ansi-code's picture
Add Phi-3-mini-4k instruct v2 q4f16 model weights
2cbfe94
{
"metadata": {
"ParamSize": 325,
"ParamBytes": 2149644288.0,
"BitsPerParam": 4.500600961055312
},
"records": [
{
"dataPath": "params_shard_0.bin",
"format": "raw-shard",
"nbytes": 49250304,
"records": [
{
"name": "lm_head.q_weight",
"shape": [
32064,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 49250304,
"byteOffset": 0
}
],
"md5sum": "1c324d749f85a670edb243b63ff0cd8e"
},
{
"dataPath": "params_shard_1.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "transformer.h.21.mlp.gate_up_proj.q_weight",
"shape": [
16384,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "bffc9ab5fa8de9bf1f64c2ed2ba1632e"
},
{
"dataPath": "params_shard_2.bin",
"format": "raw-shard",
"nbytes": 23470080,
"records": [
{
"name": "lm_head.q_scale",
"shape": [
32064,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6156288,
"byteOffset": 0
},
{
"name": "transformer.h.21.ln.weight",
"shape": [
3072
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6144,
"byteOffset": 6156288
},
{
"name": "transformer.h.21.mlp.down_proj.q_weight",
"shape": [
3072,
1024
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 6162432
},
{
"name": "transformer.h.21.mlp.down_proj.q_scale",
"shape": [
3072,
256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 18745344
},
{
"name": "transformer.h.21.mlp.gate_up_proj.q_scale",
"shape": [
16384,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 20318208
},
{
"name": "transformer.h.21.post_attention_layernorm.weight",
"shape": [
3072
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6144,
"byteOffset": 23463936
}
],
"md5sum": "e72a01ea1e27a47f7dcdbdfbc1de1b32"
},
{
"dataPath": "params_shard_3.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "transformer.h.22.mlp.gate_up_proj.q_weight",
"shape": [
16384,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "e897efaf2e2d9bf411130cd6fc54dec3"
},
{
"dataPath": "params_shard_4.bin",
"format": "raw-shard",
"nbytes": 33239040,
"records": [
{
"name": "transformer.h.21.mixer.qkv_proj.q_weight",
"shape": [
9216,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14155776,
"byteOffset": 0
},
{
"name": "transformer.h.21.mixer.qkv_proj.q_scale",
"shape": [
9216,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1769472,
"byteOffset": 14155776
},
{
"name": "transformer.h.22.ln.weight",
"shape": [
3072
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6144,
"byteOffset": 15925248
},
{
"name": "transformer.h.22.mlp.down_proj.q_weight",
"shape": [
3072,
1024
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 15931392
},
{
"name": "transformer.h.22.mlp.down_proj.q_scale",
"shape": [
3072,
256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 28514304
},
{
"name": "transformer.h.22.mlp.gate_up_proj.q_scale",
"shape": [
16384,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 30087168
},
{
"name": "transformer.h.22.post_attention_layernorm.weight",
"shape": [
3072
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6144,
"byteOffset": 33232896
}
],
"md5sum": "44b1fea3199543a76635b17d8d1080f6"
},
{
"dataPath": "params_shard_5.bin",
"format": "raw-shard",
"nbytes": 21239808,
"records": [
{
"name": "transformer.h.22.mixer.out_proj.q_weight",
"shape": [
3072,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 4718592,
"byteOffset": 0
},
{
"name": "transformer.h.22.mixer.out_proj.q_scale",
"shape": [
3072,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 4718592
},
{
"name": "transformer.h.22.mixer.qkv_proj.q_weight",
"shape": [
9216,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14155776,
"byteOffset": 5308416
},
{
"name": "transformer.h.22.mixer.qkv_proj.q_scale",
"shape": [
9216,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1769472,
"byteOffset": 19464192
},
{
"name": "transformer.h.23.ln.weight",
"shape": [
3072
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6144,
"byteOffset": 21233664
}
],
"md5sum": "3a10eea0db5e47d4ddf18ac6e45156a7"
},
{
"dataPath": "params_shard_6.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "transformer.h.23.mlp.gate_up_proj.q_weight",
"shape": [
16384,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "aff5daaa7eab02f545b6de95a07f629c"
},
{
"dataPath": "params_shard_7.bin",
"format": "raw-shard",
"nbytes": 22616064,
"records": [
{
"name": "transformer.h.23.mlp.down_proj.q_weight",
"shape": [
3072,
1024
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "transformer.h.23.mlp.down_proj.q_scale",
"shape": [
3072,
256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "transformer.h.23.mlp.gate_up_proj.q_scale",
"shape": [
16384,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 14155776
},
{
"name": "transformer.h.23.post_attention_layernorm.weight",
"shape": [
3072
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6144,
"byteOffset": 17301504
},
{
"name": "transformer.h.23.mixer.out_proj.q_weight",
"shape": [
3072,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 4718592,
"byteOffset": 17307648
},
{
"name": "transformer.h.23.mixer.out_proj.q_scale",
"shape": [
3072,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 22026240
}
],
"md5sum": "317ef88c263aa7153b49d9d413aa214a"
},
{
"dataPath": "params_shard_8.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "transformer.h.24.mlp.gate_up_proj.q_weight",
"shape": [
16384,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "7d8126ab1042ee97aa2a9a4751248c66"
},
{
"dataPath": "params_shard_9.bin",
"format": "raw-shard",
"nbytes": 33239040,
"records": [
{
"name": "transformer.h.23.mixer.qkv_proj.q_weight",
"shape": [
9216,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14155776,
"byteOffset": 0
},
{
"name": "transformer.h.23.mixer.qkv_proj.q_scale",
"shape": [
9216,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1769472,
"byteOffset": 14155776
},
{
"name": "transformer.h.24.ln.weight",
"shape": [
3072
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6144,
"byteOffset": 15925248
},
{
"name": "transformer.h.24.mlp.down_proj.q_weight",
"shape": [
3072,
1024
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 15931392
},
{
"name": "transformer.h.24.mlp.down_proj.q_scale",
"shape": [
3072,
256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 28514304
},
{
"name": "transformer.h.24.mlp.gate_up_proj.q_scale",
"shape": [
16384,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 30087168
},
{
"name": "transformer.h.24.post_attention_layernorm.weight",
"shape": [
3072
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6144,
"byteOffset": 33232896
}
],
"md5sum": "760693568c03ab16652491ad1040ef67"
},
{
"dataPath": "params_shard_10.bin",
"format": "raw-shard",
"nbytes": 21239808,
"records": [
{
"name": "transformer.h.24.mixer.out_proj.q_weight",
"shape": [
3072,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 4718592,
"byteOffset": 0
},
{
"name": "transformer.h.24.mixer.out_proj.q_scale",
"shape": [
3072,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 4718592
},
{
"name": "transformer.h.24.mixer.qkv_proj.q_weight",
"shape": [
9216,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14155776,
"byteOffset": 5308416
},
{
"name": "transformer.h.24.mixer.qkv_proj.q_scale",
