jykim310's picture
Upload 29 files
125ac6c verified
raw
history blame
30.2 kB
{
"metadata": {
"ParamSize": 65,
"ParamBytes": 830578688.0,
"BitsPerParam": 4.500414746671623
},
"records": [
{
"dataPath": "params_shard_0.bin",
"format": "raw-shard",
"nbytes": 65536000,
"records": [
{
"name": "model.embed_tokens.q_weight",
"shape": [
32000,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 65536000,
"byteOffset": 0
}
],
"md5sum": "6074b8d5faea8fb20a1397a0b432521b"
},
{
"dataPath": "params_shard_1.bin",
"format": "raw-shard",
"nbytes": 33357824,
"records": [
{
"name": "model.embed_tokens.q_scale",
"shape": [
32000,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192000,
"byteOffset": 0
},
{
"name": "model.layers.0.self_attn.qkv_proj.q_weight",
"shape": [
12288,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 8192000
}
],
"md5sum": "8659d98c418f518bdb8c8b722f6dc22a"
},
{
"dataPath": "params_shard_2.bin",
"format": "raw-shard",
"nbytes": 45088768,
"records": [
{
"name": "model.layers.0.mlp.gate_up_proj.q_weight",
"shape": [
22016,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 45088768,
"byteOffset": 0
}
],
"md5sum": "4a67c897593512bb619d55ebf0325675"
},
{
"dataPath": "params_shard_3.bin",
"format": "raw-shard",
"nbytes": 22544384,
"records": [
{
"name": "model.layers.0.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 22544384,
"byteOffset": 0
}
],
"md5sum": "2e00ba1bedd2ff2e87489c6583492e87"
},
{
"dataPath": "params_shard_4.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.1.self_attn.qkv_proj.q_weight",
"shape": [
12288,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "ee7beab1026365e49ede869f77ae62da"
},
{
"dataPath": "params_shard_5.bin",
"format": "raw-shard",
"nbytes": 32587776,
"records": [
{
"name": "model.layers.0.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 0
},
{
"name": "model.layers.0.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 3145728
},
{
"name": "model.layers.0.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 11534336
},
{
"name": "model.layers.0.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 12582912
},
{
"name": "model.layers.0.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 18219008
},
{
"name": "model.layers.0.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21037056
},
{
"name": "model.layers.0.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21045248
},
{
"name": "model.layers.1.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 21053440
},
{
"name": "model.layers.1.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 24199168
}
],
"md5sum": "3022c6ab78d72b512472d9859c8fc586"
},
{
"dataPath": "params_shard_6.bin",
"format": "raw-shard",
"nbytes": 45088768,
"records": [
{
"name": "model.layers.1.mlp.gate_up_proj.q_weight",
"shape": [
22016,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 45088768,
"byteOffset": 0
}
],
"md5sum": "17147d4a8ad730c664d430f91f823be0"
},
{
"dataPath": "params_shard_7.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.2.self_attn.qkv_proj.q_weight",
"shape": [
12288,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "cb171bd0adfef7bbcc08fa2a9d3845a6"
},
{
"dataPath": "params_shard_8.bin",
"format": "raw-shard",
"nbytes": 32063488,
"records": [
{
"name": "model.layers.1.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 0
},
{
"name": "model.layers.1.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 1048576
},
{
"name": "model.layers.1.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 22544384,
"byteOffset": 6684672
},
{
"name": "model.layers.1.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 29229056
},
{
"name": "model.layers.1.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 32047104
},
{
"name": "model.layers.1.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 32055296
}
],
"md5sum": "2de448c64208cb50733c0cc71d9cfc09"
},
{
"dataPath": "params_shard_9.bin",
"format": "raw-shard",
"nbytes": 45088768,
"records": [
{
"name": "model.layers.2.mlp.gate_up_proj.q_weight",
"shape": [
22016,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 45088768,
"byteOffset": 0
}
],
"md5sum": "423bcd3e7b98839c0162318276c6dbb3"
},
{
"dataPath": "params_shard_10.bin",
"format": "raw-shard",
"nbytes": 22544384,
"records": [
{
"name": "model.layers.2.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 22544384,
"byteOffset": 0
}
],
"md5sum": "0a863f18524f26e06132a73a33ad023e"
},
{
"dataPath": "params_shard_11.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.3.self_attn.qkv_proj.q_weight",
"shape": [
12288,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "e7fce24651c953a4f1f7002ebb9c3174"
},
{
"dataPath": "params_shard_12.bin",
"format": "raw-shard",
"nbytes": 32587776,
"records": [
{
"name": "model.layers.2.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 0
},
{
"name": "model.layers.2.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 3145728
},
{
"name": "model.layers.2.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 11534336
},
{
"name": "model.layers.2.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 12582912
},
{
"name": "model.layers.2.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 18219008
},
{
