SmolLM2-1.7B-Instruct-q4f16_1-MLC / ndarray-cache.json
CharlieFRuan's picture
Upload folder using huggingface_hub
1201a77 verified
{
"metadata": {
"ParamSize": 243,
"ParamBytes": 962793472.0,
"BitsPerParam": 4.500674339093837
},
"records": [
{
"dataPath": "params_shard_0.bin",
"format": "raw-shard",
"nbytes": 50331648,
"records": [
{
"name": "model.embed_tokens.q_weight",
"shape": [
49152,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 50331648,
"byteOffset": 0
}
],
"md5sum": "ac105ee525c8eb0f4ec5efd6894e9766"
},
{
"dataPath": "params_shard_1.bin",
"format": "raw-shard",
"nbytes": 32509952,
"records": [
{
"name": "model.embed_tokens.q_scale",
"shape": [
49152,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6291456,
"byteOffset": 0
},
{
"name": "model.layers.0.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 6291456
},
{
"name": "model.layers.0.mlp.down_proj.q_weight",
"shape": [
2048,
1024
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 6295552
},
{
"name": "model.layers.0.mlp.down_proj.q_scale",
"shape": [
2048,
256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 14684160
},
{
"name": "model.layers.0.mlp.gate_up_proj.q_weight",
"shape": [
16384,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 15732736
}
],
"md5sum": "3676bcd979586efcb5f42567fe8539f7"
},
{
"dataPath": "params_shard_2.bin",
"format": "raw-shard",
"nbytes": 16777216,
"records": [
{
"name": "model.layers.1.mlp.gate_up_proj.q_weight",
"shape": [
16384,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 0
}
],
"md5sum": "a31b315368b78ec8dc188bc486615364"
},
{
"dataPath": "params_shard_3.bin",
"format": "raw-shard",
"nbytes": 32522240,
"records": [
{
"name": "model.layers.0.mlp.gate_up_proj.q_scale",
"shape": [
16384,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 0
},
{
"name": "model.layers.0.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 2097152
},
{
"name": "model.layers.0.self_attn.qkv_proj.q_weight",
"shape": [
6144,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6291456,
"byteOffset": 2101248
},
{
"name": "model.layers.0.self_attn.qkv_proj.q_scale",
"shape": [
6144,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 786432,
"byteOffset": 8392704
},
{
"name": "model.layers.0.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 9179136
},
{
"name": "model.layers.0.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 11276288
},
{
"name": "model.layers.1.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 11538432
},
{
"name": "model.layers.1.mlp.down_proj.q_weight",
"shape": [
2048,
1024
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 11542528
},
{
"name": "model.layers.1.mlp.down_proj.q_scale",
"shape": [
2048,
256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 19931136
},
{
"name": "model.layers.1.mlp.gate_up_proj.q_scale",
"shape": [
16384,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 20979712
},
{
"name": "model.layers.1.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 23076864
},
{
"name": "model.layers.1.self_attn.qkv_proj.q_weight",
"shape": [
6144,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6291456,
"byteOffset": 23080960
},
{
"name": "model.layers.1.self_attn.qkv_proj.q_scale",
"shape": [
6144,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 786432,
"byteOffset": 29372416
},
{
"name": "model.layers.1.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 30158848
},
{
"name": "model.layers.1.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 32256000
},
{
"name": "model.layers.10.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 32518144
}
],
"md5sum": "accf90bdc8f6cbceb1fb5a4e574173e8"
},
{
"dataPath": "params_shard_4.bin",
"format": "raw-shard",
"nbytes": 28315648,
"records": [
{
"name": "model.layers.10.mlp.down_proj.q_weight",
"shape": [
2048,
1024
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 0
},
{
"name": "model.layers.10.mlp.down_proj.q_scale",
"shape": [
2048,
256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 8388608
},
{
"name": "model.layers.10.mlp.gate_up_proj.q_weight",
"shape": [
16384,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 9437184
},
{
"name": "model.layers.10.mlp.gate_up_proj.q_scale",
"shape": [
16384,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 26214400
},
{
"name": "model.layers.10.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 28311552
}
],
"md5sum": "bf174f23eabc43073fe87c2d41acc5b1"
},
{
