Hugging Face's logo

numen-tech
/
Llama-3-Instruct-8B-SPPO-Iter3-w3a16g40sym

Model card Files Community
Llama-3-Instruct-8B-SPPO-Iter3-w3a16g40sym / ndarray-cache.json
numen-tech's picture
numen-tech
Add weights
ba6f702
raw
history blame contribute delete
146 kB
{
"metadata": {
"ParamSize": 325,
"ParamBytes": 3631664128.0,
"BitsPerParam": 2.6739310072364444
},
"records": [
{
"dataPath": "params_shard_0.bin",
"format": "raw-shard",
"nbytes": 211365888,
"records": [
{
"name": "lm_head.q_weight",
"shape": [
128256,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 211365888,
"byteOffset": 0
}
],
"md5sum": "0348badaeb88067868f8f3e0d4f1b252"
},
{
"dataPath": "params_shard_1.bin",
"format": "raw-shard",
"nbytes": 23527424,
"records": [
{
"name": "model.layers.30.mlp.down_proj.q_weight",
"shape": [
4096,
1436
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 23527424,
"byteOffset": 0
}
],
"md5sum": "7687d5dd48e8c742f443c120b1f60177"
},
{
"dataPath": "params_shard_2.bin",
"format": "raw-shard",
"nbytes": 47251456,
"records": [
{
"name": "model.layers.30.mlp.gate_up_proj.q_weight",
"shape": [
28672,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 47251456,
"byteOffset": 0
}
],
"md5sum": "3a8d4ae0c3b0c7516609f72e2c3f328e"
},
{
"dataPath": "params_shard_3.bin",
"format": "raw-shard",
"nbytes": 29369856,
"records": [
{
"name": "lm_head.q_scale",
"shape": [
128256,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 26420736,
"byteOffset": 0
},
{
"name": "model.layers.30.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 26420736
},
{
"name": "model.layers.30.mlp.down_proj.q_scale",
"shape": [
4096,
359
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2940928,
"byteOffset": 26428928
}
],
"md5sum": "1ec83ba585a6a4dc29aed5b1a7f17df3"
},
{
"dataPath": "params_shard_4.bin",
"format": "raw-shard",
"nbytes": 23527424,
"records": [
{
"name": "model.layers.31.mlp.down_proj.q_weight",
"shape": [
4096,
1436
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 23527424,
"byteOffset": 0
}
],
"md5sum": "d684d2a4cbe42551ed54430962cd779f"
},
{
"dataPath": "params_shard_5.bin",
"format": "raw-shard",
"nbytes": 47251456,
"records": [
{
"name": "model.layers.31.mlp.gate_up_proj.q_weight",
"shape": [
28672,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 47251456,
"byteOffset": 0
}
],
"md5sum": "732233fe6acab8f7e173fde0652323f2"
},
{
"dataPath": "params_shard_6.bin",
"format": "raw-shard",
"nbytes": 27848704,
"records": [
{
"name": "model.layers.30.mlp.gate_up_proj.q_scale",
"shape": [
28672,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5906432,
"byteOffset": 0
},
{
"name": "model.layers.30.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 5906432
},
{
"name": "model.layers.30.self_attn.o_proj.q_weight",
"shape": [
4096,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6750208,
"byteOffset": 5914624
},
{
"name": "model.layers.30.self_attn.o_proj.q_scale",
"shape": [
4096,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 843776,
"byteOffset": 12664832
},
{
"name": "model.layers.30.self_attn.qkv_proj.q_weight",
"shape": [
6144,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 10125312,
"byteOffset": 13508608
},
{
"name": "model.layers.30.self_attn.qkv_proj.q_scale",
"shape": [
6144,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1265664,
"byteOffset": 23633920
},
{
"name": "model.layers.31.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24899584
},
{
"name": "model.layers.31.mlp.down_proj.q_scale",
"shape": [
4096,
359
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2940928,
"byteOffset": 24907776
}
],
"md5sum": "df5ece9420d5d43983c3b8a795f92faf"
},
{
"dataPath": "params_shard_7.bin",
"format": "raw-shard",
"nbytes": 211365888,
"records": [
{
"name": "model.embed_tokens.q_weight",
"shape": [
128256,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 211365888,
"byteOffset": 0
}
],
"md5sum": "b3eeac7c22a5ebbb89fbf94080c0b74a"
},
{
"dataPath": "params_shard_8.bin",
"format": "raw-shard",
"nbytes": 26420736,
"records": [
{
"name": "model.embed_tokens.q_scale",
"shape": [
128256,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 26420736,
"byteOffset": 0
}
],
"md5sum": "0a069d39d127484354689b48ed14b018"
},
{
"dataPath": "params_shard_9.bin",
"format": "raw-shard",
"nbytes": 23527424,
"records": [
{
"name": "model.layers.0.mlp.down_proj.q_weight",
"shape": [
4096,
1436
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 23527424,
"byteOffset": 0
}
],
"md5sum": "4bf18933df2be526060b5e67265ed12a"
},
{
"dataPath": "params_shard_10.bin",
"format": "raw-shard",
"nbytes": 47251456,
"records": [
{
"name": "model.layers.0.mlp.gate_up_proj.q_weight",
"shape": [
28672,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 47251456,
"byteOffset": 0
}
],
"md5sum": "af17a2c7685a20e4fe31916cf6912043"
},
{
"dataPath": "params_shard_11.bin",
"format": "raw-shard",
"nbytes": 27856896,
"records": [
{
"name": "model.layers.31.mlp.gate_up_proj.q_scale",
"shape": [
28672,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5906432,
"byteOffset": 0
},
{
"name": "model.layers.31.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 5906432
},
{
"name": "model.layers.31.self_attn.qkv_proj.q_weight",
"shape": [
6144,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 10125312,
"byteOffset": 5914624
},
{
"name": "model.layers.31.self_attn.qkv_proj.q_scale",
"shape": [
6144,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1265664,
"byteOffset": 16039936
},
{
"name": "model.layers.31.self_attn.o_proj.q_weight",
"shape": [
4096,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6750208,
"byteOffset": 17305600
},
{
"name": "model.layers.31.self_attn.o_proj.q_scale",
"shape": [
4096,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 843776,
"byteOffset": 24055808
},
{
"name": "model.norm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24899584
},
{
"name": "model.layers.0.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24907776
},
{
"name": "model.layers.0.mlp.down_proj.q_scale",
"shape": [
4096,
359
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2940928,
"byteOffset": 24915968
}
],
"md5sum": "27f9065b6b4996632632e97bcc4890d3"
},
{
"dataPath": "params_shard_12.bin",
"format": "raw-shard",
"nbytes": 23527424,
"records": [
{
"name": "model.layers.1.mlp.down_proj.q_weight",
"shape": [
4096,
1436
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 23527424,
"byteOffset": 0
}
],
"md5sum": "7e8056a78b10300ee5af3b0666e4a232"
},
{
"dataPath": "params_shard_13.bin",
"format": "raw-shard",
"nbytes": 47251456,
"records": [
{
"name": "model.layers.1.mlp.gate_up_proj.q_weight",
"shape": [
28672,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 47251456,
"byteOffset": 0
}
],
"md5sum": "4a1544aca48e8e160323f3b30fdb3131"
},
{
"dataPath": "params_shard_14.bin",
"format": "raw-shard",
"nbytes": 27848704,
"records": [
{
"name": "model.layers.0.mlp.gate_up_proj.q_scale",
"shape": [
28672,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5906432,
"byteOffset": 0
},
{
"name": "model.layers.0.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 5906432
},
{
"name": "model.layers.0.self_attn.qkv_proj.q_weight",
"shape": [
6144,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 10125312,
"byteOffset": 5914624
},
{
"name": "model.layers.0.self_attn.qkv_proj.q_scale",
"shape": [
6144,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1265664,
"byteOffset": 16039936
},
{
"name": "model.layers.0.self_attn.o_proj.q_weight",
"shape": [
4096,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6750208,
"byteOffset": 17305600
},
{
"name": "model.layers.0.self_attn.o_proj.q_scale",
"shape": [
