tiny_llama_zh_mlc / ndarray-cache.json
zz814's picture
Upload 30 files
cd0c4c8 verified
{
"metadata": {
"ParamSize": 225,
"ParamBytes": 694996992.0,
"BitsPerParam": 4.500857951427515
},
"records": [
{
"dataPath": "params_shard_0.bin",
"format": "raw-shard",
"nbytes": 66584576,
"records": [
{
"name": "lm_head.q_weight",
"shape": [
65024,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 66584576,
"byteOffset": 0
}
],
"md5sum": "0f9fa0a19854bb49f3e6a74c54b1b44f"
},
{
"dataPath": "params_shard_1.bin",
"format": "raw-shard",
"nbytes": 66584576,
"records": [
{
"name": "model.embed_tokens.q_weight",
"shape": [
65024,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 66584576,
"byteOffset": 0
}
],
"md5sum": "c4851353a8d2563e47c3bf8a0d5bbb43"
},
{
"dataPath": "params_shard_2.bin",
"format": "raw-shard",
"nbytes": 23138304,
"records": [
{
"name": "lm_head.q_scale",
"shape": [
65024,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8323072,
"byteOffset": 0
},
{
"name": "model.embed_tokens.q_scale",
"shape": [
65024,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8323072,
"byteOffset": 8323072
},
{
"name": "model.layers.0.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 16646144
},
{
"name": "model.layers.0.mlp.down_proj.q_weight",
"shape": [
2048,
704
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 5767168,
"byteOffset": 16650240
},
{
"name": "model.layers.0.mlp.down_proj.q_scale",
"shape": [
2048,
176
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 720896,
"byteOffset": 22417408
}
],
"md5sum": "4c6ed7223e2a4162776e7d8af803eebc"
},
{
"dataPath": "params_shard_3.bin",
"format": "raw-shard",
"nbytes": 24780800,
"records": [
{
"name": "model.layers.0.mlp.gate_up_proj.q_weight",
"shape": [
11264,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 11534336,
"byteOffset": 0
},
{
"name": "model.layers.0.mlp.gate_up_proj.q_scale",
"shape": [
11264,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1441792,
"byteOffset": 11534336
},
{
"name": "model.layers.0.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 12976128
},
{
"name": "model.layers.0.self_attn.qkv_proj.q_weight",
"shape": [
2560,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2621440,
"byteOffset": 12980224
},
{
"name": "model.layers.0.self_attn.qkv_proj.q_scale",
"shape": [
2560,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 327680,
"byteOffset": 15601664
},
{
"name": "model.layers.0.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 15929344
},
{
"name": "model.layers.0.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 18026496
},
{
"name": "model.layers.1.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 18288640
},
{
"name": "model.layers.1.mlp.down_proj.q_weight",
"shape": [
2048,
704
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 5767168,
"byteOffset": 18292736
},
{
"name": "model.layers.1.mlp.down_proj.q_scale",
"shape": [
2048,
176
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 720896,
"byteOffset": 24059904
}
],
"md5sum": "79dfe66878509fdfa072510efc71ca01"
},
{
"dataPath": "params_shard_4.bin",
"format": "raw-shard",
"nbytes": 24780800,
"records": [
{
"name": "model.layers.1.mlp.gate_up_proj.q_weight",
"shape": [
11264,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 11534336,
"byteOffset": 0
},
{
"name": "model.layers.1.mlp.gate_up_proj.q_scale",
"shape": [
11264,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1441792,
"byteOffset": 11534336
},
{
"name": "model.layers.1.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 12976128
},
{
"name": "model.layers.1.self_attn.qkv_proj.q_weight",
"shape": [
2560,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2621440,
"byteOffset": 12980224
},
{
"name": "model.layers.1.self_attn.qkv_proj.q_scale",
"shape": [
2560,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 327680,
"byteOffset": 15601664
},
{
"name": "model.layers.1.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 15929344
},
{
"name": "model.layers.1.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 18026496
},
{
"name": "model.layers.10.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 18288640
},
{
"name": "model.layers.10.mlp.down_proj.q_weight",
"shape": [
2048,
704
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 5767168,
"byteOffset": 18292736
},
{
"name": "model.layers.10.mlp.down_proj.q_scale",
"shape": [
2048,
176
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 720896,
"byteOffset": 24059904
}
],
"md5sum": "e7022aa5f2c11f49ae1eb3de1c1760e1"
},
{
"dataPath": "params_shard_5.bin",
"format": "raw-shard",
"nbytes": 24780800,
"records": [
{
"name": "model.layers.10.mlp.gate_up_proj.q_weight",
"shape": [
11264,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 11534336,
"byteOffset": 0
},
{
"name": "model.layers.10.mlp.gate_up_proj.q_scale",