"dataPath": "params_shard_5.bin",
"format": "raw-shard",
"nbytes": 16777216,
"records": [
{
"name": "model.layers.11.mlp.gate_up_proj.q_weight",
"shape": [
16384,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 0
}
],
"md5sum": "7d33740d54fa2914f53758e77e889f88"
},
{
"dataPath": "params_shard_6.bin",
"format": "raw-shard",
"nbytes": 30420992,
"records": [
{
"name": "model.layers.10.self_attn.qkv_proj.q_weight",
"shape": [
6144,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6291456,
"byteOffset": 0
},
{
"name": "model.layers.10.self_attn.qkv_proj.q_scale",
"shape": [
6144,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 786432,
"byteOffset": 6291456
},
{
"name": "model.layers.10.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 7077888
},
{
"name": "model.layers.10.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 9175040
},
{
"name": "model.layers.11.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 9437184
},
{
"name": "model.layers.11.mlp.down_proj.q_weight",
"shape": [
2048,
1024
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 9441280
},
{
"name": "model.layers.11.mlp.down_proj.q_scale",
"shape": [
2048,
256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 17829888
},
{
"name": "model.layers.11.mlp.gate_up_proj.q_scale",
"shape": [
16384,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 18878464
},
{
"name": "model.layers.11.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 20975616
},
{
"name": "model.layers.11.self_attn.qkv_proj.q_weight",
"shape": [
6144,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6291456,
"byteOffset": 20979712
},
{
"name": "model.layers.11.self_attn.qkv_proj.q_scale",
"shape": [
6144,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 786432,
"byteOffset": 27271168
},
{
"name": "model.layers.11.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 28057600
},
{
"name": "model.layers.11.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 30154752
},
{
"name": "model.layers.12.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 30416896
}
],
"md5sum": "86aa132a6578316f3056b9914bf4f126"
},
{
"dataPath": "params_shard_7.bin",
"format": "raw-shard",
"nbytes": 28315648,
"records": [
{
"name": "model.layers.12.mlp.down_proj.q_weight",
"shape": [
2048,
1024
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 0
},
{
"name": "model.layers.12.mlp.down_proj.q_scale",
"shape": [
2048,
256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 8388608
},
{
"name": "model.layers.12.mlp.gate_up_proj.q_weight",
"shape": [
16384,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 9437184
},
{
"name": "model.layers.12.mlp.gate_up_proj.q_scale",
"shape": [
16384,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 26214400
},
{
"name": "model.layers.12.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 28311552
}
],
"md5sum": "9b7234589a21cbf777afed6e109baa97"
},
{
"dataPath": "params_shard_8.bin",
"format": "raw-shard",
"nbytes": 16777216,
"records": [
{
"name": "model.layers.13.mlp.gate_up_proj.q_weight",
"shape": [
16384,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 0
}
],
"md5sum": "5e5970ad19a88672fe2f05b6978d4486"
},
{
"dataPath": "params_shard_9.bin",
"format": "raw-shard",
"nbytes": 30420992,
"records": [
{
"name": "model.layers.12.self_attn.qkv_proj.q_weight",
"shape": [
6144,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6291456,
"byteOffset": 0
},
{
"name": "model.layers.12.self_attn.qkv_proj.q_scale",
"shape": [
6144,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 786432,
"byteOffset": 6291456
},
{
"name": "model.layers.12.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 7077888
},
{
"name": "model.layers.12.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 9175040
},
{
"name": "model.layers.13.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 9437184
},
{
"name": "model.layers.13.mlp.down_proj.q_weight",
"shape": [
2048,
1024
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 9441280
},
{
"name": "model.layers.13.mlp.down_proj.q_scale",
"shape": [
2048,
256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 17829888
},
{
"name": "model.layers.13.mlp.gate_up_proj.q_scale",
"shape": [
16384,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 18878464
},
{
"name": "model.layers.13.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 20975616
},
{
"name": "model.layers.13.self_attn.qkv_proj.q_weight",
"shape": [