"shape": [
9216,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1769472,
"byteOffset": 19464192
},
{
"name": "transformer.h.25.ln.weight",
"shape": [
3072
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6144,
"byteOffset": 21233664
}
],
"md5sum": "24d17abc868ecacadfd460f533ccacbb"
},
{
"dataPath": "params_shard_11.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "transformer.h.25.mlp.gate_up_proj.q_weight",
"shape": [
16384,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "ffa93ddb620d8f019863c71ec6f9c2b1"
},
{
"dataPath": "params_shard_12.bin",
"format": "raw-shard",
"nbytes": 22616064,
"records": [
{
"name": "transformer.h.25.mlp.down_proj.q_weight",
"shape": [
3072,
1024
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "transformer.h.25.mlp.down_proj.q_scale",
"shape": [
3072,
256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "transformer.h.25.mlp.gate_up_proj.q_scale",
"shape": [
16384,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 14155776
},
{
"name": "transformer.h.25.post_attention_layernorm.weight",
"shape": [
3072
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6144,
"byteOffset": 17301504
},
{
"name": "transformer.h.25.mixer.out_proj.q_weight",
"shape": [
3072,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 4718592,
"byteOffset": 17307648
},
{
"name": "transformer.h.25.mixer.out_proj.q_scale",
"shape": [
3072,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 22026240
}
],
"md5sum": "70760ecefb8607ad526c1fbfc4672d94"
},
{
"dataPath": "params_shard_13.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "transformer.h.26.mlp.gate_up_proj.q_weight",
"shape": [
16384,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "8cb598b68f468e902a5c9dc1cc04d9a8"
},
{
"dataPath": "params_shard_14.bin",
"format": "raw-shard",
"nbytes": 33239040,
"records": [
{
"name": "transformer.h.25.mixer.qkv_proj.q_weight",
"shape": [
9216,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14155776,
"byteOffset": 0
},
{
"name": "transformer.h.25.mixer.qkv_proj.q_scale",
"shape": [
9216,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1769472,
"byteOffset": 14155776
},
{
"name": "transformer.h.26.ln.weight",
"shape": [
3072
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6144,
"byteOffset": 15925248
},
{
"name": "transformer.h.26.mlp.down_proj.q_weight",
"shape": [
3072,
1024
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 15931392
},
{
"name": "transformer.h.26.mlp.down_proj.q_scale",
"shape": [
3072,
256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 28514304
},
{
"name": "transformer.h.26.mlp.gate_up_proj.q_scale",
"shape": [
16384,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 30087168
},
{
"name": "transformer.h.26.post_attention_layernorm.weight",
"shape": [
3072
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6144,
"byteOffset": 33232896
}
],
"md5sum": "3fee913dcf27c42bd1407481a072887b"
},
{
"dataPath": "params_shard_15.bin",
"format": "raw-shard",
"nbytes": 21239808,
"records": [
{
"name": "transformer.h.26.mixer.out_proj.q_weight",
"shape": [
3072,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 4718592,
"byteOffset": 0
},
{
"name": "transformer.h.26.mixer.out_proj.q_scale",
"shape": [
3072,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 4718592
},
{
"name": "transformer.h.26.mixer.qkv_proj.q_weight",
"shape": [
9216,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14155776,
"byteOffset": 5308416
},
{
"name": "transformer.h.26.mixer.qkv_proj.q_scale",
"shape": [
9216,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1769472,
"byteOffset": 19464192
},
{
"name": "transformer.h.27.ln.weight",
"shape": [
3072
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6144,
"byteOffset": 21233664
}
],
"md5sum": "f191e42c463e42f2c0cf144f45eb974b"
},
{
"dataPath": "params_shard_16.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "transformer.h.27.mlp.gate_up_proj.q_weight",
"shape": [
16384,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "034f6e2b39a12f65af34da60dad46583"
},
{
"dataPath": "params_shard_17.bin",
"format": "raw-shard",
"nbytes": 22616064,
"records": [
{
"name": "transformer.h.27.mlp.down_proj.q_weight",
"shape": [
3072,
1024
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "transformer.h.27.mlp.down_proj.q_scale",
"shape": [
3072,
256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "transformer.h.27.mlp.gate_up_proj.q_scale",
"shape": [
16384,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 14155776
},
{
"name": "transformer.h.27.post_attention_layernorm.weight",
"shape": [
3072
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6144,
"byteOffset": 17301504
},
{
"name": "transformer.h.27.mixer.out_proj.q_weight",
"shape": [
3072,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 4718592,
"byteOffset": 17307648
},
{
"name": "transformer.h.27.mixer.out_proj.q_scale",
"shape": [
3072,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 22026240
}
],
"md5sum": "ab5230f41f8f2519045007cd6edd419a"
},
{
"dataPath": "params_shard_18.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "transformer.h.28.mlp.gate_up_proj.q_weight",
"shape": [
16384,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "448baced45bb117f6a29ee8b433f2b12"
},
{
"dataPath": "params_shard_19.bin",
"format": "raw-shard",
"nbytes": 33239040,
"records": [
{
"name": "transformer.h.27.mixer.qkv_proj.q_weight",
"shape": [
9216,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14155776,
"byteOffset": 0
},
{
"name": "transformer.h.27.mixer.qkv_proj.q_scale",
"shape": [
9216,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1769472,
"byteOffset": 14155776
},
{
"name": "transformer.h.28.ln.weight",
"shape": [
3072
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6144,
"byteOffset": 15925248
},
{
"name": "transformer.h.28.mlp.down_proj.q_weight",
"shape": [
3072,
1024
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 15931392
},
{
"name": "transformer.h.28.mlp.down_proj.q_scale",
"shape": [
3072,
256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 28514304
},
{
"name": "transformer.h.28.mlp.gate_up_proj.q_scale",
"shape": [
16384,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 30087168
},
{
"name": "transformer.h.28.post_attention_layernorm.weight",
"shape": [
3072
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6144,
"byteOffset": 33232896
}
],
"md5sum": "55ab27bdd529f9f70264310cf655fb60"
},
{
"dataPath": "params_shard_20.bin",
"format": "raw-shard",
"nbytes": 21239808,
"records": [
{
"name": "transformer.h.28.mixer.out_proj.q_weight",
"shape": [
3072,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 4718592,
"byteOffset": 0
},
{
"name": "transformer.h.28.mixer.out_proj.q_scale",
"shape": [
3072,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 4718592
},
{
"name": "transformer.h.28.mixer.qkv_proj.q_weight",
"shape": [
9216,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14155776,
"byteOffset": 5308416
},
{
"name": "transformer.h.28.mixer.qkv_proj.q_scale",
"shape": [
9216,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1769472,
"byteOffset": 19464192
},
{
"name": "transformer.h.29.ln.weight",
