weight",
"shape": [
1600,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 3072000,
"byteOffset": 16592640
},
{
"name": "model.layers.17.self_attn.o_proj.weight",
"shape": [
960,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1843200,
"byteOffset": 19664640
},
{
"name": "model.layers.18.input_layernorm.weight",
"shape": [
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1920,
"byteOffset": 21507840
},
{
"name": "model.layers.18.mlp.down_proj.weight",
"shape": [
960,
2560
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 21509760
}
],
"md5sum": "17cebaa0894919f379b2c6be4898ee3a"
},
{
"dataPath": "params_shard_8.bin",
"format": "raw-shard",
"nbytes": 32568960,
"records": [
{
"name": "model.layers.18.mlp.gate_up_proj.weight",
"shape": [
5120,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 9830400,
"byteOffset": 0
},
{
"name": "model.layers.18.post_attention_layernorm.weight",
"shape": [
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1920,
"byteOffset": 9830400
},
{
"name": "model.layers.18.self_attn.qkv_proj.weight",
"shape": [
1600,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 3072000,
"byteOffset": 9832320
},
{
"name": "model.layers.18.self_attn.o_proj.weight",
"shape": [
960,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1843200,
"byteOffset": 12904320
},
{
"name": "model.layers.19.input_layernorm.weight",
"shape": [
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1920,
"byteOffset": 14747520
},
{
"name": "model.layers.19.mlp.down_proj.weight",
"shape": [
960,
2560
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 14749440
},
{
"name": "model.layers.19.mlp.gate_up_proj.weight",
"shape": [
5120,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 9830400,
"byteOffset": 19664640
},
{
"name": "model.layers.19.post_attention_layernorm.weight",
"shape": [
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1920,
"byteOffset": 29495040
},
{
"name": "model.layers.19.self_attn.qkv_proj.weight",
"shape": [
1600,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 3072000,
"byteOffset": 29496960
}
],
"md5sum": "3f0f3089689cc0f5131d402863cddb5a"
},
{
"dataPath": "params_shard_9.bin",
"format": "raw-shard",
"nbytes": 26424960,
"records": [
{
"name": "model.layers.19.self_attn.o_proj.weight",
"shape": [
960,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1843200,
"byteOffset": 0
},
{
"name": "model.layers.2.input_layernorm.weight",
"shape": [
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1920,
"byteOffset": 1843200
},
{
"name": "model.layers.2.mlp.down_proj.weight",
"shape": [
960,
2560
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 1845120
},
{
"name": "model.layers.2.mlp.gate_up_proj.weight",
"shape": [
5120,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 9830400,
"byteOffset": 6760320
},
{
"name": "model.layers.2.post_attention_layernorm.weight",
"shape": [
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1920,
"byteOffset": 16590720
},
{
"name": "model.layers.2.self_attn.qkv_proj.weight",
"shape": [
1600,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 3072000,
"byteOffset": 16592640
},
{
"name": "model.layers.2.self_attn.o_proj.weight",
"shape": [
960,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1843200,
"byteOffset": 19664640
},
{
"name": "model.layers.20.input_layernorm.weight",
"shape": [
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1920,
"byteOffset": 21507840
},
{
"name": "model.layers.20.mlp.down_proj.weight",
"shape": [
960,
2560
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 21509760
}
],
"md5sum": "bb9220e1bfb78af00076175c7ac31465"
},
{
"dataPath": "params_shard_10.bin",
"format": "raw-shard",
"nbytes": 32568960,
"records": [
{
"name": "model.layers.20.mlp.gate_up_proj.weight",
"shape": [
5120,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 9830400,
"byteOffset": 0
},
{
"name": "model.layers.20.post_attention_layernorm.weight",
"shape": [
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1920,
"byteOffset": 9830400
},
{
"name": "model.layers.20.self_attn.qkv_proj.weight",
"shape": [
1600,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 3072000,
"byteOffset": 9832320
},
{
"name": "model.layers.20.self_attn.o_proj.weight",
"shape": [
960,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1843200,
"byteOffset": 12904320
},
{
"name": "model.layers.21.input_layernorm.weight",
"shape": [
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1920,
"byteOffset": 14747520
},
{
"name": "model.layers.21.mlp.down_proj.weight",
