DA-MLC / tensor-cache.json
Dasuperhub's picture
Round 4: 87K clean examples, progressive from R3, fixed verb roots + possessives, Soussou speaker
c5bdd63 verified
{
"metadata": {
"ParamSize": 339,
"ParamBytes": 968001536.0,
"BitsPerParam": 4.500828151065705
},
"records": [
{
"dataPath": "params_shard_0.bin",
"format": "raw-shard",
"nbytes": 155582464,
"records": [
{
"name": "model.embed_tokens.q_weight",
"shape": [
151936,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 155582464,
"byteOffset": 0
}
],
"md5sum": "4e4ec9b621dc1492b262d3614f56d118"
},
{
"dataPath": "params_shard_1.bin",
"format": "raw-shard",
"nbytes": 26529792,
"records": [
{
"name": "model.embed_tokens.q_scale",
"shape": [
151936,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 19447808,
"byteOffset": 0
},
{
"name": "model.layers.0.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 19447808
},
{
"name": "model.layers.0.mlp.down_proj.q_weight",
"shape": [
2048,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6291456,
"byteOffset": 19451904
},
{
"name": "model.layers.0.mlp.down_proj.q_scale",
"shape": [
2048,
192
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 786432,
"byteOffset": 25743360
}
],
"md5sum": "4580acbacca71b324e2484816b4574ec"
},
{
"dataPath": "params_shard_2.bin",
"format": "raw-shard",
"nbytes": 28320256,
"records": [
{
"name": "model.layers.0.mlp.gate_up_proj.q_weight",
"shape": [
12288,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.0.mlp.gate_up_proj.q_scale",
"shape": [
12288,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "model.layers.0.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 14155776
},
{
"name": "model.layers.0.self_attn.k_norm.weight",
"shape": [
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 256,
"byteOffset": 14159872
},
{
"name": "model.layers.0.self_attn.c_attn.q_weight",
"shape": [
4096,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 4194304,
"byteOffset": 14160128
},
{
"name": "model.layers.0.self_attn.c_attn.q_scale",
"shape": [
4096,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 524288,
"byteOffset": 18354432
},
{
"name": "model.layers.0.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 18878720
},
{
"name": "model.layers.0.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 20975872
},
{
"name": "model.layers.0.self_attn.q_norm.weight",
"shape": [
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 256,
"byteOffset": 21238016
},
{
"name": "model.layers.1.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 21238272
},
{
"name": "model.layers.1.mlp.down_proj.q_weight",
"shape": [
2048,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6291456,
"byteOffset": 21242368
},
{
"name": "model.layers.1.mlp.down_proj.q_scale",
"shape": [
2048,
192
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 786432,
"byteOffset": 27533824
}
],
"md5sum": "e76ac3188fa194809fe027e077d7aa33"
},
{
"dataPath": "params_shard_3.bin",
"format": "raw-shard",
"nbytes": 28320256,
"records": [
{
"name": "model.layers.1.mlp.gate_up_proj.q_weight",
"shape": [
12288,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.1.mlp.gate_up_proj.q_scale",
"shape": [
12288,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "model.layers.1.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 14155776
},
{
"name": "model.layers.1.self_attn.k_norm.weight",
"shape": [
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 256,
"byteOffset": 14159872
},
{
"name": "model.layers.1.self_attn.c_attn.q_weight",
"shape": [
4096,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 4194304,
"byteOffset": 14160128
},
{
"name": "model.layers.1.self_attn.c_attn.q_scale",
"shape": [
4096,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 524288,
"byteOffset": 18354432
},
{
"name": "model.layers.1.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 18878720
},
{
"name": "model.layers.1.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 20975872
},
{
"name": "model.layers.1.self_attn.q_norm.weight",
"shape": [
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 256,
"byteOffset": 21238016
},
{
"name": "model.layers.10.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 21238272
},
{
"name": "model.layers.10.mlp.down_proj.q_weight",
"shape": [
2048,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6291456,
"byteOffset": 21242368
},
{
"name": "model.layers.10.mlp.down_proj.q_scale",
"shape": [
2048,
192
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 786432,
"byteOffset": 27533824
}
],
"md5sum": "a7cea5ed7e47f51fe9615284626137f0"
},
{
"dataPath": "params_shard_4.bin",
"format": "raw-shard",
"nbytes": 28320256,
"records": [
{
"name": "model.layers.10.mlp.gate_up_proj.q_weight",
"shape": [
12288,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.10.mlp.gate_up_proj.q_scale",
"shape": [
12288,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "model.layers.10.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 14155776
},
{
"name": "model.layers.10.self_attn.k_norm.weight",
"shape": [
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 256,
"byteOffset": 14159872
},
{
"name": "model.layers.10.self_attn.c_attn.q_weight",
"shape": [
4096,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 4194304,
"byteOffset": 14160128
},
{
"name": "model.layers.10.self_attn.c_attn.q_scale",
"shape": [
4096,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 524288,
"byteOffset": 18354432
},
{
"name": "model.layers.10.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 18878720
},
{
"name": "model.layers.10.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 20975872