"shape": [
3072
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6144,
"byteOffset": 21233664
}
],
"md5sum": "12ff30fc3c487581828637d65f2591f8"
},
{
"dataPath": "params_shard_21.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "transformer.h.29.mlp.gate_up_proj.q_weight",
"shape": [
16384,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "88faa44d78bff9e15788775dc26ca3b5"
},
{
"dataPath": "params_shard_22.bin",
"format": "raw-shard",
"nbytes": 22616064,
"records": [
{
"name": "transformer.h.29.mlp.down_proj.q_weight",
"shape": [
3072,
1024
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "transformer.h.29.mlp.down_proj.q_scale",
"shape": [
3072,
256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "transformer.h.29.mlp.gate_up_proj.q_scale",
"shape": [
16384,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 14155776
},
{
"name": "transformer.h.29.post_attention_layernorm.weight",
"shape": [
3072
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6144,
"byteOffset": 17301504
},
{
"name": "transformer.h.29.mixer.out_proj.q_weight",
"shape": [
3072,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 4718592,
"byteOffset": 17307648
},
{
"name": "transformer.h.29.mixer.out_proj.q_scale",
"shape": [
3072,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 22026240
}
],
"md5sum": "da02480200d7f115927a8f1558383f65"
},
{
"dataPath": "params_shard_23.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "transformer.h.30.mlp.gate_up_proj.q_weight",
"shape": [
16384,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "d152ca9a5bfe20212f59c039e07ac9b6"
},
{
"dataPath": "params_shard_24.bin",
"format": "raw-shard",
"nbytes": 33239040,
"records": [
{
"name": "transformer.h.29.mixer.qkv_proj.q_weight",
"shape": [
9216,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14155776,
"byteOffset": 0
},
{
"name": "transformer.h.29.mixer.qkv_proj.q_scale",
"shape": [
9216,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1769472,
"byteOffset": 14155776
},
{
"name": "transformer.h.30.ln.weight",
"shape": [
3072
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6144,
"byteOffset": 15925248
},
{
"name": "transformer.h.30.mlp.down_proj.q_weight",
"shape": [
3072,
1024
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 15931392
},
{
"name": "transformer.h.30.mlp.down_proj.q_scale",
"shape": [
3072,
256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 28514304
},
{
"name": "transformer.h.30.mlp.gate_up_proj.q_scale",
"shape": [
16384,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 30087168
},
{
"name": "transformer.h.30.post_attention_layernorm.weight",
"shape": [
3072
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6144,
"byteOffset": 33232896
}
],
"md5sum": "d2f7d742efbc933b9a90d080be151194"
},
{
"dataPath": "params_shard_25.bin",
"format": "raw-shard",
"nbytes": 21239808,
"records": [
{
"name": "transformer.h.30.mixer.out_proj.q_weight",
"shape": [
3072,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 4718592,
"byteOffset": 0
},
{
"name": "transformer.h.30.mixer.out_proj.q_scale",
"shape": [
3072,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 4718592
},
{
"name": "transformer.h.30.mixer.qkv_proj.q_weight",
"shape": [
9216,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14155776,
"byteOffset": 5308416
},
{
"name": "transformer.h.30.mixer.qkv_proj.q_scale",
"shape": [
9216,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1769472,
"byteOffset": 19464192
},
{
"name": "transformer.h.31.ln.weight",
"shape": [
3072
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6144,
"byteOffset": 21233664
}
],
"md5sum": "85b5676eea17a5b165fce0dbc3696941"
},
{
"dataPath": "params_shard_26.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "transformer.h.31.mlp.gate_up_proj.q_weight",
"shape": [
16384,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "a4c51c3dae95ff75409b72ef1058a9f2"
},
{
"dataPath": "params_shard_27.bin",
"format": "raw-shard",
"nbytes": 22616064,
"records": [
{
"name": "transformer.h.31.mlp.down_proj.q_weight",
"shape": [
3072,
1024
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "transformer.h.31.mlp.down_proj.q_scale",
"shape": [
3072,
256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "transformer.h.31.mlp.gate_up_proj.q_scale",
"shape": [
16384,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 14155776
},
{
"name": "transformer.h.31.post_attention_layernorm.weight",
"shape": [
3072
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6144,
"byteOffset": 17301504
},
{
"name": "transformer.h.31.mixer.out_proj.q_weight",
"shape": [
3072,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 4718592,
"byteOffset": 17307648
},
{
"name": "transformer.h.31.mixer.out_proj.q_scale",
"shape": [
3072,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 22026240
}
],
"md5sum": "02315132ebf759c4a0dab6af67a23218"
},
{
"dataPath": "params_shard_28.bin",
"format": "raw-shard",
"nbytes": 49250304,
"records": [
{
"name": "transformer.embd.q_weight",
"shape": [
32064,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 49250304,
"byteOffset": 0
}
],
"md5sum": "2b60ee20e865f03d3137b3946a5e47ec"
},
{
"dataPath": "params_shard_29.bin",
"format": "raw-shard",
"nbytes": 22093824,
"records": [
{
"name": "transformer.h.31.mixer.qkv_proj.q_weight",
"shape": [
9216,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14155776,
"byteOffset": 0
},
{
"name": "transformer.h.31.mixer.qkv_proj.q_scale",
"shape": [
9216,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1769472,
"byteOffset": 14155776
},
{
"name": "transformer.norm.weight",
"shape": [
3072
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6144,
"byteOffset": 15925248
},
{
"name": "transformer.embd.q_scale",
"shape": [
32064,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6156288,
"byteOffset": 15931392
},
{
"name": "transformer.h.0.ln.weight",
"shape": [
3072
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6144,
"byteOffset": 22087680
}
],
"md5sum": "b17654ea413be96dadfaf10748457004"
},
{
"dataPath": "params_shard_30.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "transformer.h.0.mlp.gate_up_proj.q_weight",
"shape": [
16384,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "75401551f6747a316f971a1272e17b67"
},
{
"dataPath": "params_shard_31.bin",
"format": "raw-shard",
"nbytes": 22616064,
"records": [
{
"name": "transformer.h.0.mlp.down_proj.q_weight",
"shape": [
3072,
1024
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "transformer.h.0.mlp.down_proj.q_scale",
"shape": [
3072,
256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "transformer.h.0.mlp.gate_up_proj.q_scale",
"shape": [
16384,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 14155776
},
{
"name": "transformer.h.0.post_attention_layernorm.weight",
"shape": [
3072
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6144,
"byteOffset": 17301504
},
{
"name": "transformer.h.0.mixer.out_proj.q_weight",
"shape": [
3072,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 4718592,
"byteOffset": 17307648
},
{
"name": "transformer.h.0.mixer.out_proj.q_scale",
"shape": [
3072,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 22026240