4096,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 843776,
"byteOffset": 24055808
},
{
"name": "model.layers.1.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24899584
},
{
"name": "model.layers.1.mlp.down_proj.q_scale",
"shape": [
4096,
359
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2940928,
"byteOffset": 24907776
}
],
"md5sum": "c2a04aae2bd473e71e6e7f3ed861b684"
},
{
"dataPath": "params_shard_15.bin",
"format": "raw-shard",
"nbytes": 23527424,
"records": [
{
"name": "model.layers.2.mlp.down_proj.q_weight",
"shape": [
4096,
1436
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 23527424,
"byteOffset": 0
}
],
"md5sum": "ee3f5c84664ec6f0d11820c480a6aad7"
},
{
"dataPath": "params_shard_16.bin",
"format": "raw-shard",
"nbytes": 47251456,
"records": [
{
"name": "model.layers.2.mlp.gate_up_proj.q_weight",
"shape": [
28672,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 47251456,
"byteOffset": 0
}
],
"md5sum": "af0e87bc4aea7e5d08021c7460806841"
},
{
"dataPath": "params_shard_17.bin",
"format": "raw-shard",
"nbytes": 27848704,
"records": [
{
"name": "model.layers.1.mlp.gate_up_proj.q_scale",
"shape": [
28672,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5906432,
"byteOffset": 0
},
{
"name": "model.layers.1.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 5906432
},
{
"name": "model.layers.1.self_attn.qkv_proj.q_weight",
"shape": [
6144,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 10125312,
"byteOffset": 5914624
},
{
"name": "model.layers.1.self_attn.qkv_proj.q_scale",
"shape": [
6144,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1265664,
"byteOffset": 16039936
},
{
"name": "model.layers.1.self_attn.o_proj.q_weight",
"shape": [
4096,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6750208,
"byteOffset": 17305600
},
{
"name": "model.layers.1.self_attn.o_proj.q_scale",
"shape": [
4096,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 843776,
"byteOffset": 24055808
},
{
"name": "model.layers.2.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24899584
},
{
"name": "model.layers.2.mlp.down_proj.q_scale",
"shape": [
4096,
359
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2940928,
"byteOffset": 24907776
}
],
"md5sum": "4a447a30f820b8fd265eae3fb0f07b75"
},
{
"dataPath": "params_shard_18.bin",
"format": "raw-shard",
"nbytes": 23527424,
"records": [
{
"name": "model.layers.3.mlp.down_proj.q_weight",
"shape": [
4096,
1436
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 23527424,
"byteOffset": 0
}
],
"md5sum": "ff4a07a8f77777de3368cebe5154e003"
},
{
"dataPath": "params_shard_19.bin",
"format": "raw-shard",
"nbytes": 47251456,
"records": [
{
"name": "model.layers.3.mlp.gate_up_proj.q_weight",
"shape": [
28672,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 47251456,
"byteOffset": 0
}
],
"md5sum": "5ecda5583317359e6adb3ce389d7ba13"
},
{
"dataPath": "params_shard_20.bin",
"format": "raw-shard",
"nbytes": 27848704,
"records": [
{
"name": "model.layers.2.mlp.gate_up_proj.q_scale",
"shape": [
28672,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5906432,
"byteOffset": 0
},
{
"name": "model.layers.2.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 5906432
},
{
"name": "model.layers.2.self_attn.qkv_proj.q_weight",
"shape": [
6144,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 10125312,
"byteOffset": 5914624
},
{
"name": "model.layers.2.self_attn.qkv_proj.q_scale",
"shape": [
6144,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1265664,
"byteOffset": 16039936
},
{
"name": "model.layers.2.self_attn.o_proj.q_weight",
"shape": [
4096,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6750208,
"byteOffset": 17305600
},
{
"name": "model.layers.2.self_attn.o_proj.q_scale",
"shape": [
4096,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 843776,
"byteOffset": 24055808
},
{
"name": "model.layers.3.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24899584
},
{
"name": "model.layers.3.mlp.down_proj.q_scale",
"shape": [
4096,
359
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2940928,
"byteOffset": 24907776
}
],
"md5sum": "2a7a771e5b0263bbf533fa4008c88b99"
},
{
"dataPath": "params_shard_21.bin",
"format": "raw-shard",
"nbytes": 23527424,
"records": [
{
"name": "model.layers.4.mlp.down_proj.q_weight",
"shape": [
4096,
1436
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 23527424,
"byteOffset": 0
}
],
"md5sum": "6abb58eb566d009902a05dfd6c71a328"
},
{
"dataPath": "params_shard_22.bin",
"format": "raw-shard",
"nbytes": 47251456,
"records": [
{
"name": "model.layers.4.mlp.gate_up_proj.q_weight",
"shape": [
28672,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 47251456,
"byteOffset": 0
}
],
"md5sum": "d4b8ceb4fd7171cbe166e34d820a49bb"
},
{
"dataPath": "params_shard_23.bin",
"format": "raw-shard",
"nbytes": 27848704,
"records": [
{
"name": "model.layers.3.mlp.gate_up_proj.q_scale",
"shape": [
28672,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5906432,
"byteOffset": 0
},
{
"name": "model.layers.3.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 5906432
},
{
"name": "model.layers.3.self_attn.qkv_proj.q_weight",
"shape": [
6144,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 10125312,
"byteOffset": 5914624
},
{
"name": "model.layers.3.self_attn.qkv_proj.q_scale",
"shape": [
6144,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1265664,
"byteOffset": 16039936
},
{
"name": "model.layers.3.self_attn.o_proj.q_weight",
"shape": [
4096,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6750208,
"byteOffset": 17305600
},
{
"name": "model.layers.3.self_attn.o_proj.q_scale",
"shape": [
4096,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 843776,
"byteOffset": 24055808
},
{
"name": "model.layers.4.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24899584
},
{
"name": "model.layers.4.mlp.down_proj.q_scale",
"shape": [
4096,
359
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2940928,
"byteOffset": 24907776
}
],
"md5sum": "def0821224383e03ac86967b05e5cd2e"
},
{
"dataPath": "params_shard_24.bin",
"format": "raw-shard",
"nbytes": 23527424,
"records": [
{
"name": "model.layers.5.mlp.down_proj.q_weight",
"shape": [
4096,
1436
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 23527424,
"byteOffset": 0
}
],
"md5sum": "267053b0075731d6f829b6bd504f1a84"
},
{
"dataPath": "params_shard_25.bin",
"format": "raw-shard",
"nbytes": 47251456,
"records": [
{
"name": "model.layers.5.mlp.gate_up_proj.q_weight",
"shape": [
28672,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 47251456,
"byteOffset": 0
}
],
"md5sum": "d87170920c8c536d9ee348ed1276fea5"
},
{
"dataPath": "params_shard_26.bin",
"format": "raw-shard",
"nbytes": 27848704,
"records": [
{
"name": "model.layers.4.mlp.gate_up_proj.q_scale",
"shape": [
28672,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5906432,
"byteOffset": 0
},
{
"name": "model.layers.4.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 5906432
},
{
"name": "model.layers.4.self_attn.qkv_proj.q_weight",
"shape": [
6144,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 10125312,
"byteOffset": 5914624
},
{
"name": "model.layers.4.self_attn.qkv_proj.q_scale",
"shape": [
6144,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1265664,
"byteOffset": 16039936
},
{
"name": "model.layers.4.self_attn.o_proj.q_weight",
"shape": [
4096,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6750208,
"byteOffset": 17305600
},
{
"name": "model.layers.4.self_attn.o_proj.q_scale",
"shape": [
4096,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 843776,
"byteOffset": 24055808
},
{
"name": "model.layers.5.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24899584
},
{
"name": "model.layers.5.mlp.down_proj.q_scale",
"shape": [