"shape": [
11264,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1441792,
"byteOffset": 11534336
},
{
"name": "model.layers.10.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 12976128
},
{
"name": "model.layers.10.self_attn.qkv_proj.q_weight",
"shape": [
2560,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2621440,
"byteOffset": 12980224
},
{
"name": "model.layers.10.self_attn.qkv_proj.q_scale",
"shape": [
2560,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 327680,
"byteOffset": 15601664
},
{
"name": "model.layers.10.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 15929344
},
{
"name": "model.layers.10.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 18026496
},
{
"name": "model.layers.11.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 18288640
},
{
"name": "model.layers.11.mlp.down_proj.q_weight",
"shape": [
2048,
704
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 5767168,
"byteOffset": 18292736
},
{
"name": "model.layers.11.mlp.down_proj.q_scale",
"shape": [
2048,
176
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 720896,
"byteOffset": 24059904
}
],
"md5sum": "f45cff6d2687bdc703a34bb6437b709f"
},
{
"dataPath": "params_shard_6.bin",
"format": "raw-shard",
"nbytes": 24780800,
"records": [
{
"name": "model.layers.11.mlp.gate_up_proj.q_weight",
"shape": [
11264,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 11534336,
"byteOffset": 0
},
{
"name": "model.layers.11.mlp.gate_up_proj.q_scale",
"shape": [
11264,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1441792,
"byteOffset": 11534336
},
{
"name": "model.layers.11.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 12976128
},
{
"name": "model.layers.11.self_attn.qkv_proj.q_weight",
"shape": [
2560,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2621440,
"byteOffset": 12980224
},
{
"name": "model.layers.11.self_attn.qkv_proj.q_scale",
"shape": [
2560,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 327680,
"byteOffset": 15601664
},
{
"name": "model.layers.11.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 15929344
},
{
"name": "model.layers.11.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 18026496
},
{
"name": "model.layers.12.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 18288640
},
{
"name": "model.layers.12.mlp.down_proj.q_weight",
"shape": [
2048,
704
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 5767168,
"byteOffset": 18292736
},
{
"name": "model.layers.12.mlp.down_proj.q_scale",
"shape": [
2048,
176
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 720896,
"byteOffset": 24059904
}
],
"md5sum": "3219e41edabbc8b1decc2baf5b8ea7e6"
},
{
"dataPath": "params_shard_7.bin",
"format": "raw-shard",
"nbytes": 24780800,
"records": [
{
"name": "model.layers.12.mlp.gate_up_proj.q_weight",
"shape": [
11264,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 11534336,
"byteOffset": 0
},
{
"name": "model.layers.12.mlp.gate_up_proj.q_scale",
"shape": [
11264,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1441792,
"byteOffset": 11534336
},
{
"name": "model.layers.12.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 12976128
},
{
"name": "model.layers.12.self_attn.qkv_proj.q_weight",
"shape": [
2560,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2621440,
"byteOffset": 12980224
},
{
"name": "model.layers.12.self_attn.qkv_proj.q_scale",
"shape": [
2560,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 327680,
"byteOffset": 15601664
},
{
"name": "model.layers.12.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 15929344
},
{
"name": "model.layers.12.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 18026496
},
{
"name": "model.layers.13.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 18288640
},
{
"name": "model.layers.13.mlp.down_proj.q_weight",
"shape": [
2048,
704
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 5767168,
"byteOffset": 18292736
},
{
"name": "model.layers.13.mlp.down_proj.q_scale",
"shape": [
2048,
176
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 720896,
"byteOffset": 24059904
}
],
"md5sum": "d7d5c74a612879f020e3c8c98899a45c"
},
{
"dataPath": "params_shard_8.bin",
"format": "raw-shard",
"nbytes": 24780800,
"records": [
{
"name": "model.layers.13.mlp.gate_up_proj.q_weight",
"shape": [
11264,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 11534336,
"byteOffset": 0
},
{
"name": "model.layers.13.mlp.gate_up_proj.q_scale",
"shape": [
11264,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1441792,
"byteOffset": 11534336
},
{
"name": "model.layers.13.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 12976128
},
{
"name": "model.layers.13.self_attn.qkv_proj.q_weight",
"shape": [
2560,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2621440,
"byteOffset": 12980224
},
{
