Tai Truong
Add nb-llama-3.2-1B instruct model weights
9895f82
{
"metadata": {
"ParamSize": 163,
"ParamBytes": 695242752.0,
"BitsPerParam": 4.500628909972241
},
"records": [
{
"dataPath": "params_shard_0.bin",
"format": "raw-shard",
"nbytes": 131334144,
"records": [
{
"name": "model.embed_tokens.q_weight",
"shape": [
128256,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 131334144,
"byteOffset": 0
}
],
"md5sum": "8be0e3dab65f4c84b76a97120fc77fea"
},
{
"dataPath": "params_shard_1.bin",
"format": "raw-shard",
"nbytes": 16777216,
"records": [
{
"name": "model.layers.0.mlp.gate_up_proj.q_weight",
"shape": [
16384,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 0
}
],
"md5sum": "0a19e6cc58436034d275d86ce0da823c"
},
{
"dataPath": "params_shard_2.bin",
"format": "raw-shard",
"nbytes": 31498240,
"records": [
{
"name": "model.embed_tokens.q_scale",
"shape": [
128256,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 16416768,
"byteOffset": 0
},
{
"name": "model.layers.0.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 16416768
},
{
"name": "model.layers.0.mlp.down_proj.q_weight",
"shape": [
2048,
1024
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 16420864
},
{
"name": "model.layers.0.mlp.down_proj.q_scale",
"shape": [
2048,
256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 24809472
},
{
"name": "model.layers.0.mlp.gate_up_proj.q_scale",
"shape": [
16384,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 25858048
},
{
"name": "model.layers.0.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 27955200
},
{
"name": "model.layers.0.self_attn.qkv_proj.q_weight",
"shape": [
3072,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 27959296
},
{
"name": "model.layers.0.self_attn.qkv_proj.q_scale",
"shape": [
3072,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 393216,
"byteOffset": 31105024
}
],
"md5sum": "0f97dc24a0798ea12165ec223d611aa5"
},
{
"dataPath": "params_shard_3.bin",
"format": "raw-shard",
"nbytes": 30679040,
"records": [
{
"name": "model.layers.0.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 0
},
{
"name": "model.layers.0.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 2097152
},
{
"name": "model.layers.1.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 2359296
},
{
"name": "model.layers.1.mlp.down_proj.q_weight",
"shape": [
2048,
1024
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 2363392
},
{
"name": "model.layers.1.mlp.down_proj.q_scale",
"shape": [
2048,
256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 10752000
},
{
"name": "model.layers.1.mlp.gate_up_proj.q_weight",
"shape": [
16384,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 11800576
},
{
"name": "model.layers.1.mlp.gate_up_proj.q_scale",
"shape": [
16384,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 28577792
},
{
"name": "model.layers.1.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 30674944
}
],
"md5sum": "a92ac5d056252811a25b54eed4252c7e"
},
{
"dataPath": "params_shard_4.bin",
"format": "raw-shard",
"nbytes": 32116736,
"records": [
{
"name": "model.layers.1.self_attn.qkv_proj.q_weight",
"shape": [
3072,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 0
},
{
"name": "model.layers.1.self_attn.qkv_proj.q_scale",
"shape": [
3072,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 393216,
"byteOffset": 3145728
},
{
"name": "model.layers.1.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 3538944
},
{
"name": "model.layers.1.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 5636096
},
{
"name": "model.layers.10.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 5898240
},
{
"name": "model.layers.10.mlp.down_proj.q_weight",
"shape": [
2048,
1024
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 5902336
},
{
"name": "model.layers.10.mlp.down_proj.q_scale",
"shape": [
2048,
256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 14290944
},
{
"name": "model.layers.10.mlp.gate_up_proj.q_weight",
"shape": [
16384,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 15339520
}
],
"md5sum": "5f36409fe6516864981fdf6e8ae23082"
},
{
"dataPath": "params_shard_5.bin",
"format": "raw-shard",
"nbytes": 16777216,
"records": [
{
"name": "model.layers.11.mlp.gate_up_proj.q_weight",
"shape": [
16384,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 0
}
],
"md5sum": "e83d9bc3a342d5511505576cceb941f7"
},
{
"dataPath": "params_shard_6.bin",
"format": "raw-shard",
"nbytes": 25444352,
"records": [
{
"name": "model.layers.10.mlp.gate_up_proj.q_scale",
"shape": [
16384,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 0
},
{