4096,
359
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2940928,
"byteOffset": 24907776
}
],
"md5sum": "1d0c9f09c7c0a0a82582e69f3a1760b3"
},
{
"dataPath": "params_shard_27.bin",
"format": "raw-shard",
"nbytes": 23527424,
"records": [
{
"name": "model.layers.6.mlp.down_proj.q_weight",
"shape": [
4096,
1436
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 23527424,
"byteOffset": 0
}
],
"md5sum": "21e1225983818cec6f4dfad03cb9178b"
},
{
"dataPath": "params_shard_28.bin",
"format": "raw-shard",
"nbytes": 47251456,
"records": [
{
"name": "model.layers.6.mlp.gate_up_proj.q_weight",
"shape": [
28672,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 47251456,
"byteOffset": 0
}
],
"md5sum": "ee3fc557c75203e93bd0cca3dcbf01b0"
},
{
"dataPath": "params_shard_29.bin",
"format": "raw-shard",
"nbytes": 27848704,
"records": [
{
"name": "model.layers.5.mlp.gate_up_proj.q_scale",
"shape": [
28672,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5906432,
"byteOffset": 0
},
{
"name": "model.layers.5.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 5906432
},
{
"name": "model.layers.5.self_attn.qkv_proj.q_weight",
"shape": [
6144,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 10125312,
"byteOffset": 5914624
},
{
"name": "model.layers.5.self_attn.qkv_proj.q_scale",
"shape": [
6144,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1265664,
"byteOffset": 16039936
},
{
"name": "model.layers.5.self_attn.o_proj.q_weight",
"shape": [
4096,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6750208,
"byteOffset": 17305600
},
{
"name": "model.layers.5.self_attn.o_proj.q_scale",
"shape": [
4096,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 843776,
"byteOffset": 24055808
},
{
"name": "model.layers.6.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24899584
},
{
"name": "model.layers.6.mlp.down_proj.q_scale",
"shape": [
4096,
359
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2940928,
"byteOffset": 24907776
}
],
"md5sum": "cef41599586c4c716df3a8a24e761ed4"
},
{
"dataPath": "params_shard_30.bin",
"format": "raw-shard",
"nbytes": 23527424,
"records": [
{
"name": "model.layers.7.mlp.down_proj.q_weight",
"shape": [
4096,
1436
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 23527424,
"byteOffset": 0
}
],
"md5sum": "a2ca0d75885deef86e10ac031edaeebf"
},
{
"dataPath": "params_shard_31.bin",
"format": "raw-shard",
"nbytes": 47251456,
"records": [
{
"name": "model.layers.7.mlp.gate_up_proj.q_weight",
"shape": [
28672,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 47251456,
"byteOffset": 0
}
],
"md5sum": "ca2b706b7b056039cf0926e7b2c638a4"
},
{
"dataPath": "params_shard_32.bin",
"format": "raw-shard",
"nbytes": 27848704,
"records": [
{
"name": "model.layers.6.mlp.gate_up_proj.q_scale",
"shape": [
28672,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5906432,
"byteOffset": 0
},
{
"name": "model.layers.6.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 5906432
},
{
"name": "model.layers.6.self_attn.qkv_proj.q_weight",
"shape": [
6144,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 10125312,
"byteOffset": 5914624
},
{
"name": "model.layers.6.self_attn.qkv_proj.q_scale",
"shape": [
6144,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1265664,
"byteOffset": 16039936
},
{
"name": "model.layers.6.self_attn.o_proj.q_weight",
"shape": [
4096,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6750208,
"byteOffset": 17305600
},
{
"name": "model.layers.6.self_attn.o_proj.q_scale",
"shape": [
4096,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 843776,
"byteOffset": 24055808
},
{
"name": "model.layers.7.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24899584
},
{
"name": "model.layers.7.mlp.down_proj.q_scale",
"shape": [
4096,
359
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2940928,
"byteOffset": 24907776
}
],
"md5sum": "d9239bdf0d523a4cbc79de6b1f1cb561"
},
{
"dataPath": "params_shard_33.bin",
"format": "raw-shard",
"nbytes": 47251456,
"records": [
{
"name": "model.layers.8.mlp.gate_up_proj.q_weight",
"shape": [
28672,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 47251456,
"byteOffset": 0
}
],
"md5sum": "ae17e62710c1b9a6cb68b2b5a54b2528"
},
{
"dataPath": "params_shard_34.bin",
"format": "raw-shard",
"nbytes": 30806016,
"records": [
{
"name": "model.layers.7.mlp.gate_up_proj.q_scale",
"shape": [
28672,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5906432,
"byteOffset": 0
},
{
"name": "model.layers.7.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 5906432
},
{
"name": "model.layers.7.self_attn.qkv_proj.q_weight",
"shape": [
6144,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 10125312,
"byteOffset": 5914624
},
{
"name": "model.layers.7.self_attn.qkv_proj.q_scale",
"shape": [
6144,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1265664,
"byteOffset": 16039936
},
{
"name": "model.layers.7.self_attn.o_proj.q_weight",
"shape": [
4096,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6750208,
"byteOffset": 17305600
},
{
"name": "model.layers.7.self_attn.o_proj.q_scale",
"shape": [
4096,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 843776,
"byteOffset": 24055808
},
{
"name": "model.layers.8.mlp.gate_up_proj.q_scale",
"shape": [
28672,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5906432,
"byteOffset": 24899584
}
],
"md5sum": "74008f3d8a56dbb9efcee2c9180a51d8"
},
{
"dataPath": "params_shard_35.bin",
"format": "raw-shard",
"nbytes": 23527424,
"records": [
{
"name": "model.layers.10.mlp.down_proj.q_weight",
"shape": [
4096,
1436
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 23527424,
"byteOffset": 0
}
],
"md5sum": "b84dda4d3428e5f53577dc1aab3461e0"
},
{
"dataPath": "params_shard_36.bin",
"format": "raw-shard",
"nbytes": 47251456,
"records": [
{
"name": "model.layers.10.mlp.gate_up_proj.q_weight",
"shape": [
28672,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 47251456,
"byteOffset": 0
}
],
"md5sum": "4bf843856cfe85ba024e9d6dc7b2777d"
},
{
"dataPath": "params_shard_37.bin",
"format": "raw-shard",
"nbytes": 27848704,
"records": [
{
"name": "model.layers.8.self_attn.qkv_proj.q_weight",
"shape": [
6144,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 10125312,
"byteOffset": 0
},
{
"name": "model.layers.8.self_attn.qkv_proj.q_scale",
"shape": [
6144,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1265664,
"byteOffset": 10125312
},
{
"name": "model.layers.8.self_attn.o_proj.q_weight",
"shape": [
4096,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6750208,
"byteOffset": 11390976
},
{
"name": "model.layers.8.self_attn.o_proj.q_scale",
"shape": [
4096,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 843776,
"byteOffset": 18141184
},
{
"name": "model.layers.10.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 18984960
},
{
"name": "model.layers.10.mlp.down_proj.q_scale",
"shape": [
4096,
359
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2940928,
"byteOffset": 18993152
},
{
"name": "model.layers.10.mlp.gate_up_proj.q_scale",
"shape": [
28672,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5906432,
"byteOffset": 21934080
},
{
"name": "model.layers.10.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 27840512
}
],
"md5sum": "5707e41eda7c1c10c0293791f83213c5"
},
{
"dataPath": "params_shard_38.bin",
"format": "raw-shard",
"nbytes": 23527424,
"records": [
{
"name": "model.layers.11.mlp.down_proj.q_weight",
"shape": [
4096,
1436
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 23527424,
"byteOffset": 0
}
],
"md5sum": "6d106e06f2ff173632190c3521775aa6"
},
{
"dataPath": "params_shard_39.bin",
"format": "raw-shard",
"nbytes": 47251456,
"records": [
{
"name": "model.layers.11.mlp.gate_up_proj.q_weight",