}
],
"md5sum": "a1d421326fe0be9230e15e06f53e8223"
},
{
"dataPath": "params_shard_32.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "transformer.h.1.mlp.gate_up_proj.q_weight",
"shape": [
16384,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "32c8838d89ff322f16a60837303400c5"
},
{
"dataPath": "params_shard_33.bin",
"format": "raw-shard",
"nbytes": 33239040,
"records": [
{
"name": "transformer.h.0.mixer.qkv_proj.q_weight",
"shape": [
9216,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14155776,
"byteOffset": 0
},
{
"name": "transformer.h.0.mixer.qkv_proj.q_scale",
"shape": [
9216,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1769472,
"byteOffset": 14155776
},
{
"name": "transformer.h.1.ln.weight",
"shape": [
3072
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6144,
"byteOffset": 15925248
},
{
"name": "transformer.h.1.mlp.down_proj.q_weight",
"shape": [
3072,
1024
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 15931392
},
{
"name": "transformer.h.1.mlp.down_proj.q_scale",
"shape": [
3072,
256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 28514304
},
{
"name": "transformer.h.1.mlp.gate_up_proj.q_scale",
"shape": [
16384,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 30087168
},
{
"name": "transformer.h.1.post_attention_layernorm.weight",
"shape": [
3072
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6144,
"byteOffset": 33232896
}
],
"md5sum": "9bfcc97c4f7ce6455268246526ddfcf5"
},
{
"dataPath": "params_shard_34.bin",
"format": "raw-shard",
"nbytes": 21239808,
"records": [
{
"name": "transformer.h.1.mixer.out_proj.q_weight",
"shape": [
3072,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 4718592,
"byteOffset": 0
},
{
"name": "transformer.h.1.mixer.out_proj.q_scale",
"shape": [
3072,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 4718592
},
{
"name": "transformer.h.1.mixer.qkv_proj.q_weight",
"shape": [
9216,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14155776,
"byteOffset": 5308416
},
{
"name": "transformer.h.1.mixer.qkv_proj.q_scale",
"shape": [
9216,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1769472,
"byteOffset": 19464192
},
{
"name": "transformer.h.10.ln.weight",
"shape": [
3072
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6144,
"byteOffset": 21233664
}
],
"md5sum": "dced52e60045d5fb617069cc7f3fb524"
},
{
"dataPath": "params_shard_35.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "transformer.h.10.mlp.gate_up_proj.q_weight",
"shape": [
16384,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "d7f28586cab9d0f93b189dd76015ebe2"
},
{
"dataPath": "params_shard_36.bin",
"format": "raw-shard",
"nbytes": 22616064,
"records": [
{
"name": "transformer.h.10.mlp.down_proj.q_weight",
"shape": [
3072,
1024
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "transformer.h.10.mlp.down_proj.q_scale",
"shape": [
3072,
256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "transformer.h.10.mlp.gate_up_proj.q_scale",
"shape": [
16384,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 14155776
},
{
"name": "transformer.h.10.post_attention_layernorm.weight",
"shape": [
3072
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6144,
"byteOffset": 17301504
},
{
"name": "transformer.h.10.mixer.out_proj.q_weight",
"shape": [
3072,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 4718592,
"byteOffset": 17307648
},
{
"name": "transformer.h.10.mixer.out_proj.q_scale",
"shape": [
3072,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 22026240
}
],
"md5sum": "0ae96fc9216cf45966daed67a0b2e64b"
},
{
"dataPath": "params_shard_37.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "transformer.h.11.mlp.gate_up_proj.q_weight",
"shape": [
16384,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "3e27c002e8de929452465c9916ec0845"
},
{
"dataPath": "params_shard_38.bin",
"format": "raw-shard",
"nbytes": 33239040,
"records": [
{
"name": "transformer.h.10.mixer.qkv_proj.q_weight",
"shape": [
9216,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14155776,
"byteOffset": 0
},
{
"name": "transformer.h.10.mixer.qkv_proj.q_scale",
"shape": [
9216,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1769472,
"byteOffset": 14155776
},
{
"name": "transformer.h.11.ln.weight",
"shape": [
3072
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6144,
"byteOffset": 15925248
},
{
"name": "transformer.h.11.mlp.down_proj.q_weight",
"shape": [
3072,
1024
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 15931392
},
{
"name": "transformer.h.11.mlp.down_proj.q_scale",
"shape": [
3072,
256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 28514304
},
{
"name": "transformer.h.11.mlp.gate_up_proj.q_scale",
"shape": [
16384,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 30087168
},
{
"name": "transformer.h.11.post_attention_layernorm.weight",
"shape": [
3072
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6144,
"byteOffset": 33232896
}
],
"md5sum": "37742640903429b8816c163a4b36045a"
},
{
"dataPath": "params_shard_39.bin",
"format": "raw-shard",
"nbytes": 21239808,
"records": [
{
"name": "transformer.h.11.mixer.out_proj.q_weight",
"shape": [
3072,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 4718592,
"byteOffset": 0
},
{
"name": "transformer.h.11.mixer.out_proj.q_scale",
"shape": [
3072,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 4718592
},
{
"name": "transformer.h.11.mixer.qkv_proj.q_weight",
"shape": [
9216,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14155776,
"byteOffset": 5308416
},
{
"name": "transformer.h.11.mixer.qkv_proj.q_scale",
"shape": [
9216,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1769472,
"byteOffset": 19464192
},
{
"name": "transformer.h.12.ln.weight",
"shape": [
3072
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6144,
"byteOffset": 21233664
}
],
"md5sum": "a6ded082d85f0c81dfd46bd2f6921f93"
},
{
"dataPath": "params_shard_40.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "transformer.h.12.mlp.gate_up_proj.q_weight",
"shape": [
16384,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "87a00e1edfaf4b11c8bc81f2d3f69ec9"
},
{
"dataPath": "params_shard_41.bin",
"format": "raw-shard",
"nbytes": 22616064,
"records": [
{
"name": "transformer.h.12.mlp.down_proj.q_weight",
"shape": [
3072,
1024
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "transformer.h.12.mlp.down_proj.q_scale",
"shape": [
3072,
256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "transformer.h.12.mlp.gate_up_proj.q_scale",
"shape": [
16384,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 14155776
},
{
"name": "transformer.h.12.post_attention_layernorm.weight",
"shape": [
3072
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6144,
"byteOffset": 17301504
},
{
"name": "transformer.h.12.mixer.out_proj.q_weight",
"shape": [
3072,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 4718592,
"byteOffset": 17307648
},
{
"name": "transformer.h.12.mixer.out_proj.q_scale",
"shape": [
3072,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 22026240
}
],
"md5sum": "caa1ee1924b1168c702a062b9b1a3866"
},
{
"dataPath": "params_shard_42.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "transformer.h.13.mlp.gate_up_proj.q_weight",