"name": "model.layers.10.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 2097152
},
{
"name": "model.layers.10.self_attn.qkv_proj.q_weight",
"shape": [
3072,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 2101248
},
{
"name": "model.layers.10.self_attn.qkv_proj.q_scale",
"shape": [
3072,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 393216,
"byteOffset": 5246976
},
{
"name": "model.layers.10.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 5640192
},
{
"name": "model.layers.10.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 7737344
},
{
"name": "model.layers.11.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 7999488
},
{
"name": "model.layers.11.mlp.down_proj.q_weight",
"shape": [
2048,
1024
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 8003584
},
{
"name": "model.layers.11.mlp.down_proj.q_scale",
"shape": [
2048,
256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 16392192
},
{
"name": "model.layers.11.mlp.gate_up_proj.q_scale",
"shape": [
16384,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 17440768
},
{
"name": "model.layers.11.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 19537920
},
{
"name": "model.layers.11.self_attn.qkv_proj.q_weight",
"shape": [
3072,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 19542016
},
{
"name": "model.layers.11.self_attn.qkv_proj.q_scale",
"shape": [
3072,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 393216,
"byteOffset": 22687744
},
{
"name": "model.layers.11.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 23080960
},
{
"name": "model.layers.11.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 25178112
},
{
"name": "model.layers.12.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 25440256
}
],
"md5sum": "3e440b4f2200adc7a3588ea4dc632da0"
},
{
"dataPath": "params_shard_7.bin",
"format": "raw-shard",
"nbytes": 31854592,
"records": [
{
"name": "model.layers.12.mlp.down_proj.q_weight",
"shape": [
2048,
1024
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 0
},
{
"name": "model.layers.12.mlp.down_proj.q_scale",
"shape": [
2048,
256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 8388608
},
{
"name": "model.layers.12.mlp.gate_up_proj.q_weight",
"shape": [
16384,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 9437184
},
{
"name": "model.layers.12.mlp.gate_up_proj.q_scale",
"shape": [
16384,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 26214400
},
{
"name": "model.layers.12.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 28311552
},
{
"name": "model.layers.12.self_attn.qkv_proj.q_weight",
"shape": [
3072,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 28315648
},
{
"name": "model.layers.12.self_attn.qkv_proj.q_scale",
"shape": [
3072,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 393216,
"byteOffset": 31461376
}
],
"md5sum": "8bca338d6610d6c1524087a0f00074a8"
},
{
"dataPath": "params_shard_8.bin",
"format": "raw-shard",
"nbytes": 30679040,
"records": [
{
"name": "model.layers.12.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 0
},
{
"name": "model.layers.12.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 2097152
},
{
"name": "model.layers.13.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 2359296
},
{
"name": "model.layers.13.mlp.down_proj.q_weight",
"shape": [
2048,
1024
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 2363392
},
{
"name": "model.layers.13.mlp.down_proj.q_scale",
"shape": [
2048,
256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 10752000
},
{
"name": "model.layers.13.mlp.gate_up_proj.q_weight",
"shape": [
16384,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 11800576
},
{
"name": "model.layers.13.mlp.gate_up_proj.q_scale",
"shape": [
16384,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 28577792
},
{
"name": "model.layers.13.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 30674944
}
],
"md5sum": "c6f77056ef704f95e3dca4b6b5dec951"
},
{
"dataPath": "params_shard_9.bin",
"format": "raw-shard",
"nbytes": 32116736,
"records": [
{
"name": "model.layers.13.self_attn.qkv_proj.q_weight",
"shape": [
3072,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 0
},
{
"name": "model.layers.13.self_attn.qkv_proj.q_scale",
"shape": [
3072,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 393216,
"byteOffset": 3145728
},
{
"name": "model.layers.13.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 3538944
},
{
"name": "model.layers.13.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 5636096
},
{
"name": "model.layers.14.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 5898240
},
{