"shape": [
28672,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 47251456,
"byteOffset": 0
}
],
"md5sum": "24c53847db01da9dab89da7a29095c49"
},
{
"dataPath": "params_shard_40.bin",
"format": "raw-shard",
"nbytes": 27848704,
"records": [
{
"name": "model.layers.10.self_attn.qkv_proj.q_weight",
"shape": [
6144,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 10125312,
"byteOffset": 0
},
{
"name": "model.layers.10.self_attn.qkv_proj.q_scale",
"shape": [
6144,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1265664,
"byteOffset": 10125312
},
{
"name": "model.layers.10.self_attn.o_proj.q_weight",
"shape": [
4096,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6750208,
"byteOffset": 11390976
},
{
"name": "model.layers.10.self_attn.o_proj.q_scale",
"shape": [
4096,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 843776,
"byteOffset": 18141184
},
{
"name": "model.layers.11.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 18984960
},
{
"name": "model.layers.11.mlp.down_proj.q_scale",
"shape": [
4096,
359
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2940928,
"byteOffset": 18993152
},
{
"name": "model.layers.11.mlp.gate_up_proj.q_scale",
"shape": [
28672,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5906432,
"byteOffset": 21934080
},
{
"name": "model.layers.11.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 27840512
}
],
"md5sum": "ab2282f98345eac3f23cca5292b0f703"
},
{
"dataPath": "params_shard_41.bin",
"format": "raw-shard",
"nbytes": 23527424,
"records": [
{
"name": "model.layers.12.mlp.down_proj.q_weight",
"shape": [
4096,
1436
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 23527424,
"byteOffset": 0
}
],
"md5sum": "8aa8ac29d5e64091cf67db0debbcf87a"
},
{
"dataPath": "params_shard_42.bin",
"format": "raw-shard",
"nbytes": 47251456,
"records": [
{
"name": "model.layers.12.mlp.gate_up_proj.q_weight",
"shape": [
28672,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 47251456,
"byteOffset": 0
}
],
"md5sum": "033d31105ae8de0ff6fea30750d657db"
},
{
"dataPath": "params_shard_43.bin",
"format": "raw-shard",
"nbytes": 27848704,
"records": [
{
"name": "model.layers.11.self_attn.qkv_proj.q_weight",
"shape": [
6144,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 10125312,
"byteOffset": 0
},
{
"name": "model.layers.11.self_attn.qkv_proj.q_scale",
"shape": [
6144,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1265664,
"byteOffset": 10125312
},
{
"name": "model.layers.11.self_attn.o_proj.q_weight",
"shape": [
4096,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6750208,
"byteOffset": 11390976
},
{
"name": "model.layers.11.self_attn.o_proj.q_scale",
"shape": [
4096,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 843776,
"byteOffset": 18141184
},
{
"name": "model.layers.12.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 18984960
},
{
"name": "model.layers.12.mlp.down_proj.q_scale",
"shape": [
4096,
359
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2940928,
"byteOffset": 18993152
},
{
"name": "model.layers.12.mlp.gate_up_proj.q_scale",
"shape": [
28672,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5906432,
"byteOffset": 21934080
},
{
"name": "model.layers.12.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 27840512
}
],
"md5sum": "5b45ba331908b5e90b47998aaaca2bce"
},
{
"dataPath": "params_shard_44.bin",
"format": "raw-shard",
"nbytes": 23527424,
"records": [
{
"name": "model.layers.13.mlp.down_proj.q_weight",
"shape": [
4096,
1436
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 23527424,
"byteOffset": 0
}
],
"md5sum": "805aa10d58f6823bf6e6d629fb242236"
},
{
"dataPath": "params_shard_45.bin",
"format": "raw-shard",
"nbytes": 47251456,
"records": [
{
"name": "model.layers.13.mlp.gate_up_proj.q_weight",
"shape": [
28672,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 47251456,
"byteOffset": 0
}
],
"md5sum": "185905ac4df2f25e4a2c711f8204f9d4"
},
{
"dataPath": "params_shard_46.bin",
"format": "raw-shard",
"nbytes": 27848704,
"records": [
{
"name": "model.layers.12.self_attn.qkv_proj.q_weight",
"shape": [
6144,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 10125312,
"byteOffset": 0
},
{
"name": "model.layers.12.self_attn.qkv_proj.q_scale",
"shape": [
6144,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1265664,
"byteOffset": 10125312
},
{
"name": "model.layers.12.self_attn.o_proj.q_weight",
"shape": [
4096,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6750208,
"byteOffset": 11390976
},
{
"name": "model.layers.12.self_attn.o_proj.q_scale",
"shape": [
4096,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 843776,
"byteOffset": 18141184
},
{
"name": "model.layers.13.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 18984960
},
{
"name": "model.layers.13.mlp.down_proj.q_scale",
"shape": [
4096,
359
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2940928,
"byteOffset": 18993152
},
{
"name": "model.layers.13.mlp.gate_up_proj.q_scale",
"shape": [
28672,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5906432,
"byteOffset": 21934080
},
{
"name": "model.layers.13.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 27840512
}
],
"md5sum": "719d3902411f8bd213947d95caffc2a6"
},
{
"dataPath": "params_shard_47.bin",
"format": "raw-shard",
"nbytes": 23527424,
"records": [
{
"name": "model.layers.14.mlp.down_proj.q_weight",
"shape": [
4096,
1436
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 23527424,
"byteOffset": 0
}
],
"md5sum": "143b3bb0f904f6d53c28a8ec7e85ae32"
},
{
"dataPath": "params_shard_48.bin",
"format": "raw-shard",
"nbytes": 47251456,
"records": [
{
"name": "model.layers.14.mlp.gate_up_proj.q_weight",
"shape": [
28672,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 47251456,
"byteOffset": 0
}
],
"md5sum": "8f4453a9a1e80b31e77fa1bbad9417d3"
},
{
"dataPath": "params_shard_49.bin",
"format": "raw-shard",
"nbytes": 27848704,
"records": [
{
"name": "model.layers.13.self_attn.qkv_proj.q_weight",
"shape": [
6144,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 10125312,
"byteOffset": 0
},
{
"name": "model.layers.13.self_attn.qkv_proj.q_scale",
"shape": [
6144,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1265664,
"byteOffset": 10125312
},
{
"name": "model.layers.13.self_attn.o_proj.q_weight",
"shape": [
4096,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6750208,
"byteOffset": 11390976
},
{
"name": "model.layers.13.self_attn.o_proj.q_scale",
"shape": [
4096,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 843776,
"byteOffset": 18141184
},
{
"name": "model.layers.14.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 18984960
},
{
"name": "model.layers.14.mlp.down_proj.q_scale",
"shape": [
4096,
359
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2940928,
"byteOffset": 18993152
},
{
"name": "model.layers.14.mlp.gate_up_proj.q_scale",
"shape": [
28672,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5906432,
"byteOffset": 21934080
},
{
"name": "model.layers.14.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 27840512
}
],
"md5sum": "1b49b06691bd7b9ba08c2f2f64639b9a"
},
{
"dataPath": "params_shard_50.bin",
"format": "raw-shard",
"nbytes": 23527424,
"records": [
{
"name": "model.layers.15.mlp.down_proj.q_weight",
"shape": [
4096,
1436
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 23527424,
"byteOffset": 0
}
],
"md5sum": "231fb376deb96a09682c99f5c2f0ddf6"
},
{
"dataPath": "params_shard_51.bin",
"format": "raw-shard",
"nbytes": 47251456,
"records": [
{
"name": "model.layers.15.mlp.gate_up_proj.q_weight",
"shape": [
28672,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 47251456,
"byteOffset": 0
}
],
"md5sum": "9dd5985c4ff2b7d3de6a3a4c6e5acd52"
},