"name": "model.layers.13.self_attn.qkv_proj.q_scale",
"shape": [
2560,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 327680,
"byteOffset": 15601664
},
{
"name": "model.layers.13.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 15929344
},
{
"name": "model.layers.13.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 18026496
},
{
"name": "model.layers.14.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 18288640
},
{
"name": "model.layers.14.mlp.down_proj.q_weight",
"shape": [
2048,
704
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 5767168,
"byteOffset": 18292736
},
{
"name": "model.layers.14.mlp.down_proj.q_scale",
"shape": [
2048,
176
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 720896,
"byteOffset": 24059904
}
],
"md5sum": "292c4dc65c8ca71cbc9752120bc93e91"
},
{
"dataPath": "params_shard_9.bin",
"format": "raw-shard",
"nbytes": 24780800,
"records": [
{
"name": "model.layers.14.mlp.gate_up_proj.q_weight",
"shape": [
11264,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 11534336,
"byteOffset": 0
},
{
"name": "model.layers.14.mlp.gate_up_proj.q_scale",
"shape": [
11264,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1441792,
"byteOffset": 11534336
},
{
"name": "model.layers.14.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 12976128
},
{
"name": "model.layers.14.self_attn.qkv_proj.q_weight",
"shape": [
2560,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2621440,
"byteOffset": 12980224
},
{
"name": "model.layers.14.self_attn.qkv_proj.q_scale",
"shape": [
2560,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 327680,
"byteOffset": 15601664
},
{
"name": "model.layers.14.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 15929344
},
{
"name": "model.layers.14.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 18026496
},
{
"name": "model.layers.15.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 18288640
},
{
"name": "model.layers.15.mlp.down_proj.q_weight",
"shape": [
2048,
704
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 5767168,
"byteOffset": 18292736
},
{
"name": "model.layers.15.mlp.down_proj.q_scale",
"shape": [
2048,
176
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 720896,
"byteOffset": 24059904
}
],
"md5sum": "c95244eeda3cf25438d388239bae2eb9"
},
{
"dataPath": "params_shard_10.bin",
"format": "raw-shard",
"nbytes": 24780800,
"records": [
{
"name": "model.layers.15.mlp.gate_up_proj.q_weight",
"shape": [
11264,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 11534336,
"byteOffset": 0
},
{
"name": "model.layers.15.mlp.gate_up_proj.q_scale",
"shape": [
11264,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1441792,
"byteOffset": 11534336
},
{
"name": "model.layers.15.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 12976128
},
{
"name": "model.layers.15.self_attn.qkv_proj.q_weight",
"shape": [
2560,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2621440,
"byteOffset": 12980224
},
{
"name": "model.layers.15.self_attn.qkv_proj.q_scale",
"shape": [
2560,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 327680,
"byteOffset": 15601664
},
{
"name": "model.layers.15.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 15929344
},
{
"name": "model.layers.15.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 18026496
},
{
"name": "model.layers.16.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 18288640
},
{
"name": "model.layers.16.mlp.down_proj.q_weight",
"shape": [
2048,
704
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 5767168,
"byteOffset": 18292736
},
{
"name": "model.layers.16.mlp.down_proj.q_scale",
"shape": [
2048,
176
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 720896,
"byteOffset": 24059904
}
],
"md5sum": "1d7b6cfc26c9d9fe95bfb528210928d7"
},
{
"dataPath": "params_shard_11.bin",
"format": "raw-shard",
"nbytes": 24780800,
"records": [
{
"name": "model.layers.16.mlp.gate_up_proj.q_weight",
"shape": [
11264,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 11534336,
"byteOffset": 0
},
{
"name": "model.layers.16.mlp.gate_up_proj.q_scale",
"shape": [
11264,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1441792,
"byteOffset": 11534336
},
{
"name": "model.layers.16.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 12976128
},
{
"name": "model.layers.16.self_attn.qkv_proj.q_weight",
"shape": [
2560,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2621440,
"byteOffset": 12980224
},
{
"name": "model.layers.16.self_attn.qkv_proj.q_scale",
"shape": [
2560,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 327680,
"byteOffset": 15601664
},
{
"name": "model.layers.16.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 15929344
},
{
"name": "model.layers.16.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 18026496
},
{