"name": "model.layers.14.mlp.down_proj.q_weight",
"shape": [
2048,
1024
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 5902336
},
{
"name": "model.layers.14.mlp.down_proj.q_scale",
"shape": [
2048,
256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 14290944
},
{
"name": "model.layers.14.mlp.gate_up_proj.q_weight",
"shape": [
16384,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 15339520
}
],
"md5sum": "1d0dc4f84739abfa743a5d7726e35c0c"
},
{
"dataPath": "params_shard_10.bin",
"format": "raw-shard",
"nbytes": 16777216,
"records": [
{
"name": "model.layers.15.mlp.gate_up_proj.q_weight",
"shape": [
16384,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 0
}
],
"md5sum": "81ddce529045e38abe6ca98149e35f97"
},
{
"dataPath": "params_shard_11.bin",
"format": "raw-shard",
"nbytes": 25444352,
"records": [
{
"name": "model.layers.14.mlp.gate_up_proj.q_scale",
"shape": [
16384,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 0
},
{
"name": "model.layers.14.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 2097152
},
{
"name": "model.layers.14.self_attn.qkv_proj.q_weight",
"shape": [
3072,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 2101248
},
{
"name": "model.layers.14.self_attn.qkv_proj.q_scale",
"shape": [
3072,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 393216,
"byteOffset": 5246976
},
{
"name": "model.layers.14.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 5640192
},
{
"name": "model.layers.14.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 7737344
},
{
"name": "model.layers.15.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 7999488
},
{
"name": "model.layers.15.mlp.down_proj.q_weight",
"shape": [
2048,
1024
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 8003584
},
{
"name": "model.layers.15.mlp.down_proj.q_scale",
"shape": [
2048,
256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 16392192
},
{
"name": "model.layers.15.mlp.gate_up_proj.q_scale",
"shape": [
16384,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 17440768
},
{
"name": "model.layers.15.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 19537920
},
{
"name": "model.layers.15.self_attn.qkv_proj.q_weight",
"shape": [
3072,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 19542016
},
{
"name": "model.layers.15.self_attn.qkv_proj.q_scale",
"shape": [
3072,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 393216,
"byteOffset": 22687744
},
{
"name": "model.layers.15.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 23080960
},
{
"name": "model.layers.15.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 25178112
},
{
"name": "model.layers.2.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 25440256
}
],
"md5sum": "37783616694768a98305daeb0968ad3a"
},
{
"dataPath": "params_shard_12.bin",
"format": "raw-shard",
"nbytes": 31854592,
"records": [
{
"name": "model.layers.2.mlp.down_proj.q_weight",
"shape": [
2048,
1024
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 0
},
{
"name": "model.layers.2.mlp.down_proj.q_scale",
"shape": [
2048,
256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 8388608
},
{
"name": "model.layers.2.mlp.gate_up_proj.q_weight",
"shape": [
16384,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 9437184
},
{
"name": "model.layers.2.mlp.gate_up_proj.q_scale",
"shape": [
16384,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 26214400
},
{
"name": "model.layers.2.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 28311552
},
{
"name": "model.layers.2.self_attn.qkv_proj.q_weight",
"shape": [
3072,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 28315648
},
{
"name": "model.layers.2.self_attn.qkv_proj.q_scale",
"shape": [
3072,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 393216,
"byteOffset": 31461376
}
],
"md5sum": "7109b908e8d670994194f42bde87c8b2"
},
{
"dataPath": "params_shard_13.bin",
"format": "raw-shard",
"nbytes": 30679040,
"records": [
{
"name": "model.layers.2.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 0
},
{
"name": "model.layers.2.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 2097152
},
{
"name": "model.layers.3.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 2359296
},
{
"name": "model.layers.3.mlp.down_proj.q_weight",
"shape": [
2048,
1024
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 2363392
},
{
"name": "model.layers.3.mlp.down_proj.q_scale",
"shape": [
2048,
256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 10752000
},
{
"name": "model.layers.3.mlp.gate_up_proj.q_weight",
"shape": [
16384,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 11800576
},
{