"shape": [
960,
2560
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 14749440
},
{
"name": "model.layers.21.mlp.gate_up_proj.weight",
"shape": [
5120,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 9830400,
"byteOffset": 19664640
},
{
"name": "model.layers.21.post_attention_layernorm.weight",
"shape": [
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1920,
"byteOffset": 29495040
},
{
"name": "model.layers.21.self_attn.qkv_proj.weight",
"shape": [
1600,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 3072000,
"byteOffset": 29496960
}
],
"md5sum": "ce886adac6977eccb241937e18816fa2"
},
{
"dataPath": "params_shard_11.bin",
"format": "raw-shard",
"nbytes": 26424960,
"records": [
{
"name": "model.layers.21.self_attn.o_proj.weight",
"shape": [
960,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1843200,
"byteOffset": 0
},
{
"name": "model.layers.22.input_layernorm.weight",
"shape": [
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1920,
"byteOffset": 1843200
},
{
"name": "model.layers.22.mlp.down_proj.weight",
"shape": [
960,
2560
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 1845120
},
{
"name": "model.layers.22.mlp.gate_up_proj.weight",
"shape": [
5120,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 9830400,
"byteOffset": 6760320
},
{
"name": "model.layers.22.post_attention_layernorm.weight",
"shape": [
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1920,
"byteOffset": 16590720
},
{
"name": "model.layers.22.self_attn.qkv_proj.weight",
"shape": [
1600,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 3072000,
"byteOffset": 16592640
},
{
"name": "model.layers.22.self_attn.o_proj.weight",
"shape": [
960,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1843200,
"byteOffset": 19664640
},
{
"name": "model.layers.23.input_layernorm.weight",
"shape": [
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1920,
"byteOffset": 21507840
},
{
"name": "model.layers.23.mlp.down_proj.weight",
"shape": [
960,
2560
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 21509760
}
],
"md5sum": "11f8d7d14424815b3b4b0c3f5e6a9d7d"
},
{
"dataPath": "params_shard_12.bin",
"format": "raw-shard",
"nbytes": 32568960,
"records": [
{
"name": "model.layers.23.mlp.gate_up_proj.weight",
"shape": [
5120,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 9830400,
"byteOffset": 0
},
{
"name": "model.layers.23.post_attention_layernorm.weight",
"shape": [
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1920,
"byteOffset": 9830400
},
{
"name": "model.layers.23.self_attn.qkv_proj.weight",
"shape": [
1600,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 3072000,
"byteOffset": 9832320
},
{
"name": "model.layers.23.self_attn.o_proj.weight",
"shape": [
960,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1843200,
"byteOffset": 12904320
},
{
"name": "model.layers.24.input_layernorm.weight",
"shape": [
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1920,
"byteOffset": 14747520
},
{
"name": "model.layers.24.mlp.down_proj.weight",
"shape": [
960,
2560
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 14749440
},
{
"name": "model.layers.24.mlp.gate_up_proj.weight",
"shape": [
5120,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 9830400,
"byteOffset": 19664640
},
{
"name": "model.layers.24.post_attention_layernorm.weight",
"shape": [
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1920,
"byteOffset": 29495040
},
{
"name": "model.layers.24.self_attn.qkv_proj.weight",
"shape": [
1600,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 3072000,
"byteOffset": 29496960
}
],
"md5sum": "6416bde70dcfcea5bfc1b9119981fa1e"
},
{
"dataPath": "params_shard_13.bin",
"format": "raw-shard",
"nbytes": 26424960,
"records": [
{
"name": "model.layers.24.self_attn.o_proj.weight",
"shape": [
960,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1843200,
"byteOffset": 0
},
{
"name": "model.layers.25.input_layernorm.weight",
"shape": [
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1920,
"byteOffset": 1843200
},
{
"name": "model.layers.25.mlp.down_proj.weight",
"shape": [
960,
2560
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 1845120
},
{
"name": "model.layers.25.mlp.gate_up_proj.weight",
"shape": [
5120,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 9830400,
"byteOffset": 6760320
},
{
"name": "model.layers.25.post_attention_layernorm.weight",
"shape": [
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1920,
"byteOffset": 16590720
},
{
"name": "model.layers.25.self_attn.qkv_proj.weight",