{
"dataPath": "params_shard_52.bin",
"format": "raw-shard",
"nbytes": 27848704,
"records": [
{
"name": "model.layers.14.self_attn.qkv_proj.q_weight",
"shape": [
6144,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 10125312,
"byteOffset": 0
},
{
"name": "model.layers.14.self_attn.qkv_proj.q_scale",
"shape": [
6144,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1265664,
"byteOffset": 10125312
},
{
"name": "model.layers.14.self_attn.o_proj.q_weight",
"shape": [
4096,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6750208,
"byteOffset": 11390976
},
{
"name": "model.layers.14.self_attn.o_proj.q_scale",
"shape": [
4096,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 843776,
"byteOffset": 18141184
},
{
"name": "model.layers.15.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 18984960
},
{
"name": "model.layers.15.mlp.down_proj.q_scale",
"shape": [
4096,
359
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2940928,
"byteOffset": 18993152
},
{
"name": "model.layers.15.mlp.gate_up_proj.q_scale",
"shape": [
28672,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5906432,
"byteOffset": 21934080
},
{
"name": "model.layers.15.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 27840512
}
],
"md5sum": "8f3b7ef852554d1dc198c33e7c98a0d5"
},
{
"dataPath": "params_shard_53.bin",
"format": "raw-shard",
"nbytes": 23527424,
"records": [
{
"name": "model.layers.16.mlp.down_proj.q_weight",
"shape": [
4096,
1436
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 23527424,
"byteOffset": 0
}
],
"md5sum": "d970261894d2bfb09964ba16ae6346d3"
},
{
"dataPath": "params_shard_54.bin",
"format": "raw-shard",
"nbytes": 47251456,
"records": [
{
"name": "model.layers.16.mlp.gate_up_proj.q_weight",
"shape": [
28672,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 47251456,
"byteOffset": 0
}
],
"md5sum": "838a09859400105d593a9f3035dcf8db"
},
{
"dataPath": "params_shard_55.bin",
"format": "raw-shard",
"nbytes": 27848704,
"records": [
{
"name": "model.layers.15.self_attn.qkv_proj.q_weight",
"shape": [
6144,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 10125312,
"byteOffset": 0
},
{
"name": "model.layers.15.self_attn.qkv_proj.q_scale",
"shape": [
6144,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1265664,
"byteOffset": 10125312
},
{
"name": "model.layers.15.self_attn.o_proj.q_weight",
"shape": [
4096,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6750208,
"byteOffset": 11390976
},
{
"name": "model.layers.15.self_attn.o_proj.q_scale",
"shape": [
4096,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 843776,
"byteOffset": 18141184
},
{
"name": "model.layers.16.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 18984960
},
{
"name": "model.layers.16.mlp.down_proj.q_scale",
"shape": [
4096,
359
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2940928,
"byteOffset": 18993152
},
{
"name": "model.layers.16.mlp.gate_up_proj.q_scale",
"shape": [
28672,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5906432,
"byteOffset": 21934080
},
{
"name": "model.layers.16.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 27840512
}
],
"md5sum": "b302947b0beed3be764468d1b21b05e0"
},
{
"dataPath": "params_shard_56.bin",
"format": "raw-shard",
"nbytes": 23527424,
"records": [
{
"name": "model.layers.17.mlp.down_proj.q_weight",
"shape": [
4096,
1436
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 23527424,
"byteOffset": 0
}
],
"md5sum": "8afaa3c99889d3f32c264059ef3f8229"
},
{
"dataPath": "params_shard_57.bin",
"format": "raw-shard",
"nbytes": 47251456,
"records": [
{
"name": "model.layers.17.mlp.gate_up_proj.q_weight",
"shape": [
28672,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 47251456,
"byteOffset": 0
}
],
"md5sum": "25f0ba28d6e12311eacd41d6a9267ae8"
},
{
"dataPath": "params_shard_58.bin",
"format": "raw-shard",
"nbytes": 27848704,
"records": [
{
"name": "model.layers.16.self_attn.qkv_proj.q_weight",
"shape": [
6144,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 10125312,
"byteOffset": 0
},
{
"name": "model.layers.16.self_attn.qkv_proj.q_scale",
"shape": [
6144,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1265664,
"byteOffset": 10125312
},
{
"name": "model.layers.16.self_attn.o_proj.q_weight",
"shape": [
4096,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6750208,
"byteOffset": 11390976
},
{
"name": "model.layers.16.self_attn.o_proj.q_scale",
"shape": [
4096,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 843776,
"byteOffset": 18141184
},
{
"name": "model.layers.17.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 18984960
},
{
"name": "model.layers.17.mlp.down_proj.q_scale",
"shape": [
4096,
359
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2940928,
"byteOffset": 18993152
},
{
"name": "model.layers.17.mlp.gate_up_proj.q_scale",
"shape": [
28672,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5906432,
"byteOffset": 21934080
},
{
"name": "model.layers.17.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 27840512
}
],
"md5sum": "f35af49f73ca85a00d86eb3aa14897a4"
},
{
"dataPath": "params_shard_59.bin",
"format": "raw-shard",
"nbytes": 23527424,
"records": [
{
"name": "model.layers.18.mlp.down_proj.q_weight",
"shape": [
4096,
1436
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 23527424,
"byteOffset": 0
}
],
"md5sum": "e5e685bb43ad4d1ee13cc975d418a41c"
},
{
"dataPath": "params_shard_60.bin",
"format": "raw-shard",
"nbytes": 47251456,
"records": [
{
"name": "model.layers.18.mlp.gate_up_proj.q_weight",
"shape": [
28672,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 47251456,
"byteOffset": 0
}
],
"md5sum": "9514313e275aa64a9b7f69e6ac8e0fcc"
},
{
"dataPath": "params_shard_61.bin",
"format": "raw-shard",
"nbytes": 27848704,
"records": [
{
"name": "model.layers.17.self_attn.qkv_proj.q_weight",
"shape": [
6144,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 10125312,
"byteOffset": 0
},
{
"name": "model.layers.17.self_attn.qkv_proj.q_scale",
"shape": [
6144,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1265664,
"byteOffset": 10125312
},
{
"name": "model.layers.17.self_attn.o_proj.q_weight",
"shape": [
4096,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6750208,
"byteOffset": 11390976
},
{
"name": "model.layers.17.self_attn.o_proj.q_scale",
"shape": [
4096,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 843776,
"byteOffset": 18141184
},
{
"name": "model.layers.18.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 18984960
},
{
"name": "model.layers.18.mlp.down_proj.q_scale",
"shape": [
4096,
359
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2940928,
"byteOffset": 18993152
},
{
"name": "model.layers.18.mlp.gate_up_proj.q_scale",
"shape": [
28672,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5906432,
"byteOffset": 21934080
},
{
"name": "model.layers.18.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 27840512
}
],
"md5sum": "b8f23eb8fe2c17d3bfa2afec25a67d08"
},
{
"dataPath": "params_shard_62.bin",
"format": "raw-shard",
"nbytes": 30375936,
"records": [
{
"name": "model.layers.18.self_attn.qkv_proj.q_weight",
"shape": [
6144,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 10125312,
"byteOffset": 0
},
{
"name": "model.layers.18.self_attn.qkv_proj.q_scale",
"shape": [
6144,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1265664,
"byteOffset": 10125312
},
{
"name": "model.layers.18.self_attn.o_proj.q_weight",
"shape": [
4096,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6750208,
"byteOffset": 11390976
},
{
"name": "model.layers.18.self_attn.o_proj.q_scale",
"shape": [
4096,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 843776,
"byteOffset": 18141184
},
{
"name": "model.layers.19.self_attn.qkv_proj.q_weight",