6144,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6291456,
"byteOffset": 20979712
},
{
"name": "model.layers.13.self_attn.qkv_proj.q_scale",
"shape": [
6144,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 786432,
"byteOffset": 27271168
},
{
"name": "model.layers.13.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 28057600
},
{
"name": "model.layers.13.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 30154752
},
{
"name": "model.layers.14.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 30416896
}
],
"md5sum": "f59ba55f02a163f518e2f7f4de68d66b"
},
{
"dataPath": "params_shard_10.bin",
"format": "raw-shard",
"nbytes": 28315648,
"records": [
{
"name": "model.layers.14.mlp.down_proj.q_weight",
"shape": [
2048,
1024
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 0
},
{
"name": "model.layers.14.mlp.down_proj.q_scale",
"shape": [
2048,
256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 8388608
},
{
"name": "model.layers.14.mlp.gate_up_proj.q_weight",
"shape": [
16384,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 9437184
},
{
"name": "model.layers.14.mlp.gate_up_proj.q_scale",
"shape": [
16384,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 26214400
},
{
"name": "model.layers.14.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 28311552
}
],
"md5sum": "5c7fe54a9524532f16795f3d744bbc19"
},
{
"dataPath": "params_shard_11.bin",
"format": "raw-shard",
"nbytes": 16777216,
"records": [
{
"name": "model.layers.15.mlp.gate_up_proj.q_weight",
"shape": [
16384,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 0
}
],
"md5sum": "19dce74042bab9fe64c2503c392ef9ac"
},
{
"dataPath": "params_shard_12.bin",
"format": "raw-shard",
"nbytes": 30420992,
"records": [
{
"name": "model.layers.14.self_attn.qkv_proj.q_weight",
"shape": [
6144,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6291456,
"byteOffset": 0
},
{
"name": "model.layers.14.self_attn.qkv_proj.q_scale",
"shape": [
6144,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 786432,
"byteOffset": 6291456
},
{
"name": "model.layers.14.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 7077888
},
{
"name": "model.layers.14.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 9175040
},
{
"name": "model.layers.15.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 9437184
},
{
"name": "model.layers.15.mlp.down_proj.q_weight",
"shape": [
2048,
1024
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 9441280
},
{
"name": "model.layers.15.mlp.down_proj.q_scale",
"shape": [
2048,
256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 17829888
},
{
"name": "model.layers.15.mlp.gate_up_proj.q_scale",
"shape": [
16384,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 18878464
},
{
"name": "model.layers.15.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 20975616
},
{
"name": "model.layers.15.self_attn.qkv_proj.q_weight",
"shape": [
6144,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6291456,
"byteOffset": 20979712
},
{
"name": "model.layers.15.self_attn.qkv_proj.q_scale",
"shape": [
6144,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 786432,
"byteOffset": 27271168
},
{
"name": "model.layers.15.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 28057600
},
{
"name": "model.layers.15.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 30154752
},
{
"name": "model.layers.16.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 30416896
}
],
"md5sum": "78691d982fa70bc493b694d6c6bfea7d"
},
{
"dataPath": "params_shard_13.bin",
"format": "raw-shard",
"nbytes": 28315648,
"records": [
{
"name": "model.layers.16.mlp.down_proj.q_weight",
"shape": [
2048,
1024
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 0
},
{
"name": "model.layers.16.mlp.down_proj.q_scale",
"shape": [
2048,
256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 8388608
},
{
"name": "model.layers.16.mlp.gate_up_proj.q_weight",
"shape": [
16384,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 9437184
},
{
"name": "model.layers.16.mlp.gate_up_proj.q_scale",
"shape": [
16384,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 26214400
},
{
"name": "model.layers.16.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 28311552
}
],
"md5sum": "89a1aa3db70e7b444d1ba7c200020d95"
},
{
"dataPath": "params_shard_14.bin",
"format": "raw-shard",
"nbytes": 16777216,
"records": [
{
"name": "model.layers.17.mlp.gate_up_proj.q_weight",
"shape": [