"shape": [
1600,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 3072000,
"byteOffset": 16592640
},
{
"name": "model.layers.25.self_attn.o_proj.weight",
"shape": [
960,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1843200,
"byteOffset": 19664640
},
{
"name": "model.layers.26.input_layernorm.weight",
"shape": [
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1920,
"byteOffset": 21507840
},
{
"name": "model.layers.26.mlp.down_proj.weight",
"shape": [
960,
2560
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 21509760
}
],
"md5sum": "e70b1ad7bd7e5f9f56830afe5f4de825"
},
{
"dataPath": "params_shard_14.bin",
"format": "raw-shard",
"nbytes": 32568960,
"records": [
{
"name": "model.layers.26.mlp.gate_up_proj.weight",
"shape": [
5120,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 9830400,
"byteOffset": 0
},
{
"name": "model.layers.26.post_attention_layernorm.weight",
"shape": [
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1920,
"byteOffset": 9830400
},
{
"name": "model.layers.26.self_attn.qkv_proj.weight",
"shape": [
1600,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 3072000,
"byteOffset": 9832320
},
{
"name": "model.layers.26.self_attn.o_proj.weight",
"shape": [
960,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1843200,
"byteOffset": 12904320
},
{
"name": "model.layers.27.input_layernorm.weight",
"shape": [
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1920,
"byteOffset": 14747520
},
{
"name": "model.layers.27.mlp.down_proj.weight",
"shape": [
960,
2560
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 14749440
},
{
"name": "model.layers.27.mlp.gate_up_proj.weight",
"shape": [
5120,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 9830400,
"byteOffset": 19664640
},
{
"name": "model.layers.27.post_attention_layernorm.weight",
"shape": [
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1920,
"byteOffset": 29495040
},
{
"name": "model.layers.27.self_attn.qkv_proj.weight",
"shape": [
1600,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 3072000,
"byteOffset": 29496960
}
],
"md5sum": "3fb295d08878db7d5555a2e04e6fff19"
},
{
"dataPath": "params_shard_15.bin",
"format": "raw-shard",
"nbytes": 26424960,
"records": [
{
"name": "model.layers.27.self_attn.o_proj.weight",
"shape": [
960,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1843200,
"byteOffset": 0
},
{
"name": "model.layers.28.input_layernorm.weight",
"shape": [
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1920,
"byteOffset": 1843200
},
{
"name": "model.layers.28.mlp.down_proj.weight",
"shape": [
960,
2560
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 1845120
},
{
"name": "model.layers.28.mlp.gate_up_proj.weight",
"shape": [
5120,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 9830400,
"byteOffset": 6760320
},
{
"name": "model.layers.28.post_attention_layernorm.weight",
"shape": [
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1920,
"byteOffset": 16590720
},
{
"name": "model.layers.28.self_attn.qkv_proj.weight",
"shape": [
1600,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 3072000,
"byteOffset": 16592640
},
{
"name": "model.layers.28.self_attn.o_proj.weight",
"shape": [
960,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1843200,
"byteOffset": 19664640
},
{
"name": "model.layers.29.input_layernorm.weight",
"shape": [
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1920,
"byteOffset": 21507840
},
{
"name": "model.layers.29.mlp.down_proj.weight",
"shape": [
960,
2560
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 21509760
}
],
"md5sum": "090a1b58614249666b8e032b89f78399"
},
{
"dataPath": "params_shard_16.bin",
"format": "raw-shard",
"nbytes": 32568960,
"records": [
{
"name": "model.layers.29.mlp.gate_up_proj.weight",
"shape": [
5120,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 9830400,
"byteOffset": 0
},
{
"name": "model.layers.29.post_attention_layernorm.weight",
"shape": [
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1920,
"byteOffset": 9830400
},
{
"name": "model.layers.29.self_attn.qkv_proj.weight",
"shape": [
1600,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 3072000,
"byteOffset": 9832320
},
{
"name": "model.layers.29.self_attn.o_proj.weight",
"shape": [
960,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1843200,
"byteOffset": 12904320
},
{
"name": "model.layers.3.input_layernorm.weight",
"shape": [
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1920,
"byteOffset": 14747520
},
{