"shape": [
6144,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 10125312,
"byteOffset": 18984960
},
{
"name": "model.layers.19.self_attn.qkv_proj.q_scale",
"shape": [
6144,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1265664,
"byteOffset": 29110272
}
],
"md5sum": "9e1e211667e0c9bb614627a826d461cb"
},
{
"dataPath": "params_shard_63.bin",
"format": "raw-shard",
"nbytes": 31129600,
"records": [
{
"name": "model.layers.19.self_attn.o_proj.q_weight",
"shape": [
4096,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6750208,
"byteOffset": 0
},
{
"name": "model.layers.19.self_attn.o_proj.q_scale",
"shape": [
4096,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 843776,
"byteOffset": 6750208
},
{
"name": "model.layers.8.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 7593984
},
{
"name": "model.layers.8.mlp.down_proj.q_weight",
"shape": [
4096,
1436
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 23527424,
"byteOffset": 7602176
}
],
"md5sum": "4b9c03832fe0a89fc71602b35087f173"
},
{
"dataPath": "params_shard_64.bin",
"format": "raw-shard",
"nbytes": 47251456,
"records": [
{
"name": "model.layers.9.mlp.gate_up_proj.q_weight",
"shape": [
28672,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 47251456,
"byteOffset": 0
}
],
"md5sum": "e0fdb153f3f1613e8a4330b33612c904"
},
{
"dataPath": "params_shard_65.bin",
"format": "raw-shard",
"nbytes": 29425664,
"records": [
{
"name": "model.layers.8.mlp.down_proj.q_scale",
"shape": [
4096,
359
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2940928,
"byteOffset": 0
},
{
"name": "model.layers.8.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 2940928
},
{
"name": "model.layers.9.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 2949120
},
{
"name": "model.layers.9.mlp.down_proj.q_weight",
"shape": [
4096,
1436
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 23527424,
"byteOffset": 2957312
},
{
"name": "model.layers.9.mlp.down_proj.q_scale",
"shape": [
4096,
359
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2940928,
"byteOffset": 26484736
}
],
"md5sum": "613e881914381c55022c952edad29330"
},
{
"dataPath": "params_shard_66.bin",
"format": "raw-shard",
"nbytes": 23527424,
"records": [
{
"name": "model.layers.19.mlp.down_proj.q_weight",
"shape": [
4096,
1436
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 23527424,
"byteOffset": 0
}
],
"md5sum": "1252a27fa1dcda84cad81b364034edcc"
},
{
"dataPath": "params_shard_67.bin",
"format": "raw-shard",
"nbytes": 47251456,
"records": [
{
"name": "model.layers.19.mlp.gate_up_proj.q_weight",
"shape": [
28672,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 47251456,
"byteOffset": 0
}
],
"md5sum": "598d2c76afba85ed48940e045bd9cd13"
},
{
"dataPath": "params_shard_68.bin",
"format": "raw-shard",
"nbytes": 27848704,
"records": [
{
"name": "model.layers.9.mlp.gate_up_proj.q_scale",
"shape": [
28672,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5906432,
"byteOffset": 0
},
{
"name": "model.layers.9.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 5906432
},
{
"name": "model.layers.9.self_attn.qkv_proj.q_weight",
"shape": [
6144,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 10125312,
"byteOffset": 5914624
},
{
"name": "model.layers.9.self_attn.qkv_proj.q_scale",
"shape": [
6144,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1265664,
"byteOffset": 16039936
},
{
"name": "model.layers.9.self_attn.o_proj.q_weight",
"shape": [
4096,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6750208,
"byteOffset": 17305600
},
{
"name": "model.layers.9.self_attn.o_proj.q_scale",
"shape": [
4096,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 843776,
"byteOffset": 24055808
},
{
"name": "model.layers.19.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24899584
},
{
"name": "model.layers.19.mlp.down_proj.q_scale",
"shape": [
4096,
359
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2940928,
"byteOffset": 24907776
}
],
"md5sum": "380da83cd98f3870ca395b60d3bcb9cf"
},
{
"dataPath": "params_shard_69.bin",
"format": "raw-shard",
"nbytes": 47251456,
"records": [
{
"name": "model.layers.20.mlp.gate_up_proj.q_weight",
"shape": [
28672,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 47251456,
"byteOffset": 0
}
],
"md5sum": "4d40989c387e16fea2a3fdaf3980be3b"
},
{
"dataPath": "params_shard_70.bin",
"format": "raw-shard",
"nbytes": 32391168,
"records": [
{
"name": "model.layers.19.mlp.gate_up_proj.q_scale",
"shape": [
28672,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5906432,
"byteOffset": 0
},
{
"name": "model.layers.19.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 5906432
},
{
"name": "model.layers.20.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 5914624
},
{
"name": "model.layers.20.mlp.down_proj.q_weight",
"shape": [
4096,
1436
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 23527424,
"byteOffset": 5922816
},
{
"name": "model.layers.20.mlp.down_proj.q_scale",
"shape": [
4096,
359
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2940928,
"byteOffset": 29450240
}
],
"md5sum": "b102ab13814711be4a29770f97704c59"
},
{
"dataPath": "params_shard_71.bin",
"format": "raw-shard",
"nbytes": 23527424,
"records": [
{
"name": "model.layers.21.mlp.down_proj.q_weight",
"shape": [
4096,
1436
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 23527424,
"byteOffset": 0
}
],
"md5sum": "2f1962b749de300956876b447fb4edd1"
},
{
"dataPath": "params_shard_72.bin",
"format": "raw-shard",
"nbytes": 47251456,
"records": [
{
"name": "model.layers.21.mlp.gate_up_proj.q_weight",
"shape": [
28672,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 47251456,
"byteOffset": 0
}
],
"md5sum": "98c92ce5e0c63c53e7cb8256ae703800"
},
{
"dataPath": "params_shard_73.bin",
"format": "raw-shard",
"nbytes": 27848704,
"records": [
{
"name": "model.layers.20.mlp.gate_up_proj.q_scale",
"shape": [
28672,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5906432,
"byteOffset": 0
},
{
"name": "model.layers.20.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 5906432
},
{
"name": "model.layers.20.self_attn.qkv_proj.q_weight",
"shape": [
6144,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 10125312,
"byteOffset": 5914624
},
{
"name": "model.layers.20.self_attn.qkv_proj.q_scale",
"shape": [
6144,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1265664,
"byteOffset": 16039936
},
{
"name": "model.layers.20.self_attn.o_proj.q_weight",
"shape": [
4096,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6750208,
"byteOffset": 17305600
},
{
"name": "model.layers.20.self_attn.o_proj.q_scale",
"shape": [
4096,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 843776,
"byteOffset": 24055808
},
{
"name": "model.layers.21.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24899584
},
{
"name": "model.layers.21.mlp.down_proj.q_scale",
"shape": [
4096,
359
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2940928,
"byteOffset": 24907776
}
],
"md5sum": "bed7bef98f7d046bf7415f496083320f"
},
{
"dataPath": "params_shard_74.bin",
"format": "raw-shard",
"nbytes": 23527424,
"records": [
{
"name": "model.layers.22.mlp.down_proj.q_weight",
"shape": [
4096,
1436
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 23527424,
"byteOffset": 0
}
],
"md5sum": "3635abf4c0f36a59e0d429e8937e891d"
},
{
"dataPath": "params_shard_75.bin",
"format": "raw-shard",
"nbytes": 47251456,
"records": [
{
"name": "model.layers.22.mlp.gate_up_proj.q_weight",
"shape": [
28672,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 47251456,
"byteOffset": 0
}
],
"md5sum": "2167c0eb1f118e534151f26cb4f82949"
},
{
"dataPath": "params_shard_76.bin",
"format": "raw-shard",
"nbytes": 27848704,
"records": [