16384,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 0
}
],
"md5sum": "d7bbacb7ef9f3d3b99e83092ae988694"
},
{
"dataPath": "params_shard_15.bin",
"format": "raw-shard",
"nbytes": 30420992,
"records": [
{
"name": "model.layers.16.self_attn.qkv_proj.q_weight",
"shape": [
6144,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6291456,
"byteOffset": 0
},
{
"name": "model.layers.16.self_attn.qkv_proj.q_scale",
"shape": [
6144,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 786432,
"byteOffset": 6291456
},
{
"name": "model.layers.16.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 7077888
},
{
"name": "model.layers.16.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 9175040
},
{
"name": "model.layers.17.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 9437184
},
{
"name": "model.layers.17.mlp.down_proj.q_weight",
"shape": [
2048,
1024
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 9441280
},
{
"name": "model.layers.17.mlp.down_proj.q_scale",
"shape": [
2048,
256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 17829888
},
{
"name": "model.layers.17.mlp.gate_up_proj.q_scale",
"shape": [
16384,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 18878464
},
{
"name": "model.layers.17.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 20975616
},
{
"name": "model.layers.17.self_attn.qkv_proj.q_weight",
"shape": [
6144,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6291456,
"byteOffset": 20979712
},
{
"name": "model.layers.17.self_attn.qkv_proj.q_scale",
"shape": [
6144,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 786432,
"byteOffset": 27271168
},
{
"name": "model.layers.17.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 28057600
},
{
"name": "model.layers.17.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 30154752
},
{
"name": "model.layers.18.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 30416896
}
],
"md5sum": "f3cd61bdd4f9522f925ed983357b64e7"
},
{
"dataPath": "params_shard_16.bin",
"format": "raw-shard",
"nbytes": 28315648,
"records": [
{
"name": "model.layers.18.mlp.down_proj.q_weight",
"shape": [
2048,
1024
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 0
},
{
"name": "model.layers.18.mlp.down_proj.q_scale",
"shape": [
2048,
256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 8388608
},
{
"name": "model.layers.18.mlp.gate_up_proj.q_weight",
"shape": [
16384,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 9437184
},
{
"name": "model.layers.18.mlp.gate_up_proj.q_scale",
"shape": [
16384,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 26214400
},
{
"name": "model.layers.18.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 28311552
}
],
"md5sum": "7ed5a2d129181624ae7b79dcb1d268b2"
},
{
"dataPath": "params_shard_17.bin",
"format": "raw-shard",
"nbytes": 16777216,
"records": [
{
"name": "model.layers.19.mlp.gate_up_proj.q_weight",
"shape": [
16384,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 0
}
],
"md5sum": "626748bd09fb5068212a396a343c0b2f"
},
{
"dataPath": "params_shard_18.bin",
"format": "raw-shard",
"nbytes": 30420992,
"records": [
{
"name": "model.layers.18.self_attn.qkv_proj.q_weight",
"shape": [
6144,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6291456,
"byteOffset": 0
},
{
"name": "model.layers.18.self_attn.qkv_proj.q_scale",
"shape": [
6144,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 786432,
"byteOffset": 6291456
},
{
"name": "model.layers.18.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 7077888
},
{
"name": "model.layers.18.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 9175040
},
{
"name": "model.layers.19.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 9437184
},
{
"name": "model.layers.19.mlp.down_proj.q_weight",
"shape": [
2048,
1024
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 9441280
},
{
"name": "model.layers.19.mlp.down_proj.q_scale",
"shape": [
2048,
256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 17829888
},
{
"name": "model.layers.19.mlp.gate_up_proj.q_scale",
"shape": [
16384,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 18878464
},
{
"name": "model.layers.19.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 20975616
},
{
"name": "model.layers.19.self_attn.qkv_proj.q_weight",
"shape": [
6144,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6291456,
"byteOffset": 20979712
},
{
"name": "model.layers.19.self_attn.qkv_proj.q_scale",
"shape": [