"name": "model.layers.2.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21037056
},
{
"name": "model.layers.2.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21045248
},
{
"name": "model.layers.3.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 21053440
},
{
"name": "model.layers.3.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 24199168
}
],
"md5sum": "3dc9af9bab07bfb4d9811d6a8bc3e50b"
},
{
"dataPath": "params_shard_13.bin",
"format": "raw-shard",
"nbytes": 45088768,
"records": [
{
"name": "model.layers.3.mlp.gate_up_proj.q_weight",
"shape": [
22016,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 45088768,
"byteOffset": 0
}
],
"md5sum": "5577b15a8daf2ae1005e7ad4f88e9ded"
},
{
"dataPath": "params_shard_14.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.4.self_attn.qkv_proj.q_weight",
"shape": [
12288,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "e416ee6940c00d9eb6b4f12444857158"
},
{
"dataPath": "params_shard_15.bin",
"format": "raw-shard",
"nbytes": 32063488,
"records": [
{
"name": "model.layers.3.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 0
},
{
"name": "model.layers.3.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 1048576
},
{
"name": "model.layers.3.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 22544384,
"byteOffset": 6684672
},
{
"name": "model.layers.3.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 29229056
},
{
"name": "model.layers.3.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 32047104
},
{
"name": "model.layers.3.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 32055296
}
],
"md5sum": "5633c5a4f580f309dde8f1dbb283fe34"
},
{
"dataPath": "params_shard_16.bin",
"format": "raw-shard",
"nbytes": 45088768,
"records": [
{
"name": "model.layers.4.mlp.gate_up_proj.q_weight",
"shape": [
22016,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 45088768,
"byteOffset": 0
}
],
"md5sum": "c1c05d00a63fd2310e9277e1afe994e8"
},
{
"dataPath": "params_shard_17.bin",
"format": "raw-shard",
"nbytes": 22544384,
"records": [
{
"name": "model.layers.4.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 22544384,
"byteOffset": 0
}
],
"md5sum": "a25e26f7a02645b6fdc6b884c3666702"
},
{
"dataPath": "params_shard_18.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.5.self_attn.qkv_proj.q_weight",
"shape": [
12288,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "d866d6f43426a7a64c32b2d6948a6b47"
},
{
"dataPath": "params_shard_19.bin",
"format": "raw-shard",
"nbytes": 32587776,
"records": [
{
"name": "model.layers.4.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 0
},
{
"name": "model.layers.4.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 3145728
},
{
"name": "model.layers.4.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 11534336
},
{
"name": "model.layers.4.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 12582912
},
{
"name": "model.layers.4.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 18219008
},
{
"name": "model.layers.4.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21037056
},
{
"name": "model.layers.4.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21045248
},
{
"name": "model.layers.5.self_attn.qkv_proj.q_scale",
"shape": [
12288,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 21053440
},
{
"name": "model.layers.5.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 24199168
}
],
"md5sum": "cc26b507fe975f21c9131cde44f3907a"
},
{
"dataPath": "params_shard_20.bin",
"format": "raw-shard",
"nbytes": 45088768,
"records": [
{
"name": "model.layers.5.mlp.gate_up_proj.q_weight",
"shape": [
22016,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 45088768,
"byteOffset": 0
}
],
"md5sum": "4aa7af8962ab8a9dd9d48986eec4947f"
},
{
"dataPath": "params_shard_21.bin",
"format": "raw-shard",
"nbytes": 65536000,
"records": [
{
"name": "lm_head.q_weight",
"shape": [
32000,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 65536000,
"byteOffset": 0
}
],
"md5sum": "2e559f694c15d0d40bf21fbb1d025ee8"
},
{
"dataPath": "params_shard_22.bin",
"format": "raw-shard",
"nbytes": 32071680,
"records": [
{
"name": "model.layers.5.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 0
},
{
"name": "model.layers.5.mlp.gate_up_proj.q_scale",
"shape": [
22016,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5636096,
"byteOffset": 1048576
},
{
"name": "model.layers.5.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 22544384,
"byteOffset": 6684672
},
{
"name": "model.layers.5.mlp.down_proj.q_scale",
"shape": [
4096,
344
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2818048,
"byteOffset": 29229056
},
{
"name": "model.layers.5.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 32047104
},
{
"name": "model.layers.5.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 32055296
},
{
"name": "model.norm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 32063488
}
],
"md5sum": "3026df031148ab773e9b7047ad28afe5"
},
{
"dataPath": "params_shard_23.bin",
"format": "raw-shard",
"nbytes": 8192000,
"records": [
{
"name": "lm_head.q_scale",
"shape": [
32000,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192000,
"byteOffset": 0
}
],
"md5sum": "315a4c72ed5633971de22527b937ecf7"
}
]
}