{
"name": "model.layers.21.mlp.gate_up_proj.q_scale",
"shape": [
28672,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5906432,
"byteOffset": 0
},
{
"name": "model.layers.21.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 5906432
},
{
"name": "model.layers.21.self_attn.qkv_proj.q_weight",
"shape": [
6144,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 10125312,
"byteOffset": 5914624
},
{
"name": "model.layers.21.self_attn.qkv_proj.q_scale",
"shape": [
6144,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1265664,
"byteOffset": 16039936
},
{
"name": "model.layers.21.self_attn.o_proj.q_weight",
"shape": [
4096,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6750208,
"byteOffset": 17305600
},
{
"name": "model.layers.21.self_attn.o_proj.q_scale",
"shape": [
4096,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 843776,
"byteOffset": 24055808
},
{
"name": "model.layers.22.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24899584
},
{
"name": "model.layers.22.mlp.down_proj.q_scale",
"shape": [
4096,
359
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2940928,
"byteOffset": 24907776
}
],
"md5sum": "88e825afc00112c6bb4c3b58c036313f"
},
{
"dataPath": "params_shard_77.bin",
"format": "raw-shard",
"nbytes": 23527424,
"records": [
{
"name": "model.layers.23.mlp.down_proj.q_weight",
"shape": [
4096,
1436
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 23527424,
"byteOffset": 0
}
],
"md5sum": "7642a7fac421aa580952f394783800bd"
},
{
"dataPath": "params_shard_78.bin",
"format": "raw-shard",
"nbytes": 47251456,
"records": [
{
"name": "model.layers.23.mlp.gate_up_proj.q_weight",
"shape": [
28672,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 47251456,
"byteOffset": 0
}
],
"md5sum": "235336f8578c2b9efee6b860fa728b4c"
},
{
"dataPath": "params_shard_79.bin",
"format": "raw-shard",
"nbytes": 27848704,
"records": [
{
"name": "model.layers.22.mlp.gate_up_proj.q_scale",
"shape": [
28672,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5906432,
"byteOffset": 0
},
{
"name": "model.layers.22.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 5906432
},
{
"name": "model.layers.22.self_attn.qkv_proj.q_weight",
"shape": [
6144,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 10125312,
"byteOffset": 5914624
},
{
"name": "model.layers.22.self_attn.qkv_proj.q_scale",
"shape": [
6144,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1265664,
"byteOffset": 16039936
},
{
"name": "model.layers.22.self_attn.o_proj.q_weight",
"shape": [
4096,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6750208,
"byteOffset": 17305600
},
{
"name": "model.layers.22.self_attn.o_proj.q_scale",
"shape": [
4096,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 843776,
"byteOffset": 24055808
},
{
"name": "model.layers.23.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24899584
},
{
"name": "model.layers.23.mlp.down_proj.q_scale",
"shape": [
4096,
359
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2940928,
"byteOffset": 24907776
}
],
"md5sum": "a5d9703d75e4234a301ec5995e4ac8ed"
},
{
"dataPath": "params_shard_80.bin",
"format": "raw-shard",
"nbytes": 23527424,
"records": [
{
"name": "model.layers.24.mlp.down_proj.q_weight",
"shape": [
4096,
1436
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 23527424,
"byteOffset": 0
}
],
"md5sum": "544a70b3be5cdd7a4c88a12b6c633fa5"
},
{
"dataPath": "params_shard_81.bin",
"format": "raw-shard",
"nbytes": 47251456,
"records": [
{
"name": "model.layers.24.mlp.gate_up_proj.q_weight",
"shape": [
28672,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 47251456,
"byteOffset": 0
}
],
"md5sum": "50a31f775b64dce52c3b1b87f24941f1"
},
{
"dataPath": "params_shard_82.bin",
"format": "raw-shard",
"nbytes": 27848704,
"records": [
{
"name": "model.layers.23.mlp.gate_up_proj.q_scale",
"shape": [
28672,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5906432,
"byteOffset": 0
},
{
"name": "model.layers.23.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 5906432
},
{
"name": "model.layers.23.self_attn.qkv_proj.q_weight",
"shape": [
6144,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 10125312,
"byteOffset": 5914624
},
{
"name": "model.layers.23.self_attn.qkv_proj.q_scale",
"shape": [
6144,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1265664,
"byteOffset": 16039936
},
{
"name": "model.layers.23.self_attn.o_proj.q_weight",
"shape": [
4096,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6750208,
"byteOffset": 17305600
},
{
"name": "model.layers.23.self_attn.o_proj.q_scale",
"shape": [
4096,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 843776,
"byteOffset": 24055808
},
{
"name": "model.layers.24.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24899584
},
{
"name": "model.layers.24.mlp.down_proj.q_scale",
"shape": [
4096,
359
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2940928,
"byteOffset": 24907776
}
],
"md5sum": "3c918aac754bc7b29f94da8452865da0"
},
{
"dataPath": "params_shard_83.bin",
"format": "raw-shard",
"nbytes": 23527424,
"records": [
{
"name": "model.layers.25.mlp.down_proj.q_weight",
"shape": [
4096,
1436
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 23527424,
"byteOffset": 0
}
],
"md5sum": "8ddb6600583163f95533bee5ef864cfd"
},
{
"dataPath": "params_shard_84.bin",
"format": "raw-shard",
"nbytes": 47251456,
"records": [
{
"name": "model.layers.25.mlp.gate_up_proj.q_weight",
"shape": [
28672,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 47251456,
"byteOffset": 0
}
],
"md5sum": "be7f395f5b22143438fd631d5963b44f"
},
{
"dataPath": "params_shard_85.bin",
"format": "raw-shard",
"nbytes": 27848704,
"records": [
{
"name": "model.layers.24.mlp.gate_up_proj.q_scale",
"shape": [
28672,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5906432,
"byteOffset": 0
},
{
"name": "model.layers.24.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 5906432
},
{
"name": "model.layers.24.self_attn.qkv_proj.q_weight",
"shape": [
6144,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 10125312,
"byteOffset": 5914624
},
{
"name": "model.layers.24.self_attn.qkv_proj.q_scale",
"shape": [
6144,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1265664,
"byteOffset": 16039936
},
{
"name": "model.layers.24.self_attn.o_proj.q_weight",
"shape": [
4096,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6750208,
"byteOffset": 17305600
},
{
"name": "model.layers.24.self_attn.o_proj.q_scale",
"shape": [
4096,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 843776,
"byteOffset": 24055808
},
{
"name": "model.layers.25.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24899584
},
{
"name": "model.layers.25.mlp.down_proj.q_scale",
"shape": [
4096,
359
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2940928,
"byteOffset": 24907776
}
],
"md5sum": "8a610ce97f99d4ea805bf5ec480b8504"
},
{
"dataPath": "params_shard_86.bin",
"format": "raw-shard",
"nbytes": 23527424,
"records": [
{
"name": "model.layers.26.mlp.down_proj.q_weight",
"shape": [
4096,
1436
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 23527424,
"byteOffset": 0
}
],
"md5sum": "10ebfecbe2c7959834684c793c86c8e8"
},
{
"dataPath": "params_shard_87.bin",
"format": "raw-shard",
"nbytes": 47251456,
"records": [
{
"name": "model.layers.26.mlp.gate_up_proj.q_weight",
"shape": [
28672,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 47251456,
"byteOffset": 0
}
],
"md5sum": "2e465afc8bfeff7728572144b0c44415"
},
{
"dataPath": "params_shard_88.bin",
"format": "raw-shard",
"nbytes": 27848704,
"records": [
{
"name": "model.layers.25.mlp.gate_up_proj.q_scale",
"shape": [
28672,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5906432,
"byteOffset": 0
},
{