6144,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 786432,
"byteOffset": 27271168
},
{
"name": "model.layers.19.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 28057600
},
{
"name": "model.layers.19.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 30154752
},
{
"name": "model.layers.2.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 30416896
}
],
"md5sum": "f0eb530a02a90ee643a9a08f612b58a7"
},
{
"dataPath": "params_shard_19.bin",
"format": "raw-shard",
"nbytes": 28315648,
"records": [
{
"name": "model.layers.2.mlp.down_proj.q_weight",
"shape": [
2048,
1024
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 0
},
{
"name": "model.layers.2.mlp.down_proj.q_scale",
"shape": [
2048,
256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 8388608
},
{
"name": "model.layers.2.mlp.gate_up_proj.q_weight",
"shape": [
16384,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 9437184
},
{
"name": "model.layers.2.mlp.gate_up_proj.q_scale",
"shape": [
16384,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 26214400
},
{
"name": "model.layers.2.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 28311552
}
],
"md5sum": "47fbe87c3472c2acd77dfc530b73c91b"
},
{
"dataPath": "params_shard_20.bin",
"format": "raw-shard",
"nbytes": 16777216,
"records": [
{
"name": "model.layers.20.mlp.gate_up_proj.q_weight",
"shape": [
16384,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 0
}
],
"md5sum": "792aaa998cd506b1051a7beb75682cce"
},
{
"dataPath": "params_shard_21.bin",
"format": "raw-shard",
"nbytes": 30420992,
"records": [
{
"name": "model.layers.2.self_attn.qkv_proj.q_weight",
"shape": [
6144,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6291456,
"byteOffset": 0
},
{
"name": "model.layers.2.self_attn.qkv_proj.q_scale",
"shape": [
6144,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 786432,
"byteOffset": 6291456
},
{
"name": "model.layers.2.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 7077888
},
{
"name": "model.layers.2.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 9175040
},
{
"name": "model.layers.20.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 9437184
},
{
"name": "model.layers.20.mlp.down_proj.q_weight",
"shape": [
2048,
1024
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 9441280
},
{
"name": "model.layers.20.mlp.down_proj.q_scale",
"shape": [
2048,
256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 17829888
},
{
"name": "model.layers.20.mlp.gate_up_proj.q_scale",
"shape": [
16384,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 18878464
},
{
"name": "model.layers.20.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 20975616
},
{
"name": "model.layers.20.self_attn.qkv_proj.q_weight",
"shape": [
6144,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6291456,
"byteOffset": 20979712
},
{
"name": "model.layers.20.self_attn.qkv_proj.q_scale",
"shape": [
6144,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 786432,
"byteOffset": 27271168
},
{
"name": "model.layers.20.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 28057600
},
{
"name": "model.layers.20.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 30154752
},
{
"name": "model.layers.21.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 30416896
}
],
"md5sum": "587dae7dda93b58417fb48df24b42cce"
},
{
"dataPath": "params_shard_22.bin",
"format": "raw-shard",
"nbytes": 28315648,
"records": [
{
"name": "model.layers.21.mlp.down_proj.q_weight",
"shape": [
2048,
1024
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 0
},
{
"name": "model.layers.21.mlp.down_proj.q_scale",
"shape": [
2048,
256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 8388608
},
{
"name": "model.layers.21.mlp.gate_up_proj.q_weight",
"shape": [
16384,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 9437184
},
{
"name": "model.layers.21.mlp.gate_up_proj.q_scale",
"shape": [
16384,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 26214400
},
{
"name": "model.layers.21.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 28311552
}
],
"md5sum": "adba660820b3c0e79b4a6038a6ed5921"
},
{
"dataPath": "params_shard_23.bin",
"format": "raw-shard",
"nbytes": 16777216,
"records": [
{
"name": "model.layers.22.mlp.gate_up_proj.q_weight",
"shape": [
16384,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 0
}
],
"md5sum": "2fa4789a5d7025c513dff0c9bfae5ec4"
},
{
"dataPath": "params_shard_24.bin",
"format": "raw-shard",
"nbytes": 30420992,