},
{
"name": "model.layers.10.self_attn.q_norm.weight",
"shape": [
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 256,
"byteOffset": 21238016
},
{
"name": "model.layers.11.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 21238272
},
{
"name": "model.layers.11.mlp.down_proj.q_weight",
"shape": [
2048,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6291456,
"byteOffset": 21242368
},
{
"name": "model.layers.11.mlp.down_proj.q_scale",
"shape": [
2048,
192
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 786432,
"byteOffset": 27533824
}
],
"md5sum": "356555fb67d6e29d69d53706a3fd0df7"
},
{
"dataPath": "params_shard_5.bin",
"format": "raw-shard",
"nbytes": 28320256,
"records": [
{
"name": "model.layers.11.mlp.gate_up_proj.q_weight",
"shape": [
12288,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.11.mlp.gate_up_proj.q_scale",
"shape": [
12288,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "model.layers.11.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 14155776
},
{
"name": "model.layers.11.self_attn.k_norm.weight",
"shape": [
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 256,
"byteOffset": 14159872
},
{
"name": "model.layers.11.self_attn.c_attn.q_weight",
"shape": [
4096,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 4194304,
"byteOffset": 14160128
},
{
"name": "model.layers.11.self_attn.c_attn.q_scale",
"shape": [
4096,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 524288,
"byteOffset": 18354432
},
{
"name": "model.layers.11.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 18878720
},
{
"name": "model.layers.11.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 20975872
},
{
"name": "model.layers.11.self_attn.q_norm.weight",
"shape": [
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 256,
"byteOffset": 21238016
},
{
"name": "model.layers.12.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 21238272
},
{
"name": "model.layers.12.mlp.down_proj.q_weight",
"shape": [
2048,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6291456,
"byteOffset": 21242368
},
{
"name": "model.layers.12.mlp.down_proj.q_scale",
"shape": [
2048,
192
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 786432,
"byteOffset": 27533824
}
],
"md5sum": "7eee6a25fef9079fa950f8d04395f43a"
},
{
"dataPath": "params_shard_6.bin",
"format": "raw-shard",
"nbytes": 28320256,
"records": [
{
"name": "model.layers.12.mlp.gate_up_proj.q_weight",
"shape": [
12288,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.12.mlp.gate_up_proj.q_scale",
"shape": [
12288,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "model.layers.12.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 14155776
},
{
"name": "model.layers.12.self_attn.k_norm.weight",
"shape": [
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 256,
"byteOffset": 14159872
},
{
"name": "model.layers.12.self_attn.c_attn.q_weight",
"shape": [
4096,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 4194304,
"byteOffset": 14160128
},
{
"name": "model.layers.12.self_attn.c_attn.q_scale",
"shape": [
4096,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 524288,
"byteOffset": 18354432
},
{
"name": "model.layers.12.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 18878720
},
{
"name": "model.layers.12.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 20975872
},
{
"name": "model.layers.12.self_attn.q_norm.weight",
"shape": [
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 256,
"byteOffset": 21238016
},
{
"name": "model.layers.13.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 21238272
},
{
"name": "model.layers.13.mlp.down_proj.q_weight",
"shape": [
2048,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6291456,
"byteOffset": 21242368
},
{
"name": "model.layers.13.mlp.down_proj.q_scale",
"shape": [
2048,
192
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 786432,
"byteOffset": 27533824
}
],
"md5sum": "64c0c19b56a2c648a20f3eada01772d7"
},
{
"dataPath": "params_shard_7.bin",
"format": "raw-shard",
"nbytes": 28320256,
"records": [
{
"name": "model.layers.13.mlp.gate_up_proj.q_weight",
"shape": [
12288,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.13.mlp.gate_up_proj.q_scale",
"shape": [
12288,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "model.layers.13.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 14155776
},
{
"name": "model.layers.13.self_attn.k_norm.weight",
"shape": [
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 256,
"byteOffset": 14159872
},
{
"name": "model.layers.13.self_attn.c_attn.q_weight",
"shape": [
4096,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 4194304,
"byteOffset": 14160128
},
{
"name": "model.layers.13.self_attn.c_attn.q_scale",
"shape": [
4096,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 524288,
"byteOffset": 18354432
},
{
"name": "model.layers.13.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 18878720
},
{
"name": "model.layers.13.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 20975872
},
{
"name": "model.layers.13.self_attn.q_norm.weight",
"shape": [
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 256,
"byteOffset": 21238016
},
{
"name": "model.layers.14.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 21238272
},
{
"name": "model.layers.14.mlp.down_proj.q_weight",
"shape": [
2048,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6291456,
"byteOffset": 21242368
},
{
"name": "model.layers.14.mlp.down_proj.q_scale",
"shape": [
2048,
192
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 786432,
"byteOffset": 27533824
}
],
"md5sum": "d9a8ba7807d30c4eb114dacd18d7f36e"