"shape": [
16384,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "58c3d33aa0b8a26013d20ac1d277fc93"
},
{
"dataPath": "params_shard_43.bin",
"format": "raw-shard",
"nbytes": 33239040,
"records": [
{
"name": "transformer.h.12.mixer.qkv_proj.q_weight",
"shape": [
9216,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14155776,
"byteOffset": 0
},
{
"name": "transformer.h.12.mixer.qkv_proj.q_scale",
"shape": [
9216,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1769472,
"byteOffset": 14155776
},
{
"name": "transformer.h.13.ln.weight",
"shape": [
3072
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6144,
"byteOffset": 15925248
},
{
"name": "transformer.h.13.mlp.down_proj.q_weight",
"shape": [
3072,
1024
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 15931392
},
{
"name": "transformer.h.13.mlp.down_proj.q_scale",
"shape": [
3072,
256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 28514304
},
{
"name": "transformer.h.13.mlp.gate_up_proj.q_scale",
"shape": [
16384,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 30087168
},
{
"name": "transformer.h.13.post_attention_layernorm.weight",
"shape": [
3072
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6144,
"byteOffset": 33232896
}
],
"md5sum": "3a7e74933fc43b2aa18a5af30d4fb221"
},
{
"dataPath": "params_shard_44.bin",
"format": "raw-shard",
"nbytes": 21239808,
"records": [
{
"name": "transformer.h.13.mixer.out_proj.q_weight",
"shape": [
3072,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 4718592,
"byteOffset": 0
},
{
"name": "transformer.h.13.mixer.out_proj.q_scale",
"shape": [
3072,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 4718592
},
{
"name": "transformer.h.13.mixer.qkv_proj.q_weight",
"shape": [
9216,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14155776,
"byteOffset": 5308416
},
{
"name": "transformer.h.13.mixer.qkv_proj.q_scale",
"shape": [
9216,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1769472,
"byteOffset": 19464192
},
{
"name": "transformer.h.14.ln.weight",
"shape": [
3072
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6144,
"byteOffset": 21233664
}
],
"md5sum": "e6334b1865a724a2a724b0dfff24ac09"
},
{
"dataPath": "params_shard_45.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "transformer.h.14.mlp.gate_up_proj.q_weight",
"shape": [
16384,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "5d1686c23d8da5de1ede4d033422a4c3"
},
{
"dataPath": "params_shard_46.bin",
"format": "raw-shard",
"nbytes": 22616064,
"records": [
{
"name": "transformer.h.14.mlp.down_proj.q_weight",
"shape": [
3072,
1024
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "transformer.h.14.mlp.down_proj.q_scale",
"shape": [
3072,
256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "transformer.h.14.mlp.gate_up_proj.q_scale",
"shape": [
16384,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 14155776
},
{
"name": "transformer.h.14.post_attention_layernorm.weight",
"shape": [
3072
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6144,
"byteOffset": 17301504
},
{
"name": "transformer.h.14.mixer.out_proj.q_weight",
"shape": [
3072,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 4718592,
"byteOffset": 17307648
},
{
"name": "transformer.h.14.mixer.out_proj.q_scale",
"shape": [
3072,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 22026240
}
],
"md5sum": "78f794cf74cb3d33ddb66964a9343568"
},
{
"dataPath": "params_shard_47.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "transformer.h.15.mlp.gate_up_proj.q_weight",
"shape": [
16384,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "5e1edd49737a8656bbc36acad0a839ca"
},
{
"dataPath": "params_shard_48.bin",
"format": "raw-shard",
"nbytes": 33239040,
"records": [
{
"name": "transformer.h.14.mixer.qkv_proj.q_weight",
"shape": [
9216,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14155776,
"byteOffset": 0
},
{
"name": "transformer.h.14.mixer.qkv_proj.q_scale",
"shape": [
9216,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1769472,
"byteOffset": 14155776
},
{
"name": "transformer.h.15.ln.weight",
"shape": [
3072
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6144,
"byteOffset": 15925248
},
{
"name": "transformer.h.15.mlp.down_proj.q_weight",
"shape": [
3072,
1024
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 15931392
},
{
"name": "transformer.h.15.mlp.down_proj.q_scale",
"shape": [
3072,
256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 28514304
},
{
"name": "transformer.h.15.mlp.gate_up_proj.q_scale",
"shape": [
16384,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 30087168
},
{
"name": "transformer.h.15.post_attention_layernorm.weight",
"shape": [
3072
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6144,
"byteOffset": 33232896
}
],
"md5sum": "803f63f6a86d13d2a6e1c59ce92947ee"
},
{
"dataPath": "params_shard_49.bin",
"format": "raw-shard",
"nbytes": 21239808,
"records": [
{
"name": "transformer.h.15.mixer.out_proj.q_weight",
"shape": [
3072,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 4718592,
"byteOffset": 0
},
{
"name": "transformer.h.15.mixer.out_proj.q_scale",
"shape": [
3072,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 4718592
},
{
"name": "transformer.h.15.mixer.qkv_proj.q_weight",
"shape": [
9216,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14155776,
"byteOffset": 5308416
},
{
"name": "transformer.h.15.mixer.qkv_proj.q_scale",
"shape": [
9216,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1769472,
"byteOffset": 19464192
},
{
"name": "transformer.h.16.ln.weight",
"shape": [
3072
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6144,
"byteOffset": 21233664
}
],
"md5sum": "f3a09e267df6f5594ffae01144a634b2"
},
{
"dataPath": "params_shard_50.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "transformer.h.16.mlp.gate_up_proj.q_weight",
"shape": [
16384,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "0a40db84a8a908402cd849136ea328ba"
},
{
"dataPath": "params_shard_51.bin",
"format": "raw-shard",
"nbytes": 22616064,
"records": [
{
"name": "transformer.h.16.mlp.down_proj.q_weight",
"shape": [
3072,
1024
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "transformer.h.16.mlp.down_proj.q_scale",
"shape": [
3072,
256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "transformer.h.16.mlp.gate_up_proj.q_scale",
"shape": [
16384,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 14155776
},
{
"name": "transformer.h.16.post_attention_layernorm.weight",
"shape": [
3072
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6144,
"byteOffset": 17301504
},
{
"name": "transformer.h.16.mixer.out_proj.q_weight",
"shape": [
3072,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 4718592,
"byteOffset": 17307648
},
{
"name": "transformer.h.16.mixer.out_proj.q_scale",
"shape": [
3072,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 22026240
}
],
"md5sum": "2c1bce816f80cdd52275a116d88319fd"
},
{
"dataPath": "params_shard_52.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "transformer.h.17.mlp.gate_up_proj.q_weight",
"shape": [
16384,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "784df42386b4f8809ac5bec036edd830"
},
{