"name": "model.layers.17.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 18288640
},
{
"name": "model.layers.17.mlp.down_proj.q_weight",
"shape": [
2048,
704
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 5767168,
"byteOffset": 18292736
},
{
"name": "model.layers.17.mlp.down_proj.q_scale",
"shape": [
2048,
176
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 720896,
"byteOffset": 24059904
}
],
"md5sum": "93ec21beb9f888dffbb5d8d3ff12b987"
},
{
"dataPath": "params_shard_12.bin",
"format": "raw-shard",
"nbytes": 24780800,
"records": [
{
"name": "model.layers.17.mlp.gate_up_proj.q_weight",
"shape": [
11264,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 11534336,
"byteOffset": 0
},
{
"name": "model.layers.17.mlp.gate_up_proj.q_scale",
"shape": [
11264,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1441792,
"byteOffset": 11534336
},
{
"name": "model.layers.17.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 12976128
},
{
"name": "model.layers.17.self_attn.qkv_proj.q_weight",
"shape": [
2560,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2621440,
"byteOffset": 12980224
},
{
"name": "model.layers.17.self_attn.qkv_proj.q_scale",
"shape": [
2560,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 327680,
"byteOffset": 15601664
},
{
"name": "model.layers.17.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 15929344
},
{
"name": "model.layers.17.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 18026496
},
{
"name": "model.layers.18.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 18288640
},
{
"name": "model.layers.18.mlp.down_proj.q_weight",
"shape": [
2048,
704
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 5767168,
"byteOffset": 18292736
},
{
"name": "model.layers.18.mlp.down_proj.q_scale",
"shape": [
2048,
176
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 720896,
"byteOffset": 24059904
}
],
"md5sum": "252eb9f66784e3f186d332a2234b3b47"
},
{
"dataPath": "params_shard_13.bin",
"format": "raw-shard",
"nbytes": 24780800,
"records": [
{
"name": "model.layers.18.mlp.gate_up_proj.q_weight",
"shape": [
11264,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 11534336,
"byteOffset": 0
},
{
"name": "model.layers.18.mlp.gate_up_proj.q_scale",
"shape": [
11264,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1441792,
"byteOffset": 11534336
},
{
"name": "model.layers.18.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 12976128
},
{
"name": "model.layers.18.self_attn.qkv_proj.q_weight",
"shape": [
2560,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2621440,
"byteOffset": 12980224
},
{
"name": "model.layers.18.self_attn.qkv_proj.q_scale",
"shape": [
2560,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 327680,
"byteOffset": 15601664
},
{
"name": "model.layers.18.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 15929344
},
{
"name": "model.layers.18.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 18026496
},
{
"name": "model.layers.19.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 18288640
},
{
"name": "model.layers.19.mlp.down_proj.q_weight",
"shape": [
2048,
704
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 5767168,
"byteOffset": 18292736
},
{
"name": "model.layers.19.mlp.down_proj.q_scale",
"shape": [
2048,
176
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 720896,
"byteOffset": 24059904
}
],
"md5sum": "059a30652f62bc53f40deb3742b57dbf"
},
{
"dataPath": "params_shard_14.bin",
"format": "raw-shard",
"nbytes": 24780800,
"records": [
{
"name": "model.layers.19.mlp.gate_up_proj.q_weight",
"shape": [
11264,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 11534336,
"byteOffset": 0
},
{
"name": "model.layers.19.mlp.gate_up_proj.q_scale",
"shape": [
11264,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1441792,
"byteOffset": 11534336
},
{
"name": "model.layers.19.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 12976128
},
{
"name": "model.layers.19.self_attn.qkv_proj.q_weight",
"shape": [
2560,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2621440,
"byteOffset": 12980224
},
{
"name": "model.layers.19.self_attn.qkv_proj.q_scale",
"shape": [
2560,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 327680,
"byteOffset": 15601664
},
{
"name": "model.layers.19.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 15929344
},
{
"name": "model.layers.19.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 18026496
},
{
"name": "model.layers.2.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 18288640
},
{
"name": "model.layers.2.mlp.down_proj.q_weight",
"shape": [
2048,
704
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 5767168,
"byteOffset": 18292736
},
{
"name": "model.layers.2.mlp.down_proj.q_scale",
"shape": [
2048,
176
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 720896,
"byteOffset": 24059904