},
{
"dataPath": "params_shard_8.bin",
"format": "raw-shard",
"nbytes": 28320256,
"records": [
{
"name": "model.layers.14.mlp.gate_up_proj.q_weight",
"shape": [
12288,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.14.mlp.gate_up_proj.q_scale",
"shape": [
12288,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "model.layers.14.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 14155776
},
{
"name": "model.layers.14.self_attn.k_norm.weight",
"shape": [
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 256,
"byteOffset": 14159872
},
{
"name": "model.layers.14.self_attn.c_attn.q_weight",
"shape": [
4096,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 4194304,
"byteOffset": 14160128
},
{
"name": "model.layers.14.self_attn.c_attn.q_scale",
"shape": [
4096,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 524288,
"byteOffset": 18354432
},
{
"name": "model.layers.14.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 18878720
},
{
"name": "model.layers.14.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 20975872
},
{
"name": "model.layers.14.self_attn.q_norm.weight",
"shape": [
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 256,
"byteOffset": 21238016
},
{
"name": "model.layers.15.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 21238272
},
{
"name": "model.layers.15.mlp.down_proj.q_weight",
"shape": [
2048,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6291456,
"byteOffset": 21242368
},
{
"name": "model.layers.15.mlp.down_proj.q_scale",
"shape": [
2048,
192
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 786432,
"byteOffset": 27533824
}
],
"md5sum": "7a6799cbbac2285a629a610ebdc90da1"
},
{
"dataPath": "params_shard_9.bin",
"format": "raw-shard",
"nbytes": 28320256,
"records": [
{
"name": "model.layers.15.mlp.gate_up_proj.q_weight",
"shape": [
12288,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.15.mlp.gate_up_proj.q_scale",
"shape": [
12288,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "model.layers.15.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 14155776
},
{
"name": "model.layers.15.self_attn.k_norm.weight",
"shape": [
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 256,
"byteOffset": 14159872
},
{
"name": "model.layers.15.self_attn.c_attn.q_weight",
"shape": [
4096,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 4194304,
"byteOffset": 14160128
},
{
"name": "model.layers.15.self_attn.c_attn.q_scale",
"shape": [
4096,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 524288,
"byteOffset": 18354432
},
{
"name": "model.layers.15.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 18878720
},
{
"name": "model.layers.15.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 20975872
},
{
"name": "model.layers.15.self_attn.q_norm.weight",
"shape": [
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 256,
"byteOffset": 21238016
},
{
"name": "model.layers.16.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 21238272
},
{
"name": "model.layers.16.mlp.down_proj.q_weight",
"shape": [
2048,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6291456,
"byteOffset": 21242368
},
{
"name": "model.layers.16.mlp.down_proj.q_scale",
"shape": [
2048,
192
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 786432,
"byteOffset": 27533824
}
],
"md5sum": "ae9fce143d2dae36a91b5f951b524140"
},
{
"dataPath": "params_shard_10.bin",
"format": "raw-shard",
"nbytes": 28320256,
"records": [
{
"name": "model.layers.16.mlp.gate_up_proj.q_weight",
"shape": [
12288,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.16.mlp.gate_up_proj.q_scale",
"shape": [
12288,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "model.layers.16.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 14155776
},
{
"name": "model.layers.16.self_attn.k_norm.weight",
"shape": [
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 256,
"byteOffset": 14159872
},
{
"name": "model.layers.16.self_attn.c_attn.q_weight",
"shape": [
4096,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 4194304,
"byteOffset": 14160128
},
{
"name": "model.layers.16.self_attn.c_attn.q_scale",
"shape": [
4096,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 524288,
"byteOffset": 18354432
},
{
"name": "model.layers.16.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 18878720
},
{
"name": "model.layers.16.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 20975872
},
{
"name": "model.layers.16.self_attn.q_norm.weight",
"shape": [
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 256,
"byteOffset": 21238016
},
{
"name": "model.layers.17.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 21238272
},
{
"name": "model.layers.17.mlp.down_proj.q_weight",
"shape": [
2048,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6291456,
"byteOffset": 21242368
},
{
"name": "model.layers.17.mlp.down_proj.q_scale",
"shape": [
2048,
192
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 786432,
"byteOffset": 27533824
}
],
"md5sum": "d1d4f356ab3629391b9b543f3a3cb483"
},
{
"dataPath": "params_shard_11.bin",
"format": "raw-shard",
"nbytes": 28320256,
"records": [
{
"name": "model.layers.17.mlp.gate_up_proj.q_weight",
"shape": [
12288,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.17.mlp.gate_up_proj.q_scale",
"shape": [
12288,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "model.layers.17.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 14155776
},
{
"name": "model.layers.17.self_attn.k_norm.weight",
"shape": [
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 256,
"byteOffset": 14159872
},
{