"dataPath": "params_shard_53.bin",
"format": "raw-shard",
"nbytes": 33239040,
"records": [
{
"name": "transformer.h.16.mixer.qkv_proj.q_weight",
"shape": [
9216,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14155776,
"byteOffset": 0
},
{
"name": "transformer.h.16.mixer.qkv_proj.q_scale",
"shape": [
9216,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1769472,
"byteOffset": 14155776
},
{
"name": "transformer.h.17.ln.weight",
"shape": [
3072
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6144,
"byteOffset": 15925248
},
{
"name": "transformer.h.17.mlp.down_proj.q_weight",
"shape": [
3072,
1024
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 15931392
},
{
"name": "transformer.h.17.mlp.down_proj.q_scale",
"shape": [
3072,
256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 28514304
},
{
"name": "transformer.h.17.mlp.gate_up_proj.q_scale",
"shape": [
16384,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 30087168
},
{
"name": "transformer.h.17.post_attention_layernorm.weight",
"shape": [
3072
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6144,
"byteOffset": 33232896
}
],
"md5sum": "90124113ba5f9b805f5fa75023f5025e"
},
{
"dataPath": "params_shard_54.bin",
"format": "raw-shard",
"nbytes": 21239808,
"records": [
{
"name": "transformer.h.17.mixer.out_proj.q_weight",
"shape": [
3072,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 4718592,
"byteOffset": 0
},
{
"name": "transformer.h.17.mixer.out_proj.q_scale",
"shape": [
3072,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 4718592
},
{
"name": "transformer.h.17.mixer.qkv_proj.q_weight",
"shape": [
9216,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14155776,
"byteOffset": 5308416
},
{
"name": "transformer.h.17.mixer.qkv_proj.q_scale",
"shape": [
9216,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1769472,
"byteOffset": 19464192
},
{
"name": "transformer.h.18.ln.weight",
"shape": [
3072
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6144,
"byteOffset": 21233664
}
],
"md5sum": "8d567a57285f50a297b8afbd8502f99e"
},
{
"dataPath": "params_shard_55.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "transformer.h.18.mlp.gate_up_proj.q_weight",
"shape": [
16384,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "ec7d2c37d48d083a733010532f256c10"
},
{
"dataPath": "params_shard_56.bin",
"format": "raw-shard",
"nbytes": 22616064,
"records": [
{
"name": "transformer.h.18.mlp.down_proj.q_weight",
"shape": [
3072,
1024
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "transformer.h.18.mlp.down_proj.q_scale",
"shape": [
3072,
256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "transformer.h.18.mlp.gate_up_proj.q_scale",
"shape": [
16384,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 14155776
},
{
"name": "transformer.h.18.post_attention_layernorm.weight",
"shape": [
3072
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6144,
"byteOffset": 17301504
},
{
"name": "transformer.h.18.mixer.out_proj.q_weight",
"shape": [
3072,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 4718592,
"byteOffset": 17307648
},
{
"name": "transformer.h.18.mixer.out_proj.q_scale",
"shape": [
3072,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 22026240
}
],
"md5sum": "5e6308e488505ef6c8d104e67522b478"
},
{
"dataPath": "params_shard_57.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "transformer.h.19.mlp.gate_up_proj.q_weight",
"shape": [
16384,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "6d35f9b61baf1e5681d78c07262951e0"
},
{
"dataPath": "params_shard_58.bin",
"format": "raw-shard",
"nbytes": 33239040,
"records": [
{
"name": "transformer.h.18.mixer.qkv_proj.q_weight",
"shape": [
9216,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14155776,
"byteOffset": 0
},
{
"name": "transformer.h.18.mixer.qkv_proj.q_scale",
"shape": [
9216,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1769472,
"byteOffset": 14155776
},
{
"name": "transformer.h.19.ln.weight",
"shape": [
3072
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6144,
"byteOffset": 15925248
},
{
"name": "transformer.h.19.mlp.down_proj.q_weight",
"shape": [
3072,
1024
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 15931392
},
{
"name": "transformer.h.19.mlp.down_proj.q_scale",
"shape": [
3072,
256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 28514304
},
{
"name": "transformer.h.19.mlp.gate_up_proj.q_scale",
"shape": [
16384,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 30087168
},
{
"name": "transformer.h.19.post_attention_layernorm.weight",
"shape": [
3072
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6144,
"byteOffset": 33232896
}
],
"md5sum": "e1f03fdc798d913ebabec6037c9a6129"
},
{
"dataPath": "params_shard_59.bin",
"format": "raw-shard",
"nbytes": 21239808,
"records": [
{
"name": "transformer.h.19.mixer.out_proj.q_weight",
"shape": [
3072,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 4718592,
"byteOffset": 0
},
{
"name": "transformer.h.19.mixer.out_proj.q_scale",
"shape": [
3072,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 4718592
},
{
"name": "transformer.h.19.mixer.qkv_proj.q_weight",
"shape": [
9216,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14155776,
"byteOffset": 5308416
},
{
"name": "transformer.h.19.mixer.qkv_proj.q_scale",
"shape": [
9216,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1769472,
"byteOffset": 19464192
},
{
"name": "transformer.h.2.ln.weight",
"shape": [
3072
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6144,
"byteOffset": 21233664
}
],
"md5sum": "cb3c6009727454ce2a1b6db5edcf3601"
},
{
"dataPath": "params_shard_60.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "transformer.h.2.mlp.gate_up_proj.q_weight",
"shape": [
16384,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "3aa4d6a54245039a1f1d3c6ae286891a"
},
{
"dataPath": "params_shard_61.bin",
"format": "raw-shard",
"nbytes": 22616064,
"records": [
{
"name": "transformer.h.2.mlp.down_proj.q_weight",
"shape": [
3072,
1024
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "transformer.h.2.mlp.down_proj.q_scale",
"shape": [
3072,
256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "transformer.h.2.mlp.gate_up_proj.q_scale",
"shape": [
16384,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 14155776
},
{
"name": "transformer.h.2.post_attention_layernorm.weight",
"shape": [
3072
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6144,
"byteOffset": 17301504
},
{
"name": "transformer.h.2.mixer.out_proj.q_weight",
"shape": [
3072,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 4718592,
"byteOffset": 17307648
},
{
"name": "transformer.h.2.mixer.out_proj.q_scale",
"shape": [
3072,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 22026240
}
],
"md5sum": "c81bbe6024af7234a44178b9fb2608df"
},
{
"dataPath": "params_shard_62.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "transformer.h.20.mlp.gate_up_proj.q_weight",
"shape": [
16384,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "adf14f3c50401edc8c78cecdebe1a2f2"
},
{
"dataPath": "params_shard_63.bin",
"format": "raw-shard",
"nbytes": 33239040,
"records": [
{
"name": "transformer.h.2.mixer.qkv_proj.q_weight",
"shape": [