}
],
"md5sum": "c41e8ad7f31fe03e8156eda6593ac2c6"
},
{
"dataPath": "params_shard_15.bin",
"format": "raw-shard",
"nbytes": 24780800,
"records": [
{
"name": "model.layers.2.mlp.gate_up_proj.q_weight",
"shape": [
11264,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 11534336,
"byteOffset": 0
},
{
"name": "model.layers.2.mlp.gate_up_proj.q_scale",
"shape": [
11264,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1441792,
"byteOffset": 11534336
},
{
"name": "model.layers.2.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 12976128
},
{
"name": "model.layers.2.self_attn.qkv_proj.q_weight",
"shape": [
2560,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2621440,
"byteOffset": 12980224
},
{
"name": "model.layers.2.self_attn.qkv_proj.q_scale",
"shape": [
2560,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 327680,
"byteOffset": 15601664
},
{
"name": "model.layers.2.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 15929344
},
{
"name": "model.layers.2.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 18026496
},
{
"name": "model.layers.20.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 18288640
},
{
"name": "model.layers.20.mlp.down_proj.q_weight",
"shape": [
2048,
704
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 5767168,
"byteOffset": 18292736
},
{
"name": "model.layers.20.mlp.down_proj.q_scale",
"shape": [
2048,
176
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 720896,
"byteOffset": 24059904
}
],
"md5sum": "3dbcb76c12ca477d6df8ea1aa572674a"
},
{
"dataPath": "params_shard_16.bin",
"format": "raw-shard",
"nbytes": 24780800,
"records": [
{
"name": "model.layers.20.mlp.gate_up_proj.q_weight",
"shape": [
11264,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 11534336,
"byteOffset": 0
},
{
"name": "model.layers.20.mlp.gate_up_proj.q_scale",
"shape": [
11264,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1441792,
"byteOffset": 11534336
},
{
"name": "model.layers.20.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 12976128
},
{
"name": "model.layers.20.self_attn.qkv_proj.q_weight",
"shape": [
2560,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2621440,
"byteOffset": 12980224
},
{
"name": "model.layers.20.self_attn.qkv_proj.q_scale",
"shape": [
2560,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 327680,
"byteOffset": 15601664
},
{
"name": "model.layers.20.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 15929344
},
{
"name": "model.layers.20.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 18026496
},
{
"name": "model.layers.21.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 18288640
},
{
"name": "model.layers.21.mlp.down_proj.q_weight",
"shape": [
2048,
704
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 5767168,
"byteOffset": 18292736
},
{
"name": "model.layers.21.mlp.down_proj.q_scale",
"shape": [
2048,
176
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 720896,
"byteOffset": 24059904
}
],
"md5sum": "bcd7ef15371c7bc90b12f293d4de7e71"
},
{
"dataPath": "params_shard_17.bin",
"format": "raw-shard",
"nbytes": 24780800,
"records": [
{
"name": "model.layers.21.mlp.gate_up_proj.q_weight",
"shape": [
11264,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 11534336,
"byteOffset": 0
},
{
"name": "model.layers.21.mlp.gate_up_proj.q_scale",
"shape": [
11264,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1441792,
"byteOffset": 11534336
},
{
"name": "model.layers.21.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 12976128
},
{
"name": "model.layers.21.self_attn.qkv_proj.q_weight",
"shape": [
2560,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2621440,
"byteOffset": 12980224
},
{
"name": "model.layers.21.self_attn.qkv_proj.q_scale",
"shape": [
2560,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 327680,
"byteOffset": 15601664
},
{
"name": "model.layers.21.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 15929344
},
{
"name": "model.layers.21.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 18026496
},
{
"name": "model.layers.3.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 18288640
},
{
"name": "model.layers.3.mlp.down_proj.q_weight",
"shape": [
2048,
704
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 5767168,
"byteOffset": 18292736
},
{
"name": "model.layers.3.mlp.down_proj.q_scale",
"shape": [
2048,
176
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 720896,
"byteOffset": 24059904
}
],
"md5sum": "a7bc7c31bdf390d7b42269dc738eb8c0"
},
{
"dataPath": "params_shard_18.bin",
"format": "raw-shard",
"nbytes": 24780800,
"records": [
{
"name": "model.layers.3.mlp.gate_up_proj.q_weight",
"shape": [
11264,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 11534336,
"byteOffset": 0
},
{
"name": "model.layers.3.mlp.gate_up_proj.q_scale",
"shape": [