"name": "model.layers.17.self_attn.c_attn.q_weight",
"shape": [
4096,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 4194304,
"byteOffset": 14160128
},
{
"name": "model.layers.17.self_attn.c_attn.q_scale",
"shape": [
4096,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 524288,
"byteOffset": 18354432
},
{
"name": "model.layers.17.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 18878720
},
{
"name": "model.layers.17.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 20975872
},
{
"name": "model.layers.17.self_attn.q_norm.weight",
"shape": [
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 256,
"byteOffset": 21238016
},
{
"name": "model.layers.18.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 21238272
},
{
"name": "model.layers.18.mlp.down_proj.q_weight",
"shape": [
2048,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6291456,
"byteOffset": 21242368
},
{
"name": "model.layers.18.mlp.down_proj.q_scale",
"shape": [
2048,
192
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 786432,
"byteOffset": 27533824
}
],
"md5sum": "2e698b7ad3d83b77de1e7c369856ac24"
},
{
"dataPath": "params_shard_12.bin",
"format": "raw-shard",
"nbytes": 28320256,
"records": [
{
"name": "model.layers.18.mlp.gate_up_proj.q_weight",
"shape": [
12288,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.18.mlp.gate_up_proj.q_scale",
"shape": [
12288,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "model.layers.18.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 14155776
},
{
"name": "model.layers.18.self_attn.k_norm.weight",
"shape": [
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 256,
"byteOffset": 14159872
},
{
"name": "model.layers.18.self_attn.c_attn.q_weight",
"shape": [
4096,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 4194304,
"byteOffset": 14160128
},
{
"name": "model.layers.18.self_attn.c_attn.q_scale",
"shape": [
4096,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 524288,
"byteOffset": 18354432
},
{
"name": "model.layers.18.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 18878720
},
{
"name": "model.layers.18.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 20975872
},
{
"name": "model.layers.18.self_attn.q_norm.weight",
"shape": [
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 256,
"byteOffset": 21238016
},
{
"name": "model.layers.19.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 21238272
},
{
"name": "model.layers.19.mlp.down_proj.q_weight",
"shape": [
2048,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6291456,
"byteOffset": 21242368
},
{
"name": "model.layers.19.mlp.down_proj.q_scale",
"shape": [
2048,
192
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 786432,
"byteOffset": 27533824
}
],
"md5sum": "e632ed0424659ddf9bc2bc2c52f30885"
},
{
"dataPath": "params_shard_13.bin",
"format": "raw-shard",
"nbytes": 28320256,
"records": [
{
"name": "model.layers.19.mlp.gate_up_proj.q_weight",
"shape": [
12288,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.19.mlp.gate_up_proj.q_scale",
"shape": [
12288,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "model.layers.19.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 14155776
},
{
"name": "model.layers.19.self_attn.k_norm.weight",
"shape": [
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 256,
"byteOffset": 14159872
},
{
"name": "model.layers.19.self_attn.c_attn.q_weight",
"shape": [
4096,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 4194304,
"byteOffset": 14160128
},
{
"name": "model.layers.19.self_attn.c_attn.q_scale",
"shape": [
4096,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 524288,
"byteOffset": 18354432
},
{
"name": "model.layers.19.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 18878720
},
{
"name": "model.layers.19.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 20975872
},
{
"name": "model.layers.19.self_attn.q_norm.weight",
"shape": [
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 256,
"byteOffset": 21238016
},
{
"name": "model.layers.2.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 21238272
},
{
"name": "model.layers.2.mlp.down_proj.q_weight",
"shape": [
2048,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6291456,
"byteOffset": 21242368
},
{
"name": "model.layers.2.mlp.down_proj.q_scale",
"shape": [
2048,
192
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 786432,
"byteOffset": 27533824
}
],
"md5sum": "862b8ce040ca96a3d7e286fa066f8038"
},
{
"dataPath": "params_shard_14.bin",
"format": "raw-shard",
"nbytes": 28320256,
"records": [
{
"name": "model.layers.2.mlp.gate_up_proj.q_weight",
"shape": [
12288,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.2.mlp.gate_up_proj.q_scale",
"shape": [
12288,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "model.layers.2.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 14155776
},
{
"name": "model.layers.2.self_attn.k_norm.weight",
"shape": [
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 256,
"byteOffset": 14159872
},
{
"name": "model.layers.2.self_attn.c_attn.q_weight",
"shape": [
4096,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 4194304,
"byteOffset": 14160128
},
{
"name": "model.layers.2.self_attn.c_attn.q_scale",
"shape": [
4096,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 524288,
"byteOffset": 18354432
},
{
"name": "model.layers.2.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 18878720
},
{
"name": "model.layers.2.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 20975872
},
{
"name": "model.layers.2.self_attn.q_norm.weight",
"shape": [
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 256,