"records": [
{
"name": "model.layers.21.self_attn.qkv_proj.q_weight",
"shape": [
6144,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6291456,
"byteOffset": 0
},
{
"name": "model.layers.21.self_attn.qkv_proj.q_scale",
"shape": [
6144,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 786432,
"byteOffset": 6291456
},
{
"name": "model.layers.21.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 7077888
},
{
"name": "model.layers.21.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 9175040
},
{
"name": "model.layers.22.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 9437184
},
{
"name": "model.layers.22.mlp.down_proj.q_weight",
"shape": [
2048,
1024
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 9441280
},
{
"name": "model.layers.22.mlp.down_proj.q_scale",
"shape": [
2048,
256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 17829888
},
{
"name": "model.layers.22.mlp.gate_up_proj.q_scale",
"shape": [
16384,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 18878464
},
{
"name": "model.layers.22.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 20975616
},
{
"name": "model.layers.22.self_attn.qkv_proj.q_weight",
"shape": [
6144,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6291456,
"byteOffset": 20979712
},
{
"name": "model.layers.22.self_attn.qkv_proj.q_scale",
"shape": [
6144,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 786432,
"byteOffset": 27271168
},
{
"name": "model.layers.22.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 28057600
},
{
"name": "model.layers.22.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 30154752
},
{
"name": "model.layers.23.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 30416896
}
],
"md5sum": "8a1f5d3495b80fe880016a4dfd173e16"
},
{
"dataPath": "params_shard_25.bin",
"format": "raw-shard",
"nbytes": 28315648,
"records": [
{
"name": "model.layers.23.mlp.down_proj.q_weight",
"shape": [
2048,
1024
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 0
},
{
"name": "model.layers.23.mlp.down_proj.q_scale",
"shape": [
2048,
256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 8388608
},
{
"name": "model.layers.23.mlp.gate_up_proj.q_weight",
"shape": [
16384,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 9437184
},
{
"name": "model.layers.23.mlp.gate_up_proj.q_scale",
"shape": [
16384,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 26214400
},
{
"name": "model.layers.23.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 28311552
}
],
"md5sum": "cacf613229548c1e43446f1ce5233f68"
},
{
"dataPath": "params_shard_26.bin",
"format": "raw-shard",
"nbytes": 16777216,
"records": [
{
"name": "model.layers.3.mlp.gate_up_proj.q_weight",
"shape": [
16384,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 0
}
],
"md5sum": "3ad908646e7ccbcd6339885b43a8d683"
},
{
"dataPath": "params_shard_27.bin",
"format": "raw-shard",
"nbytes": 30420992,
"records": [
{
"name": "model.layers.23.self_attn.qkv_proj.q_weight",
"shape": [
6144,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6291456,
"byteOffset": 0
},
{
"name": "model.layers.23.self_attn.qkv_proj.q_scale",
"shape": [
6144,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 786432,
"byteOffset": 6291456
},
{
"name": "model.layers.23.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 7077888
},
{
"name": "model.layers.23.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 9175040
},
{
"name": "model.layers.3.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 9437184
},
{
"name": "model.layers.3.mlp.down_proj.q_weight",
"shape": [
2048,
1024
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 9441280
},
{
"name": "model.layers.3.mlp.down_proj.q_scale",
"shape": [
2048,
256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 17829888
},
{
"name": "model.layers.3.mlp.gate_up_proj.q_scale",
"shape": [
16384,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 18878464
},
{
"name": "model.layers.3.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 20975616
},
{
"name": "model.layers.3.self_attn.qkv_proj.q_weight",
"shape": [
6144,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6291456,
"byteOffset": 20979712
},
{
"name": "model.layers.3.self_attn.qkv_proj.q_scale",
"shape": [
6144,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 786432,
"byteOffset": 27271168
},
{
"name": "model.layers.3.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 28057600
},
{