"name": "model.layers.25.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 5906432
},
{
"name": "model.layers.25.self_attn.qkv_proj.q_weight",
"shape": [
6144,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 10125312,
"byteOffset": 5914624
},
{
"name": "model.layers.25.self_attn.qkv_proj.q_scale",
"shape": [
6144,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1265664,
"byteOffset": 16039936
},
{
"name": "model.layers.25.self_attn.o_proj.q_weight",
"shape": [
4096,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6750208,
"byteOffset": 17305600
},
{
"name": "model.layers.25.self_attn.o_proj.q_scale",
"shape": [
4096,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 843776,
"byteOffset": 24055808
},
{
"name": "model.layers.26.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24899584
},
{
"name": "model.layers.26.mlp.down_proj.q_scale",
"shape": [
4096,
359
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2940928,
"byteOffset": 24907776
}
],
"md5sum": "2750b690877a0cc086998fb2b0ccaf44"
},
{
"dataPath": "params_shard_89.bin",
"format": "raw-shard",
"nbytes": 23527424,
"records": [
{
"name": "model.layers.27.mlp.down_proj.q_weight",
"shape": [
4096,
1436
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 23527424,
"byteOffset": 0
}
],
"md5sum": "0a02ef32ff282200ee4d13464bc54c43"
},
{
"dataPath": "params_shard_90.bin",
"format": "raw-shard",
"nbytes": 47251456,
"records": [
{
"name": "model.layers.27.mlp.gate_up_proj.q_weight",
"shape": [
28672,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 47251456,
"byteOffset": 0
}
],
"md5sum": "6c9f4ba27247e5bd342b2118fc46f3db"
},
{
"dataPath": "params_shard_91.bin",
"format": "raw-shard",
"nbytes": 27848704,
"records": [
{
"name": "model.layers.26.mlp.gate_up_proj.q_scale",
"shape": [
28672,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5906432,
"byteOffset": 0
},
{
"name": "model.layers.26.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 5906432
},
{
"name": "model.layers.26.self_attn.qkv_proj.q_weight",
"shape": [
6144,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 10125312,
"byteOffset": 5914624
},
{
"name": "model.layers.26.self_attn.qkv_proj.q_scale",
"shape": [
6144,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1265664,
"byteOffset": 16039936
},
{
"name": "model.layers.26.self_attn.o_proj.q_weight",
"shape": [
4096,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6750208,
"byteOffset": 17305600
},
{
"name": "model.layers.26.self_attn.o_proj.q_scale",
"shape": [
4096,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 843776,
"byteOffset": 24055808
},
{
"name": "model.layers.27.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24899584
},
{
"name": "model.layers.27.mlp.down_proj.q_scale",
"shape": [
4096,
359
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2940928,
"byteOffset": 24907776
}
],
"md5sum": "3de5db836cb5a16ba7a06202e8600ef1"
},
{
"dataPath": "params_shard_92.bin",
"format": "raw-shard",
"nbytes": 23527424,
"records": [
{
"name": "model.layers.28.mlp.down_proj.q_weight",
"shape": [
4096,
1436
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 23527424,
"byteOffset": 0
}
],
"md5sum": "66604d4f6f5e1c2d3a93772e5a1d4aab"
},
{
"dataPath": "params_shard_93.bin",
"format": "raw-shard",
"nbytes": 47251456,
"records": [
{
"name": "model.layers.28.mlp.gate_up_proj.q_weight",
"shape": [
28672,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 47251456,
"byteOffset": 0
}
],
"md5sum": "8b0e44f42f21963b8aaadae7856f99a1"
},
{
"dataPath": "params_shard_94.bin",
"format": "raw-shard",
"nbytes": 27848704,
"records": [
{
"name": "model.layers.27.mlp.gate_up_proj.q_scale",
"shape": [
28672,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5906432,
"byteOffset": 0
},
{
"name": "model.layers.27.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 5906432
},
{
"name": "model.layers.27.self_attn.qkv_proj.q_weight",
"shape": [
6144,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 10125312,
"byteOffset": 5914624
},
{
"name": "model.layers.27.self_attn.qkv_proj.q_scale",
"shape": [
6144,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1265664,
"byteOffset": 16039936
},
{
"name": "model.layers.27.self_attn.o_proj.q_weight",
"shape": [
4096,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6750208,
"byteOffset": 17305600
},
{
"name": "model.layers.27.self_attn.o_proj.q_scale",
"shape": [
4096,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 843776,
"byteOffset": 24055808
},
{
"name": "model.layers.28.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24899584
},
{
"name": "model.layers.28.mlp.down_proj.q_scale",
"shape": [
4096,
359
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2940928,
"byteOffset": 24907776
}
],
"md5sum": "a69137fd772ff29f6d6f4fedca472cfb"
},
{
"dataPath": "params_shard_95.bin",
"format": "raw-shard",
"nbytes": 23527424,
"records": [
{
"name": "model.layers.29.mlp.down_proj.q_weight",
"shape": [
4096,
1436
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 23527424,
"byteOffset": 0
}
],
"md5sum": "779a3c79f0e7b9585c9ad6936645b182"
},
{
"dataPath": "params_shard_96.bin",
"format": "raw-shard",
"nbytes": 47251456,
"records": [
{
"name": "model.layers.29.mlp.gate_up_proj.q_weight",
"shape": [
28672,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 47251456,
"byteOffset": 0
}
],
"md5sum": "7e3936d29b132aff7100a3d0d2aca9e6"
},
{
"dataPath": "params_shard_97.bin",
"format": "raw-shard",
"nbytes": 27848704,
"records": [
{
"name": "model.layers.28.mlp.gate_up_proj.q_scale",
"shape": [
28672,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5906432,
"byteOffset": 0
},
{
"name": "model.layers.28.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 5906432
},
{
"name": "model.layers.28.self_attn.qkv_proj.q_weight",
"shape": [
6144,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 10125312,
"byteOffset": 5914624
},
{
"name": "model.layers.28.self_attn.qkv_proj.q_scale",
"shape": [
6144,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1265664,
"byteOffset": 16039936
},
{
"name": "model.layers.28.self_attn.o_proj.q_weight",
"shape": [
4096,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6750208,
"byteOffset": 17305600
},
{
"name": "model.layers.28.self_attn.o_proj.q_scale",
"shape": [
4096,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 843776,
"byteOffset": 24055808
},
{
"name": "model.layers.29.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24899584
},
{
"name": "model.layers.29.mlp.down_proj.q_scale",
"shape": [
4096,
359
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2940928,
"byteOffset": 24907776
}
],
"md5sum": "c1b86ee5f942e65191ed35929e1da773"
},
{
"dataPath": "params_shard_98.bin",
"format": "raw-shard",
"nbytes": 24899584,
"records": [
{
"name": "model.layers.29.mlp.gate_up_proj.q_scale",
"shape": [
28672,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5906432,
"byteOffset": 0
},
{
"name": "model.layers.29.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 5906432
},
{
"name": "model.layers.29.self_attn.qkv_proj.q_weight",
"shape": [
6144,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 10125312,
"byteOffset": 5914624
},
{
"name": "model.layers.29.self_attn.qkv_proj.q_scale",
"shape": [
6144,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1265664,
"byteOffset": 16039936
},
{
"name": "model.layers.29.self_attn.o_proj.q_weight",
"shape": [
4096,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6750208,
"byteOffset": 17305600
},
{
"name": "model.layers.29.self_attn.o_proj.q_scale",
"shape": [
4096,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 843776,
"byteOffset": 24055808
}
],
"md5sum": "36e7440d142527e667759c20ac008d8c"
}
]
}