"byteOffset": 21238016
},
{
"name": "model.layers.20.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 21238272
},
{
"name": "model.layers.20.mlp.down_proj.q_weight",
"shape": [
2048,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6291456,
"byteOffset": 21242368
},
{
"name": "model.layers.20.mlp.down_proj.q_scale",
"shape": [
2048,
192
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 786432,
"byteOffset": 27533824
}
],
"md5sum": "0e1c92a5ef79ff2a886723cd95095cd1"
},
{
"dataPath": "params_shard_15.bin",
"format": "raw-shard",
"nbytes": 28320256,
"records": [
{
"name": "model.layers.20.mlp.gate_up_proj.q_weight",
"shape": [
12288,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.20.mlp.gate_up_proj.q_scale",
"shape": [
12288,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "model.layers.20.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 14155776
},
{
"name": "model.layers.20.self_attn.k_norm.weight",
"shape": [
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 256,
"byteOffset": 14159872
},
{
"name": "model.layers.20.self_attn.c_attn.q_weight",
"shape": [
4096,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 4194304,
"byteOffset": 14160128
},
{
"name": "model.layers.20.self_attn.c_attn.q_scale",
"shape": [
4096,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 524288,
"byteOffset": 18354432
},
{
"name": "model.layers.20.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 18878720
},
{
"name": "model.layers.20.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 20975872
},
{
"name": "model.layers.20.self_attn.q_norm.weight",
"shape": [
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 256,
"byteOffset": 21238016
},
{
"name": "model.layers.21.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 21238272
},
{
"name": "model.layers.21.mlp.down_proj.q_weight",
"shape": [
2048,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6291456,
"byteOffset": 21242368
},
{
"name": "model.layers.21.mlp.down_proj.q_scale",
"shape": [
2048,
192
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 786432,
"byteOffset": 27533824
}
],
"md5sum": "799619fc5942144ffaf1ddcafd1749e1"
},
{
"dataPath": "params_shard_16.bin",
"format": "raw-shard",
"nbytes": 28320256,
"records": [
{
"name": "model.layers.21.mlp.gate_up_proj.q_weight",
"shape": [
12288,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.21.mlp.gate_up_proj.q_scale",
"shape": [
12288,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "model.layers.21.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 14155776
},
{
"name": "model.layers.21.self_attn.k_norm.weight",
"shape": [
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 256,
"byteOffset": 14159872
},
{
"name": "model.layers.21.self_attn.c_attn.q_weight",
"shape": [
4096,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 4194304,
"byteOffset": 14160128
},
{
"name": "model.layers.21.self_attn.c_attn.q_scale",
"shape": [
4096,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 524288,
"byteOffset": 18354432
},
{
"name": "model.layers.21.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 18878720
},
{
"name": "model.layers.21.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 20975872
},
{
"name": "model.layers.21.self_attn.q_norm.weight",
"shape": [
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 256,
"byteOffset": 21238016
},
{
"name": "model.layers.22.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 21238272
},
{
"name": "model.layers.22.mlp.down_proj.q_weight",
"shape": [
2048,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6291456,
"byteOffset": 21242368
},
{
"name": "model.layers.22.mlp.down_proj.q_scale",
"shape": [
2048,
192
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 786432,
"byteOffset": 27533824
}
],
"md5sum": "f1f82f0c89689288fe28f23da4be8430"
},
{
"dataPath": "params_shard_17.bin",
"format": "raw-shard",
"nbytes": 28320256,
"records": [
{
"name": "model.layers.22.mlp.gate_up_proj.q_weight",
"shape": [
12288,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.22.mlp.gate_up_proj.q_scale",
"shape": [
12288,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "model.layers.22.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 14155776
},
{
"name": "model.layers.22.self_attn.k_norm.weight",
"shape": [
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 256,
"byteOffset": 14159872
},
{
"name": "model.layers.22.self_attn.c_attn.q_weight",
"shape": [
4096,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 4194304,
"byteOffset": 14160128
},
{
"name": "model.layers.22.self_attn.c_attn.q_scale",
"shape": [
4096,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 524288,
"byteOffset": 18354432
},
{
"name": "model.layers.22.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 18878720
},
{
"name": "model.layers.22.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 20975872
},
{
"name": "model.layers.22.self_attn.q_norm.weight",
"shape": [
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 256,
"byteOffset": 21238016
},
{
"name": "model.layers.23.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 21238272
},
{
"name": "model.layers.23.mlp.down_proj.q_weight",
"shape": [
2048,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6291456,
"byteOffset": 21242368
},
{
"name": "model.layers.23.mlp.down_proj.q_scale",
"shape": [
2048,
192
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 786432,
"byteOffset": 27533824
}
],
"md5sum": "7a54f5f38bc83b15c7038ac374386d96"
},
{
"dataPath": "params_shard_18.bin",
"format": "raw-shard",
"nbytes": 28320256,
"records": [
{
"name": "model.layers.23.mlp.gate_up_proj.q_weight",