11264,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1441792,
"byteOffset": 11534336
},
{
"name": "model.layers.3.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 12976128
},
{
"name": "model.layers.3.self_attn.qkv_proj.q_weight",
"shape": [
2560,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2621440,
"byteOffset": 12980224
},
{
"name": "model.layers.3.self_attn.qkv_proj.q_scale",
"shape": [
2560,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 327680,
"byteOffset": 15601664
},
{
"name": "model.layers.3.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 15929344
},
{
"name": "model.layers.3.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 18026496
},
{
"name": "model.layers.4.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 18288640
},
{
"name": "model.layers.4.mlp.down_proj.q_weight",
"shape": [
2048,
704
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 5767168,
"byteOffset": 18292736
},
{
"name": "model.layers.4.mlp.down_proj.q_scale",
"shape": [
2048,
176
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 720896,
"byteOffset": 24059904
}
],
"md5sum": "8b6140e47fae0999f13e399639b3f6de"
},
{
"dataPath": "params_shard_19.bin",
"format": "raw-shard",
"nbytes": 24780800,
"records": [
{
"name": "model.layers.4.mlp.gate_up_proj.q_weight",
"shape": [
11264,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 11534336,
"byteOffset": 0
},
{
"name": "model.layers.4.mlp.gate_up_proj.q_scale",
"shape": [
11264,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1441792,
"byteOffset": 11534336
},
{
"name": "model.layers.4.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 12976128
},
{
"name": "model.layers.4.self_attn.qkv_proj.q_weight",
"shape": [
2560,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2621440,
"byteOffset": 12980224
},
{
"name": "model.layers.4.self_attn.qkv_proj.q_scale",
"shape": [
2560,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 327680,
"byteOffset": 15601664
},
{
"name": "model.layers.4.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 15929344
},
{
"name": "model.layers.4.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 18026496
},
{
"name": "model.layers.5.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 18288640
},
{
"name": "model.layers.5.mlp.down_proj.q_weight",
"shape": [
2048,
704
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 5767168,
"byteOffset": 18292736
},
{
"name": "model.layers.5.mlp.down_proj.q_scale",
"shape": [
2048,
176
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 720896,
"byteOffset": 24059904
}
],
"md5sum": "bd6606704559e75d7958a06d3f9d37e9"
},
{
"dataPath": "params_shard_20.bin",
"format": "raw-shard",
"nbytes": 24780800,
"records": [
{
"name": "model.layers.5.mlp.gate_up_proj.q_weight",
"shape": [
11264,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 11534336,
"byteOffset": 0
},
{
"name": "model.layers.5.mlp.gate_up_proj.q_scale",
"shape": [
11264,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1441792,
"byteOffset": 11534336
},
{
"name": "model.layers.5.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 12976128
},
{
"name": "model.layers.5.self_attn.qkv_proj.q_weight",
"shape": [
2560,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2621440,
"byteOffset": 12980224
},
{
"name": "model.layers.5.self_attn.qkv_proj.q_scale",
"shape": [
2560,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 327680,
"byteOffset": 15601664
},
{
"name": "model.layers.5.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 15929344
},
{
"name": "model.layers.5.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 18026496
},
{
"name": "model.layers.6.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 18288640
},
{
"name": "model.layers.6.mlp.down_proj.q_weight",
"shape": [
2048,
704
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 5767168,
"byteOffset": 18292736
},
{
"name": "model.layers.6.mlp.down_proj.q_scale",
"shape": [
2048,
176
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 720896,
"byteOffset": 24059904
}
],
"md5sum": "4e00b0e85bb81d8dd5c3e7a4b6f8a1fb"
},
{
"dataPath": "params_shard_21.bin",
"format": "raw-shard",
"nbytes": 24780800,
"records": [
{
"name": "model.layers.6.mlp.gate_up_proj.q_weight",
"shape": [
11264,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 11534336,
"byteOffset": 0
},
{
"name": "model.layers.6.mlp.gate_up_proj.q_scale",
"shape": [
11264,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1441792,
"byteOffset": 11534336
},
{
"name": "model.layers.6.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 12976128
},
{
"name": "model.layers.6.self_attn.qkv_proj.q_weight",
"shape": [
2560,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2621440,
"byteOffset": 12980224
},
{
"name": "model.layers.6.self_attn.qkv_proj.q_scale",
"shape": [