"name": "model.layers.3.mlp.down_proj.weight",
"shape": [
960,
2560
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 14749440
},
{
"name": "model.layers.3.mlp.gate_up_proj.weight",
"shape": [
5120,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 9830400,
"byteOffset": 19664640
},
{
"name": "model.layers.3.post_attention_layernorm.weight",
"shape": [
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1920,
"byteOffset": 29495040
},
{
"name": "model.layers.3.self_attn.qkv_proj.weight",
"shape": [
1600,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 3072000,
"byteOffset": 29496960
}
],
"md5sum": "86548c3d1596b446424a94077f2c63af"
},
{
"dataPath": "params_shard_17.bin",
"format": "raw-shard",
"nbytes": 26424960,
"records": [
{
"name": "model.layers.3.self_attn.o_proj.weight",
"shape": [
960,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1843200,
"byteOffset": 0
},
{
"name": "model.layers.30.input_layernorm.weight",
"shape": [
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1920,
"byteOffset": 1843200
},
{
"name": "model.layers.30.mlp.down_proj.weight",
"shape": [
960,
2560
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 1845120
},
{
"name": "model.layers.30.mlp.gate_up_proj.weight",
"shape": [
5120,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 9830400,
"byteOffset": 6760320
},
{
"name": "model.layers.30.post_attention_layernorm.weight",
"shape": [
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1920,
"byteOffset": 16590720
},
{
"name": "model.layers.30.self_attn.qkv_proj.weight",
"shape": [
1600,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 3072000,
"byteOffset": 16592640
},
{
"name": "model.layers.30.self_attn.o_proj.weight",
"shape": [
960,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1843200,
"byteOffset": 19664640
},
{
"name": "model.layers.31.input_layernorm.weight",
"shape": [
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1920,
"byteOffset": 21507840
},
{
"name": "model.layers.31.mlp.down_proj.weight",
"shape": [
960,
2560
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 21509760
}
],
"md5sum": "45bd05f0361fc80f5cc8c91353e9ace6"
},
{
"dataPath": "params_shard_18.bin",
"format": "raw-shard",
"nbytes": 32568960,
"records": [
{
"name": "model.layers.31.mlp.gate_up_proj.weight",
"shape": [
5120,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 9830400,
"byteOffset": 0
},
{
"name": "model.layers.31.post_attention_layernorm.weight",
"shape": [
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1920,
"byteOffset": 9830400
},
{
"name": "model.layers.31.self_attn.qkv_proj.weight",
"shape": [
1600,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 3072000,
"byteOffset": 9832320
},
{
"name": "model.layers.31.self_attn.o_proj.weight",
"shape": [
960,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1843200,
"byteOffset": 12904320
},
{
"name": "model.layers.4.input_layernorm.weight",
"shape": [
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1920,
"byteOffset": 14747520
},
{
"name": "model.layers.4.mlp.down_proj.weight",
"shape": [
960,
2560
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 14749440
},
{
"name": "model.layers.4.mlp.gate_up_proj.weight",
"shape": [
5120,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 9830400,
"byteOffset": 19664640
},
{
"name": "model.layers.4.post_attention_layernorm.weight",
"shape": [
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1920,
"byteOffset": 29495040
},
{
"name": "model.layers.4.self_attn.qkv_proj.weight",
"shape": [
1600,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 3072000,
"byteOffset": 29496960
}
],
"md5sum": "393a1c2234049aa027f54430202a2a86"
},
{
"dataPath": "params_shard_19.bin",
"format": "raw-shard",
"nbytes": 26424960,
"records": [
{
"name": "model.layers.4.self_attn.o_proj.weight",
"shape": [
960,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1843200,
"byteOffset": 0
},
{
"name": "model.layers.5.input_layernorm.weight",
"shape": [
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1920,
"byteOffset": 1843200
},
{
"name": "model.layers.5.mlp.down_proj.weight",
"shape": [
960,
2560
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 1845120
},
{
"name": "model.layers.5.mlp.gate_up_proj.weight",
"shape": [
5120,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 9830400,
"byteOffset": 6760320
},
{
"name": "model.layers.5.post_attention_layernorm.weight",
"shape": [
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1920,
"byteOffset": 16590720
},
{