"shape": [
12288,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.23.mlp.gate_up_proj.q_scale",
"shape": [
12288,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "model.layers.23.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 14155776
},
{
"name": "model.layers.23.self_attn.k_norm.weight",
"shape": [
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 256,
"byteOffset": 14159872
},
{
"name": "model.layers.23.self_attn.c_attn.q_weight",
"shape": [
4096,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 4194304,
"byteOffset": 14160128
},
{
"name": "model.layers.23.self_attn.c_attn.q_scale",
"shape": [
4096,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 524288,
"byteOffset": 18354432
},
{
"name": "model.layers.23.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 18878720
},
{
"name": "model.layers.23.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 20975872
},
{
"name": "model.layers.23.self_attn.q_norm.weight",
"shape": [
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 256,
"byteOffset": 21238016
},
{
"name": "model.layers.24.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 21238272
},
{
"name": "model.layers.24.mlp.down_proj.q_weight",
"shape": [
2048,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6291456,
"byteOffset": 21242368
},
{
"name": "model.layers.24.mlp.down_proj.q_scale",
"shape": [
2048,
192
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 786432,
"byteOffset": 27533824
}
],
"md5sum": "2fb39cf116e637363aeac4e7ff47ab41"
},
{
"dataPath": "params_shard_19.bin",
"format": "raw-shard",
"nbytes": 28320256,
"records": [
{
"name": "model.layers.24.mlp.gate_up_proj.q_weight",
"shape": [
12288,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.24.mlp.gate_up_proj.q_scale",
"shape": [
12288,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "model.layers.24.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 14155776
},
{
"name": "model.layers.24.self_attn.k_norm.weight",
"shape": [
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 256,
"byteOffset": 14159872
},
{
"name": "model.layers.24.self_attn.c_attn.q_weight",
"shape": [
4096,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 4194304,
"byteOffset": 14160128
},
{
"name": "model.layers.24.self_attn.c_attn.q_scale",
"shape": [
4096,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 524288,
"byteOffset": 18354432
},
{
"name": "model.layers.24.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 18878720
},
{
"name": "model.layers.24.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 20975872
},
{
"name": "model.layers.24.self_attn.q_norm.weight",
"shape": [
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 256,
"byteOffset": 21238016
},
{
"name": "model.layers.25.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 21238272
},
{
"name": "model.layers.25.mlp.down_proj.q_weight",
"shape": [
2048,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6291456,
"byteOffset": 21242368
},
{
"name": "model.layers.25.mlp.down_proj.q_scale",
"shape": [
2048,
192
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 786432,
"byteOffset": 27533824
}
],
"md5sum": "1af2773f371b0bbc23cf04fe45eae670"
},
{
"dataPath": "params_shard_20.bin",
"format": "raw-shard",
"nbytes": 28320256,
"records": [
{
"name": "model.layers.25.mlp.gate_up_proj.q_weight",
"shape": [
12288,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.25.mlp.gate_up_proj.q_scale",
"shape": [
12288,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "model.layers.25.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 14155776
},
{
"name": "model.layers.25.self_attn.k_norm.weight",
"shape": [
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 256,
"byteOffset": 14159872
},
{
"name": "model.layers.25.self_attn.c_attn.q_weight",
"shape": [
4096,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 4194304,
"byteOffset": 14160128
},
{
"name": "model.layers.25.self_attn.c_attn.q_scale",
"shape": [
4096,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 524288,
"byteOffset": 18354432
},
{
"name": "model.layers.25.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 18878720
},
{
"name": "model.layers.25.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 20975872
},
{
"name": "model.layers.25.self_attn.q_norm.weight",
"shape": [
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 256,
"byteOffset": 21238016
},
{
"name": "model.layers.26.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 21238272
},
{
"name": "model.layers.26.mlp.down_proj.q_weight",
"shape": [
2048,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6291456,
"byteOffset": 21242368
},
{
"name": "model.layers.26.mlp.down_proj.q_scale",
"shape": [
2048,
192
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 786432,
"byteOffset": 27533824
}
],
"md5sum": "d3e740ecfad9a3ccf2d2fdb9355955ad"
},
{
"dataPath": "params_shard_21.bin",
"format": "raw-shard",
"nbytes": 28320256,
"records": [
{
"name": "model.layers.26.mlp.gate_up_proj.q_weight",
"shape": [
12288,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.26.mlp.gate_up_proj.q_scale",
"shape": [
12288,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "model.layers.26.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 14155776
},
{
"name": "model.layers.26.self_attn.k_norm.weight",
"shape": [
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 256,
"byteOffset": 14159872
},
{
"name": "model.layers.26.self_attn.c_attn.q_weight",
"shape": [
4096,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 4194304,
"byteOffset": 14160128
},
{