"name": "model.layers.3.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 30154752
},
{
"name": "model.layers.4.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 30416896
}
],
"md5sum": "6bbc94eee5db16d62164711b57fc4375"
},
{
"dataPath": "params_shard_28.bin",
"format": "raw-shard",
"nbytes": 28315648,
"records": [
{
"name": "model.layers.4.mlp.down_proj.q_weight",
"shape": [
2048,
1024
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 0
},
{
"name": "model.layers.4.mlp.down_proj.q_scale",
"shape": [
2048,
256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 8388608
},
{
"name": "model.layers.4.mlp.gate_up_proj.q_weight",
"shape": [
16384,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 9437184
},
{
"name": "model.layers.4.mlp.gate_up_proj.q_scale",
"shape": [
16384,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 26214400
},
{
"name": "model.layers.4.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 28311552
}
],
"md5sum": "c2e5944cf211e97d84ac86a8c6204551"
},
{
"dataPath": "params_shard_29.bin",
"format": "raw-shard",
"nbytes": 16777216,
"records": [
{
"name": "model.layers.5.mlp.gate_up_proj.q_weight",
"shape": [
16384,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 0
}
],
"md5sum": "2af1a8d31ef73ecc3bf80aa336b09481"
},
{
"dataPath": "params_shard_30.bin",
"format": "raw-shard",
"nbytes": 30420992,
"records": [
{
"name": "model.layers.4.self_attn.qkv_proj.q_weight",
"shape": [
6144,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6291456,
"byteOffset": 0
},
{
"name": "model.layers.4.self_attn.qkv_proj.q_scale",
"shape": [
6144,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 786432,
"byteOffset": 6291456
},
{
"name": "model.layers.4.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 7077888
},
{
"name": "model.layers.4.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 9175040
},
{
"name": "model.layers.5.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 9437184
},
{
"name": "model.layers.5.mlp.down_proj.q_weight",
"shape": [
2048,
1024
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 9441280
},
{
"name": "model.layers.5.mlp.down_proj.q_scale",
"shape": [
2048,
256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 17829888
},
{
"name": "model.layers.5.mlp.gate_up_proj.q_scale",
"shape": [
16384,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 18878464
},
{
"name": "model.layers.5.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 20975616
},
{
"name": "model.layers.5.self_attn.qkv_proj.q_weight",
"shape": [
6144,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6291456,
"byteOffset": 20979712
},
{
"name": "model.layers.5.self_attn.qkv_proj.q_scale",
"shape": [
6144,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 786432,
"byteOffset": 27271168
},
{
"name": "model.layers.5.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 28057600
},
{
"name": "model.layers.5.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 30154752
},
{
"name": "model.layers.6.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 30416896
}
],
"md5sum": "5cf2164db75318e7ba911b29ddf1db5c"
},
{
"dataPath": "params_shard_31.bin",
"format": "raw-shard",
"nbytes": 28315648,
"records": [
{
"name": "model.layers.6.mlp.down_proj.q_weight",
"shape": [
2048,
1024
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 0
},
{
"name": "model.layers.6.mlp.down_proj.q_scale",
"shape": [
2048,
256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 8388608
},
{
"name": "model.layers.6.mlp.gate_up_proj.q_weight",
"shape": [
16384,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 9437184
},
{
"name": "model.layers.6.mlp.gate_up_proj.q_scale",
"shape": [
16384,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 26214400
},
{
"name": "model.layers.6.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 28311552
}
],
"md5sum": "f93da0b127e3ce8ed734730bdcd641d3"
},
{
"dataPath": "params_shard_32.bin",
"format": "raw-shard",
"nbytes": 16777216,
"records": [
{
"name": "model.layers.7.mlp.gate_up_proj.q_weight",
"shape": [
16384,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 0
}
],
"md5sum": "6f5d07df5204058cb0970190056edc67"
},
{
"dataPath": "params_shard_33.bin",
"format": "raw-shard",
"nbytes": 30420992,
"records": [
{
"name": "model.layers.6.self_attn.qkv_proj.q_weight",
"shape": [
6144,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6291456,
"byteOffset": 0
},
{