"name": "model.layers.5.self_attn.qkv_proj.weight",
"shape": [
1600,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 3072000,
"byteOffset": 16592640
},
{
"name": "model.layers.5.self_attn.o_proj.weight",
"shape": [
960,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1843200,
"byteOffset": 19664640
},
{
"name": "model.layers.6.input_layernorm.weight",
"shape": [
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1920,
"byteOffset": 21507840
},
{
"name": "model.layers.6.mlp.down_proj.weight",
"shape": [
960,
2560
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 21509760
}
],
"md5sum": "a19bd9e170235162c715a26be4d32ea9"
},
{
"dataPath": "params_shard_20.bin",
"format": "raw-shard",
"nbytes": 32568960,
"records": [
{
"name": "model.layers.6.mlp.gate_up_proj.weight",
"shape": [
5120,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 9830400,
"byteOffset": 0
},
{
"name": "model.layers.6.post_attention_layernorm.weight",
"shape": [
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1920,
"byteOffset": 9830400
},
{
"name": "model.layers.6.self_attn.qkv_proj.weight",
"shape": [
1600,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 3072000,
"byteOffset": 9832320
},
{
"name": "model.layers.6.self_attn.o_proj.weight",
"shape": [
960,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1843200,
"byteOffset": 12904320
},
{
"name": "model.layers.7.input_layernorm.weight",
"shape": [
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1920,
"byteOffset": 14747520
},
{
"name": "model.layers.7.mlp.down_proj.weight",
"shape": [
960,
2560
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 14749440
},
{
"name": "model.layers.7.mlp.gate_up_proj.weight",
"shape": [
5120,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 9830400,
"byteOffset": 19664640
},
{
"name": "model.layers.7.post_attention_layernorm.weight",
"shape": [
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1920,
"byteOffset": 29495040
},
{
"name": "model.layers.7.self_attn.qkv_proj.weight",
"shape": [
1600,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 3072000,
"byteOffset": 29496960
}
],
"md5sum": "176f8fdb7f6e8c93bc2feb08b18ec76c"
},
{
"dataPath": "params_shard_21.bin",
"format": "raw-shard",
"nbytes": 26424960,
"records": [
{
"name": "model.layers.7.self_attn.o_proj.weight",
"shape": [
960,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1843200,
"byteOffset": 0
},
{
"name": "model.layers.8.input_layernorm.weight",
"shape": [
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1920,
"byteOffset": 1843200
},
{
"name": "model.layers.8.mlp.down_proj.weight",
"shape": [
960,
2560
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 1845120
},
{
"name": "model.layers.8.mlp.gate_up_proj.weight",
"shape": [
5120,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 9830400,
"byteOffset": 6760320
},
{
"name": "model.layers.8.post_attention_layernorm.weight",
"shape": [
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1920,
"byteOffset": 16590720
},
{
"name": "model.layers.8.self_attn.qkv_proj.weight",
"shape": [
1600,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 3072000,
"byteOffset": 16592640
},
{
"name": "model.layers.8.self_attn.o_proj.weight",
"shape": [
960,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1843200,
"byteOffset": 19664640
},
{
"name": "model.layers.9.input_layernorm.weight",
"shape": [
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1920,
"byteOffset": 21507840
},
{
"name": "model.layers.9.mlp.down_proj.weight",
"shape": [
960,
2560
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 21509760
}
],
"md5sum": "aa08f3e3e1ee6ea8c9ff7ccd521c8180"
},
{
"dataPath": "params_shard_22.bin",
"format": "raw-shard",
"nbytes": 14749440,
"records": [
{
"name": "model.layers.9.mlp.gate_up_proj.weight",
"shape": [
5120,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 9830400,
"byteOffset": 0
},
{
"name": "model.layers.9.post_attention_layernorm.weight",
"shape": [
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1920,
"byteOffset": 9830400
},
{
"name": "model.layers.9.self_attn.qkv_proj.weight",
"shape": [
1600,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 3072000,
"byteOffset": 9832320
},
{
"name": "model.layers.9.self_attn.o_proj.weight",
"shape": [
960,
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1843200,
"byteOffset": 12904320
},
{
"name": "model.norm.weight",
"shape": [
960
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1920,
"byteOffset": 14747520
}
],
"md5sum": "20f62539576533bc8d758a592c542357"
}
]
}