"name": "model.layers.26.self_attn.c_attn.q_scale",
"shape": [
4096,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 524288,
"byteOffset": 18354432
},
{
"name": "model.layers.26.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 18878720
},
{
"name": "model.layers.26.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 20975872
},
{
"name": "model.layers.26.self_attn.q_norm.weight",
"shape": [
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 256,
"byteOffset": 21238016
},
{
"name": "model.layers.27.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 21238272
},
{
"name": "model.layers.27.mlp.down_proj.q_weight",
"shape": [
2048,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6291456,
"byteOffset": 21242368
},
{
"name": "model.layers.27.mlp.down_proj.q_scale",
"shape": [
2048,
192
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 786432,
"byteOffset": 27533824
}
],
"md5sum": "2fe7c392d38f70f07aafb20300075c4d"
},
{
"dataPath": "params_shard_22.bin",
"format": "raw-shard",
"nbytes": 28320256,
"records": [
{
"name": "model.layers.27.mlp.gate_up_proj.q_weight",
"shape": [
12288,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.27.mlp.gate_up_proj.q_scale",
"shape": [
12288,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "model.layers.27.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 14155776
},
{
"name": "model.layers.27.self_attn.k_norm.weight",
"shape": [
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 256,
"byteOffset": 14159872
},
{
"name": "model.layers.27.self_attn.c_attn.q_weight",
"shape": [
4096,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 4194304,
"byteOffset": 14160128
},
{
"name": "model.layers.27.self_attn.c_attn.q_scale",
"shape": [
4096,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 524288,
"byteOffset": 18354432
},
{
"name": "model.layers.27.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 18878720
},
{
"name": "model.layers.27.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 20975872
},
{
"name": "model.layers.27.self_attn.q_norm.weight",
"shape": [
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 256,
"byteOffset": 21238016
},
{
"name": "model.layers.3.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 21238272
},
{
"name": "model.layers.3.mlp.down_proj.q_weight",
"shape": [
2048,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6291456,
"byteOffset": 21242368
},
{
"name": "model.layers.3.mlp.down_proj.q_scale",
"shape": [
2048,
192
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 786432,
"byteOffset": 27533824
}
],
"md5sum": "b9c4176e573da8172ca5a96433078374"
},
{
"dataPath": "params_shard_23.bin",
"format": "raw-shard",
"nbytes": 28320256,
"records": [
{
"name": "model.layers.3.mlp.gate_up_proj.q_weight",
"shape": [
12288,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.3.mlp.gate_up_proj.q_scale",
"shape": [
12288,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "model.layers.3.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 14155776
},
{
"name": "model.layers.3.self_attn.k_norm.weight",
"shape": [
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 256,
"byteOffset": 14159872
},
{
"name": "model.layers.3.self_attn.c_attn.q_weight",
"shape": [
4096,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 4194304,
"byteOffset": 14160128
},
{
"name": "model.layers.3.self_attn.c_attn.q_scale",
"shape": [
4096,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 524288,
"byteOffset": 18354432
},
{
"name": "model.layers.3.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 18878720
},
{
"name": "model.layers.3.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 20975872
},
{
"name": "model.layers.3.self_attn.q_norm.weight",
"shape": [
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 256,
"byteOffset": 21238016
},
{
"name": "model.layers.4.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 21238272
},
{
"name": "model.layers.4.mlp.down_proj.q_weight",
"shape": [
2048,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6291456,
"byteOffset": 21242368
},
{
"name": "model.layers.4.mlp.down_proj.q_scale",
"shape": [
2048,
192
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 786432,
"byteOffset": 27533824
}
],
"md5sum": "6900f22a21bc76ae5177a47b3a5ef4ea"
},
{
"dataPath": "params_shard_24.bin",
"format": "raw-shard",
"nbytes": 28320256,
"records": [
{
"name": "model.layers.4.mlp.gate_up_proj.q_weight",
"shape": [
12288,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.4.mlp.gate_up_proj.q_scale",
"shape": [
12288,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "model.layers.4.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 14155776
},
{
"name": "model.layers.4.self_attn.k_norm.weight",
"shape": [
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 256,
"byteOffset": 14159872
},
{
"name": "model.layers.4.self_attn.c_attn.q_weight",
"shape": [
4096,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 4194304,
"byteOffset": 14160128
},
{
"name": "model.layers.4.self_attn.c_attn.q_scale",
"shape": [
4096,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 524288,
"byteOffset": 18354432
},
{
"name": "model.layers.4.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 18878720
},
{
"name": "model.layers.4.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 20975872
},
{
"name": "model.layers.4.self_attn.q_norm.weight",
"shape": [
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 256,
"byteOffset": 21238016
},
{
"name": "model.layers.5.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 21238272
},
{
"name": "model.layers.5.mlp.down_proj.q_weight",