"name": "model.layers.6.self_attn.qkv_proj.q_scale",
"shape": [
6144,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 786432,
"byteOffset": 6291456
},
{
"name": "model.layers.6.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 7077888
},
{
"name": "model.layers.6.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 9175040
},
{
"name": "model.layers.7.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 9437184
},
{
"name": "model.layers.7.mlp.down_proj.q_weight",
"shape": [
2048,
1024
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 9441280
},
{
"name": "model.layers.7.mlp.down_proj.q_scale",
"shape": [
2048,
256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 17829888
},
{
"name": "model.layers.7.mlp.gate_up_proj.q_scale",
"shape": [
16384,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 18878464
},
{
"name": "model.layers.7.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 20975616
},
{
"name": "model.layers.7.self_attn.qkv_proj.q_weight",
"shape": [
6144,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6291456,
"byteOffset": 20979712
},
{
"name": "model.layers.7.self_attn.qkv_proj.q_scale",
"shape": [
6144,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 786432,
"byteOffset": 27271168
},
{
"name": "model.layers.7.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 28057600
},
{
"name": "model.layers.7.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 30154752
},
{
"name": "model.layers.8.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 30416896
}
],
"md5sum": "4247029d5d9e379827fdfba773ea9912"
},
{
"dataPath": "params_shard_34.bin",
"format": "raw-shard",
"nbytes": 28315648,
"records": [
{
"name": "model.layers.8.mlp.down_proj.q_weight",
"shape": [
2048,
1024
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 0
},
{
"name": "model.layers.8.mlp.down_proj.q_scale",
"shape": [
2048,
256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 8388608
},
{
"name": "model.layers.8.mlp.gate_up_proj.q_weight",
"shape": [
16384,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 9437184
},
{
"name": "model.layers.8.mlp.gate_up_proj.q_scale",
"shape": [
16384,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 26214400
},
{
"name": "model.layers.8.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 28311552
}
],
"md5sum": "079b389b056bd8ac94be907dd7f83947"
},
{
"dataPath": "params_shard_35.bin",
"format": "raw-shard",
"nbytes": 16777216,
"records": [
{
"name": "model.layers.9.mlp.gate_up_proj.q_weight",
"shape": [
16384,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 0
}
],
"md5sum": "df0d96867b214297218b5f6bba8e88a0"
},
{
"dataPath": "params_shard_36.bin",
"format": "raw-shard",
"nbytes": 30420992,
"records": [
{
"name": "model.layers.8.self_attn.qkv_proj.q_weight",
"shape": [
6144,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6291456,
"byteOffset": 0
},
{
"name": "model.layers.8.self_attn.qkv_proj.q_scale",
"shape": [
6144,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 786432,
"byteOffset": 6291456
},
{
"name": "model.layers.8.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 7077888
},
{
"name": "model.layers.8.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 9175040
},
{
"name": "model.layers.9.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 9437184
},
{
"name": "model.layers.9.mlp.down_proj.q_weight",
"shape": [
2048,
1024
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 9441280
},
{
"name": "model.layers.9.mlp.down_proj.q_scale",
"shape": [
2048,
256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 17829888
},
{
"name": "model.layers.9.mlp.gate_up_proj.q_scale",
"shape": [
16384,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 18878464
},
{
"name": "model.layers.9.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 20975616
},
{
"name": "model.layers.9.self_attn.qkv_proj.q_weight",
"shape": [
6144,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6291456,
"byteOffset": 20979712
},
{
"name": "model.layers.9.self_attn.qkv_proj.q_scale",
"shape": [
6144,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 786432,
"byteOffset": 27271168
},
{
"name": "model.layers.9.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 28057600
},
{
"name": "model.layers.9.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 30154752
},
{
"name": "model.norm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 30416896
}
],
"md5sum": "e7967a863070c4176a6d895628c62971"
}
]
}