9216,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14155776,
"byteOffset": 0
},
{
"name": "transformer.h.2.mixer.qkv_proj.q_scale",
"shape": [
9216,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1769472,
"byteOffset": 14155776
},
{
"name": "transformer.h.20.ln.weight",
"shape": [
3072
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6144,
"byteOffset": 15925248
},
{
"name": "transformer.h.20.mlp.down_proj.q_weight",
"shape": [
3072,
1024
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 15931392
},
{
"name": "transformer.h.20.mlp.down_proj.q_scale",
"shape": [
3072,
256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 28514304
},
{
"name": "transformer.h.20.mlp.gate_up_proj.q_scale",
"shape": [
16384,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 30087168
},
{
"name": "transformer.h.20.post_attention_layernorm.weight",
"shape": [
3072
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6144,
"byteOffset": 33232896
}
],
"md5sum": "a85122ec700c5c303bb7d89d5a87f01e"
},
{
"dataPath": "params_shard_64.bin",
"format": "raw-shard",
"nbytes": 26548224,
"records": [
{
"name": "transformer.h.20.mixer.out_proj.q_weight",
"shape": [
3072,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 4718592,
"byteOffset": 0
},
{
"name": "transformer.h.20.mixer.out_proj.q_scale",
"shape": [
3072,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 4718592
},
{
"name": "transformer.h.20.mixer.qkv_proj.q_weight",
"shape": [
9216,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14155776,
"byteOffset": 5308416
},
{
"name": "transformer.h.20.mixer.qkv_proj.q_scale",
"shape": [
9216,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1769472,
"byteOffset": 19464192
},
{
"name": "transformer.h.21.mixer.out_proj.q_weight",
"shape": [
3072,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 4718592,
"byteOffset": 21233664
},
{
"name": "transformer.h.21.mixer.out_proj.q_scale",
"shape": [
3072,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 25952256
},
{
"name": "transformer.h.3.ln.weight",
"shape": [
3072
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6144,
"byteOffset": 26542080
}
],
"md5sum": "cb64133fbfd3d910ab512077c7c66b15"
},
{
"dataPath": "params_shard_65.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "transformer.h.3.mlp.gate_up_proj.q_weight",
"shape": [
16384,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "b81e666b4262891706432ca77dfcf7f3"
},
{
"dataPath": "params_shard_66.bin",
"format": "raw-shard",
"nbytes": 22616064,
"records": [
{
"name": "transformer.h.3.mlp.down_proj.q_weight",
"shape": [
3072,
1024
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "transformer.h.3.mlp.down_proj.q_scale",
"shape": [
3072,
256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "transformer.h.3.mlp.gate_up_proj.q_scale",
"shape": [
16384,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 14155776
},
{
"name": "transformer.h.3.post_attention_layernorm.weight",
"shape": [
3072
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6144,
"byteOffset": 17301504
},
{
"name": "transformer.h.3.mixer.out_proj.q_weight",
"shape": [
3072,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 4718592,
"byteOffset": 17307648
},
{
"name": "transformer.h.3.mixer.out_proj.q_scale",
"shape": [
3072,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 22026240
}
],
"md5sum": "1e45828db608c42c708d8007f30be975"
},
{
"dataPath": "params_shard_67.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "transformer.h.4.mlp.gate_up_proj.q_weight",
"shape": [
16384,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "9e81cbfdfb4329161636d087137f87db"
},
{
"dataPath": "params_shard_68.bin",
"format": "raw-shard",
"nbytes": 33239040,
"records": [
{
"name": "transformer.h.3.mixer.qkv_proj.q_weight",
"shape": [
9216,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14155776,
"byteOffset": 0
},
{
"name": "transformer.h.3.mixer.qkv_proj.q_scale",
"shape": [
9216,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1769472,
"byteOffset": 14155776
},
{
"name": "transformer.h.4.ln.weight",
"shape": [
3072
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6144,
"byteOffset": 15925248
},
{
"name": "transformer.h.4.mlp.down_proj.q_weight",
"shape": [
3072,
1024
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 15931392
},
{
"name": "transformer.h.4.mlp.down_proj.q_scale",
"shape": [
3072,
256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 28514304
},
{
"name": "transformer.h.4.mlp.gate_up_proj.q_scale",
"shape": [
16384,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 30087168
},
{
"name": "transformer.h.4.post_attention_layernorm.weight",
"shape": [
3072
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6144,
"byteOffset": 33232896
}
],
"md5sum": "fc6bb5ef105898c38b631b6b20705a94"
},
{
"dataPath": "params_shard_69.bin",
"format": "raw-shard",
"nbytes": 21239808,
"records": [
{
"name": "transformer.h.4.mixer.out_proj.q_weight",
"shape": [
3072,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 4718592,
"byteOffset": 0
},
{
"name": "transformer.h.4.mixer.out_proj.q_scale",
"shape": [
3072,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 4718592
},
{
"name": "transformer.h.4.mixer.qkv_proj.q_weight",
"shape": [
9216,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14155776,
"byteOffset": 5308416
},
{
"name": "transformer.h.4.mixer.qkv_proj.q_scale",
"shape": [
9216,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1769472,
"byteOffset": 19464192
},
{
"name": "transformer.h.5.ln.weight",
"shape": [
3072
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6144,
"byteOffset": 21233664
}
],
"md5sum": "dbec295ba100b917fd99a3664effd8e6"
},
{
"dataPath": "params_shard_70.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "transformer.h.5.mlp.gate_up_proj.q_weight",
"shape": [
16384,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "fc169fbad97490d0e88d24abd2e21f51"
},
{
"dataPath": "params_shard_71.bin",
"format": "raw-shard",
"nbytes": 22616064,
"records": [
{
"name": "transformer.h.5.mlp.down_proj.q_weight",
"shape": [
3072,
1024
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "transformer.h.5.mlp.down_proj.q_scale",
"shape": [
3072,
256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "transformer.h.5.mlp.gate_up_proj.q_scale",
"shape": [
16384,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 14155776
},
{
"name": "transformer.h.5.post_attention_layernorm.weight",
"shape": [
3072
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6144,
"byteOffset": 17301504
},
{
"name": "transformer.h.5.mixer.out_proj.q_weight",
"shape": [
3072,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 4718592,
"byteOffset": 17307648
},
{
"name": "transformer.h.5.mixer.out_proj.q_scale",
"shape": [
3072,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 22026240
}
],
"md5sum": "26b99ee868a5aeef56f3683f295708d2"
},
{
"dataPath": "params_shard_72.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "transformer.h.6.mlp.gate_up_proj.q_weight",
"shape": [
16384,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "d156ae918eb57c1dbbbc6d8b2e8fd0ca"
},
{
"dataPath": "params_shard_73.bin",
"format": "raw-shard",