"name": "model.layers.3.mlp.gate_up_proj.q_scale",
"shape": [
16384,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 28577792
},
{
"name": "model.layers.3.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 30674944
}
],
"md5sum": "8d9d1470a81805f057a2243f4144c24f"
},
{
"dataPath": "params_shard_14.bin",
"format": "raw-shard",
"nbytes": 32116736,
"records": [
{
"name": "model.layers.3.self_attn.qkv_proj.q_weight",
"shape": [
3072,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 0
},
{
"name": "model.layers.3.self_attn.qkv_proj.q_scale",
"shape": [
3072,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 393216,
"byteOffset": 3145728
},
{
"name": "model.layers.3.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 3538944
},
{
"name": "model.layers.3.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 5636096
},
{
"name": "model.layers.4.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 5898240
},
{
"name": "model.layers.4.mlp.down_proj.q_weight",
"shape": [
2048,
1024
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 5902336
},
{
"name": "model.layers.4.mlp.down_proj.q_scale",
"shape": [
2048,
256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 14290944
},
{
"name": "model.layers.4.mlp.gate_up_proj.q_weight",
"shape": [
16384,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 15339520
}
],
"md5sum": "203a0aceb391eff8d558433e41645418"
},
{
"dataPath": "params_shard_15.bin",
"format": "raw-shard",
"nbytes": 16777216,
"records": [
{
"name": "model.layers.5.mlp.gate_up_proj.q_weight",
"shape": [
16384,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 0
}
],
"md5sum": "b9bceb7998287370a5d8cbfda4216f2e"
},
{
"dataPath": "params_shard_16.bin",
"format": "raw-shard",
"nbytes": 25444352,
"records": [
{
"name": "model.layers.4.mlp.gate_up_proj.q_scale",
"shape": [
16384,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 0
},
{
"name": "model.layers.4.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 2097152
},
{
"name": "model.layers.4.self_attn.qkv_proj.q_weight",
"shape": [
3072,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 2101248
},
{
"name": "model.layers.4.self_attn.qkv_proj.q_scale",
"shape": [
3072,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 393216,
"byteOffset": 5246976
},
{
"name": "model.layers.4.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 5640192
},
{
"name": "model.layers.4.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 7737344
},
{
"name": "model.layers.5.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 7999488
},
{
"name": "model.layers.5.mlp.down_proj.q_weight",
"shape": [
2048,
1024
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 8003584
},
{
"name": "model.layers.5.mlp.down_proj.q_scale",
"shape": [
2048,
256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 16392192
},
{
"name": "model.layers.5.mlp.gate_up_proj.q_scale",
"shape": [
16384,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 17440768
},
{
"name": "model.layers.5.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 19537920
},
{
"name": "model.layers.5.self_attn.qkv_proj.q_weight",
"shape": [
3072,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 19542016
},
{
"name": "model.layers.5.self_attn.qkv_proj.q_scale",
"shape": [
3072,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 393216,
"byteOffset": 22687744
},
{
"name": "model.layers.5.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 23080960
},
{
"name": "model.layers.5.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 25178112
},
{
"name": "model.layers.6.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 25440256
}
],
"md5sum": "fc0102cd5668a83e4075e5716d125a74"
},
{
"dataPath": "params_shard_17.bin",
"format": "raw-shard",
"nbytes": 31854592,
"records": [
{
"name": "model.layers.6.mlp.down_proj.q_weight",
"shape": [
2048,
1024
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 0
},
{
"name": "model.layers.6.mlp.down_proj.q_scale",
"shape": [
2048,
256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 8388608
},
{
"name": "model.layers.6.mlp.gate_up_proj.q_weight",
"shape": [
16384,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 9437184
},
{
"name": "model.layers.6.mlp.gate_up_proj.q_scale",
"shape": [
16384,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 26214400
},
{
"name": "model.layers.6.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 28311552
},
{
"name": "model.layers.6.self_attn.qkv_proj.q_weight",
"shape": [
3072,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 28315648
},
{
"name": "model.layers.6.self_attn.qkv_proj.q_scale",
"shape": [