2560,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 327680,
"byteOffset": 15601664
},
{
"name": "model.layers.6.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 15929344
},
{
"name": "model.layers.6.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 18026496
},
{
"name": "model.layers.7.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 18288640
},
{
"name": "model.layers.7.mlp.down_proj.q_weight",
"shape": [
2048,
704
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 5767168,
"byteOffset": 18292736
},
{
"name": "model.layers.7.mlp.down_proj.q_scale",
"shape": [
2048,
176
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 720896,
"byteOffset": 24059904
}
],
"md5sum": "98bb60cf7f41ca949866554fac1d6b41"
},
{
"dataPath": "params_shard_22.bin",
"format": "raw-shard",
"nbytes": 24780800,
"records": [
{
"name": "model.layers.7.mlp.gate_up_proj.q_weight",
"shape": [
11264,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 11534336,
"byteOffset": 0
},
{
"name": "model.layers.7.mlp.gate_up_proj.q_scale",
"shape": [
11264,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1441792,
"byteOffset": 11534336
},
{
"name": "model.layers.7.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 12976128
},
{
"name": "model.layers.7.self_attn.qkv_proj.q_weight",
"shape": [
2560,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2621440,
"byteOffset": 12980224
},
{
"name": "model.layers.7.self_attn.qkv_proj.q_scale",
"shape": [
2560,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 327680,
"byteOffset": 15601664
},
{
"name": "model.layers.7.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 15929344
},
{
"name": "model.layers.7.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 18026496
},
{
"name": "model.layers.8.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 18288640
},
{
"name": "model.layers.8.mlp.down_proj.q_weight",
"shape": [
2048,
704
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 5767168,
"byteOffset": 18292736
},
{
"name": "model.layers.8.mlp.down_proj.q_scale",
"shape": [
2048,
176
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 720896,
"byteOffset": 24059904
}
],
"md5sum": "922f2d133b9adbd0699c0df7272ea578"
},
{
"dataPath": "params_shard_23.bin",
"format": "raw-shard",
"nbytes": 24780800,
"records": [
{
"name": "model.layers.8.mlp.gate_up_proj.q_weight",
"shape": [
11264,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 11534336,
"byteOffset": 0
},
{
"name": "model.layers.8.mlp.gate_up_proj.q_scale",
"shape": [
11264,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1441792,
"byteOffset": 11534336
},
{
"name": "model.layers.8.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 12976128
},
{
"name": "model.layers.8.self_attn.qkv_proj.q_weight",
"shape": [
2560,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2621440,
"byteOffset": 12980224
},
{
"name": "model.layers.8.self_attn.qkv_proj.q_scale",
"shape": [
2560,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 327680,
"byteOffset": 15601664
},
{
"name": "model.layers.8.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 15929344
},
{
"name": "model.layers.8.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 18026496
},
{
"name": "model.layers.9.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 18288640
},
{
"name": "model.layers.9.mlp.down_proj.q_weight",
"shape": [
2048,
704
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 5767168,
"byteOffset": 18292736
},
{
"name": "model.layers.9.mlp.down_proj.q_scale",
"shape": [
2048,
176
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 720896,
"byteOffset": 24059904
}
],
"md5sum": "8dad1c13c9d46b44b149d8c8120c76d7"
},
{
"dataPath": "params_shard_24.bin",
"format": "raw-shard",
"nbytes": 18292736,
"records": [
{
"name": "model.layers.9.mlp.gate_up_proj.q_weight",
"shape": [
11264,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 11534336,
"byteOffset": 0
},
{
"name": "model.layers.9.mlp.gate_up_proj.q_scale",
"shape": [
11264,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1441792,
"byteOffset": 11534336
},
{
"name": "model.layers.9.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 12976128
},
{
"name": "model.layers.9.self_attn.qkv_proj.q_weight",
"shape": [
2560,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2621440,
"byteOffset": 12980224
},
{
"name": "model.layers.9.self_attn.qkv_proj.q_scale",
"shape": [
2560,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 327680,
"byteOffset": 15601664
},
{
"name": "model.layers.9.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 15929344
},
{
"name": "model.layers.9.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 18026496
},
{
"name": "model.norm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 18288640
}
],
"md5sum": "f3d45dacc534f3d71074aa3643a7860d"
}
]
}