"nbytes": 33239040,
"records": [
{
"name": "transformer.h.5.mixer.qkv_proj.q_weight",
"shape": [
9216,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14155776,
"byteOffset": 0
},
{
"name": "transformer.h.5.mixer.qkv_proj.q_scale",
"shape": [
9216,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1769472,
"byteOffset": 14155776
},
{
"name": "transformer.h.6.ln.weight",
"shape": [
3072
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6144,
"byteOffset": 15925248
},
{
"name": "transformer.h.6.mlp.down_proj.q_weight",
"shape": [
3072,
1024
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 15931392
},
{
"name": "transformer.h.6.mlp.down_proj.q_scale",
"shape": [
3072,
256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 28514304
},
{
"name": "transformer.h.6.mlp.gate_up_proj.q_scale",
"shape": [
16384,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 30087168
},
{
"name": "transformer.h.6.post_attention_layernorm.weight",
"shape": [
3072
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6144,
"byteOffset": 33232896
}
],
"md5sum": "d9e6ac49824860c2de97abbf00698695"
},
{
"dataPath": "params_shard_74.bin",
"format": "raw-shard",
"nbytes": 21239808,
"records": [
{
"name": "transformer.h.6.mixer.out_proj.q_weight",
"shape": [
3072,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 4718592,
"byteOffset": 0
},
{
"name": "transformer.h.6.mixer.out_proj.q_scale",
"shape": [
3072,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 4718592
},
{
"name": "transformer.h.6.mixer.qkv_proj.q_weight",
"shape": [
9216,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14155776,
"byteOffset": 5308416
},
{
"name": "transformer.h.6.mixer.qkv_proj.q_scale",
"shape": [
9216,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1769472,
"byteOffset": 19464192
},
{
"name": "transformer.h.7.ln.weight",
"shape": [
3072
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6144,
"byteOffset": 21233664
}
],
"md5sum": "af0a79d47f7b455087aacf5e5ff1af9e"
},
{
"dataPath": "params_shard_75.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "transformer.h.7.mlp.gate_up_proj.q_weight",
"shape": [
16384,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "e7bd172032b3148ee4aa90cf4ada0b03"
},
{
"dataPath": "params_shard_76.bin",
"format": "raw-shard",
"nbytes": 22616064,
"records": [
{
"name": "transformer.h.7.mlp.down_proj.q_weight",
"shape": [
3072,
1024
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "transformer.h.7.mlp.down_proj.q_scale",
"shape": [
3072,
256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "transformer.h.7.mlp.gate_up_proj.q_scale",
"shape": [
16384,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 14155776
},
{
"name": "transformer.h.7.post_attention_layernorm.weight",
"shape": [
3072
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6144,
"byteOffset": 17301504
},
{
"name": "transformer.h.7.mixer.out_proj.q_weight",
"shape": [
3072,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 4718592,
"byteOffset": 17307648
},
{
"name": "transformer.h.7.mixer.out_proj.q_scale",
"shape": [
3072,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 22026240
}
],
"md5sum": "d42b22e18cc5bdf195f442fd7ca40f2b"
},
{
"dataPath": "params_shard_77.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "transformer.h.8.mlp.gate_up_proj.q_weight",
"shape": [
16384,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "4590a6b3aa5cc504087fecd175a20de5"
},
{
"dataPath": "params_shard_78.bin",
"format": "raw-shard",
"nbytes": 33239040,
"records": [
{
"name": "transformer.h.7.mixer.qkv_proj.q_weight",
"shape": [
9216,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14155776,
"byteOffset": 0
},
{
"name": "transformer.h.7.mixer.qkv_proj.q_scale",
"shape": [
9216,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1769472,
"byteOffset": 14155776
},
{
"name": "transformer.h.8.ln.weight",
"shape": [
3072
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6144,
"byteOffset": 15925248
},
{
"name": "transformer.h.8.mlp.down_proj.q_weight",
"shape": [
3072,
1024
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 15931392
},
{
"name": "transformer.h.8.mlp.down_proj.q_scale",
"shape": [
3072,
256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 28514304
},
{
"name": "transformer.h.8.mlp.gate_up_proj.q_scale",
"shape": [
16384,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 30087168
},
{
"name": "transformer.h.8.post_attention_layernorm.weight",
"shape": [
3072
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6144,
"byteOffset": 33232896
}
],
"md5sum": "72a8836c3978d0b6a341e8d8fb1a0c1a"
},
{
"dataPath": "params_shard_79.bin",
"format": "raw-shard",
"nbytes": 21239808,
"records": [
{
"name": "transformer.h.8.mixer.out_proj.q_weight",
"shape": [
3072,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 4718592,
"byteOffset": 0
},
{
"name": "transformer.h.8.mixer.out_proj.q_scale",
"shape": [
3072,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 4718592
},
{
"name": "transformer.h.8.mixer.qkv_proj.q_weight",
"shape": [
9216,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14155776,
"byteOffset": 5308416
},
{
"name": "transformer.h.8.mixer.qkv_proj.q_scale",
"shape": [
9216,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1769472,
"byteOffset": 19464192
},
{
"name": "transformer.h.9.ln.weight",
"shape": [
3072
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6144,
"byteOffset": 21233664
}
],
"md5sum": "90290a3fd5c0d06783ccf25bff65b27d"
},
{
"dataPath": "params_shard_80.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "transformer.h.9.mlp.gate_up_proj.q_weight",
"shape": [
16384,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "8b18b0c72648d0b534d1ee7428629f09"
},
{
"dataPath": "params_shard_81.bin",
"format": "raw-shard",
"nbytes": 22616064,
"records": [
{
"name": "transformer.h.9.mlp.down_proj.q_weight",
"shape": [
3072,
1024
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "transformer.h.9.mlp.down_proj.q_scale",
"shape": [
3072,
256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "transformer.h.9.mlp.gate_up_proj.q_scale",
"shape": [
16384,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3145728,
"byteOffset": 14155776
},
{
"name": "transformer.h.9.post_attention_layernorm.weight",
"shape": [
3072
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6144,
"byteOffset": 17301504
},
{
"name": "transformer.h.9.mixer.out_proj.q_weight",
"shape": [
3072,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 4718592,
"byteOffset": 17307648
},
{
"name": "transformer.h.9.mixer.out_proj.q_scale",
"shape": [
3072,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 22026240
}
],
"md5sum": "c7af733d42ff2ae14089da2731395c82"
},
{
"dataPath": "params_shard_82.bin",
"format": "raw-shard",
"nbytes": 15925248,
"records": [
{
"name": "transformer.h.9.mixer.qkv_proj.q_weight",
"shape": [
9216,
384
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14155776,
"byteOffset": 0
},
{
"name": "transformer.h.9.mixer.qkv_proj.q_scale",
"shape": [
9216,
96
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1769472,
"byteOffset": 14155776
}
],
"md5sum": "a8985ccd28f117d43e67fd3ef21ff314"
}
]
}