3072,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 393216,
"byteOffset": 31461376
}
],
"md5sum": "f2d27d15e751b5290a1ab852e7973ec9"
},
{
"dataPath": "params_shard_18.bin",
"format": "raw-shard",
"nbytes": 30679040,
"records": [
{
"name": "model.layers.6.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 0
},
{
"name": "model.layers.6.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 2097152
},
{
"name": "model.layers.7.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 2359296
},
{
"name": "model.layers.7.mlp.down_proj.q_weight",
"shape": [
2048,
1024
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 2363392
},
{
"name": "model.layers.7.mlp.down_proj.q_scale",
"shape": [
2048,
256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 10752000
},
{
"name": "model.layers.7.mlp.gate_up_proj.q_weight",
"shape": [
16384,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 11800576
},
{
"name": "model.layers.7.mlp.gate_up_proj.q_scale",
"shape": [
16384,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 28577792
},
{
"name": "model.layers.7.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 30674944
}
],
"md5sum": "8fdd8dca9704ec0d73272b90ce86bd9b"
},
{
"dataPath": "params_shard_19.bin",
"format": "raw-shard",
"nbytes": 32116736,
"records": [
{
"name": "model.layers.7.self_attn.qkv_proj.q_weight",
"shape": [
3072,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 0
},
{
"name": "model.layers.7.self_attn.qkv_proj.q_scale",
"shape": [
3072,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 393216,
"byteOffset": 3145728
},
{
"name": "model.layers.7.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 3538944
},
{
"name": "model.layers.7.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 5636096
},
{
"name": "model.layers.8.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 5898240
},
{
"name": "model.layers.8.mlp.down_proj.q_weight",
"shape": [
2048,
1024
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 5902336
},
{
"name": "model.layers.8.mlp.down_proj.q_scale",
"shape": [
2048,
256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 14290944
},
{
"name": "model.layers.8.mlp.gate_up_proj.q_weight",
"shape": [
16384,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 15339520
}
],
"md5sum": "1d4ec38053b6fc193c16506ec356ef10"
},
{
"dataPath": "params_shard_20.bin",
"format": "raw-shard",
"nbytes": 16777216,
"records": [
{
"name": "model.layers.9.mlp.gate_up_proj.q_weight",
"shape": [
16384,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 0
}
],
"md5sum": "ef64f2ec0f30ddbcffa3e6c635900a3c"
},
{
"dataPath": "params_shard_21.bin",
"format": "raw-shard",
"nbytes": 25444352,
"records": [
{
"name": "model.layers.8.mlp.gate_up_proj.q_scale",
"shape": [
16384,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 0
},
{
"name": "model.layers.8.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 2097152
},
{
"name": "model.layers.8.self_attn.qkv_proj.q_weight",
"shape": [
3072,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 2101248
},
{
"name": "model.layers.8.self_attn.qkv_proj.q_scale",
"shape": [
3072,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 393216,
"byteOffset": 5246976
},
{
"name": "model.layers.8.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 5640192
},
{
"name": "model.layers.8.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 7737344
},
{
"name": "model.layers.9.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 7999488
},
{
"name": "model.layers.9.mlp.down_proj.q_weight",
"shape": [
2048,
1024
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 8003584
},
{
"name": "model.layers.9.mlp.down_proj.q_scale",
"shape": [
2048,
256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 16392192
},
{
"name": "model.layers.9.mlp.gate_up_proj.q_scale",
"shape": [
16384,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 17440768
},
{
"name": "model.layers.9.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 19537920
},
{
"name": "model.layers.9.self_attn.qkv_proj.q_weight",
"shape": [
3072,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 19542016
},
{
"name": "model.layers.9.self_attn.qkv_proj.q_scale",
"shape": [
3072,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 393216,
"byteOffset": 22687744
},
{
"name": "model.layers.9.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 23080960
},
{
"name": "model.layers.9.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 25178112
},
{
"name": "model.norm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 25440256
}
],
"md5sum": "724d790441913ab134430ec423263e43"
}
]
}