"shape": [
2048,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6291456,
"byteOffset": 21242368
},
{
"name": "model.layers.5.mlp.down_proj.q_scale",
"shape": [
2048,
192
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 786432,
"byteOffset": 27533824
}
],
"md5sum": "a4671d62f491feca6b5abae850ac8471"
},
{
"dataPath": "params_shard_25.bin",
"format": "raw-shard",
"nbytes": 28320256,
"records": [
{
"name": "model.layers.5.mlp.gate_up_proj.q_weight",
"shape": [
12288,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.5.mlp.gate_up_proj.q_scale",
"shape": [
12288,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "model.layers.5.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 14155776
},
{
"name": "model.layers.5.self_attn.k_norm.weight",
"shape": [
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 256,
"byteOffset": 14159872
},
{
"name": "model.layers.5.self_attn.c_attn.q_weight",
"shape": [
4096,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 4194304,
"byteOffset": 14160128
},
{
"name": "model.layers.5.self_attn.c_attn.q_scale",
"shape": [
4096,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 524288,
"byteOffset": 18354432
},
{
"name": "model.layers.5.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 18878720
},
{
"name": "model.layers.5.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 20975872
},
{
"name": "model.layers.5.self_attn.q_norm.weight",
"shape": [
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 256,
"byteOffset": 21238016
},
{
"name": "model.layers.6.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 21238272
},
{
"name": "model.layers.6.mlp.down_proj.q_weight",
"shape": [
2048,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6291456,
"byteOffset": 21242368
},
{
"name": "model.layers.6.mlp.down_proj.q_scale",
"shape": [
2048,
192
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 786432,
"byteOffset": 27533824
}
],
"md5sum": "d6d307c2a74e1767768a64e8950d54e3"
},
{
"dataPath": "params_shard_26.bin",
"format": "raw-shard",
"nbytes": 28320256,
"records": [
{
"name": "model.layers.6.mlp.gate_up_proj.q_weight",
"shape": [
12288,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.6.mlp.gate_up_proj.q_scale",
"shape": [
12288,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "model.layers.6.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 14155776
},
{
"name": "model.layers.6.self_attn.k_norm.weight",
"shape": [
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 256,
"byteOffset": 14159872
},
{
"name": "model.layers.6.self_attn.c_attn.q_weight",
"shape": [
4096,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 4194304,
"byteOffset": 14160128
},
{
"name": "model.layers.6.self_attn.c_attn.q_scale",
"shape": [
4096,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 524288,
"byteOffset": 18354432
},
{
"name": "model.layers.6.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 18878720
},
{
"name": "model.layers.6.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 20975872
},
{
"name": "model.layers.6.self_attn.q_norm.weight",
"shape": [
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 256,
"byteOffset": 21238016
},
{
"name": "model.layers.7.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 21238272
},
{
"name": "model.layers.7.mlp.down_proj.q_weight",
"shape": [
2048,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6291456,
"byteOffset": 21242368
},
{
"name": "model.layers.7.mlp.down_proj.q_scale",
"shape": [
2048,
192
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 786432,
"byteOffset": 27533824
}
],
"md5sum": "4ecd795fac93f4f12a67d57500538381"
},
{
"dataPath": "params_shard_27.bin",
"format": "raw-shard",
"nbytes": 28320256,
"records": [
{
"name": "model.layers.7.mlp.gate_up_proj.q_weight",
"shape": [
12288,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.7.mlp.gate_up_proj.q_scale",
"shape": [
12288,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "model.layers.7.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 14155776
},
{
"name": "model.layers.7.self_attn.k_norm.weight",
"shape": [
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 256,
"byteOffset": 14159872
},
{
"name": "model.layers.7.self_attn.c_attn.q_weight",
"shape": [
4096,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 4194304,
"byteOffset": 14160128
},
{
"name": "model.layers.7.self_attn.c_attn.q_scale",
"shape": [
4096,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 524288,
"byteOffset": 18354432
},
{
"name": "model.layers.7.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 18878720
},
{
"name": "model.layers.7.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 20975872
},
{
"name": "model.layers.7.self_attn.q_norm.weight",
"shape": [
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 256,
"byteOffset": 21238016
},
{
"name": "model.layers.8.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 21238272
},
{
"name": "model.layers.8.mlp.down_proj.q_weight",
"shape": [
2048,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6291456,
"byteOffset": 21242368
},
{
"name": "model.layers.8.mlp.down_proj.q_scale",
"shape": [
2048,
192
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 786432,
"byteOffset": 27533824
}
],
"md5sum": "972550bdd74f9801edd50f90081497d5"
},
{
"dataPath": "params_shard_28.bin",
"format": "raw-shard",
"nbytes": 28320256,
"records": [
{
"name": "model.layers.8.mlp.gate_up_proj.q_weight",
"shape": [
12288,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.8.mlp.gate_up_proj.q_scale",
"shape": [
12288,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "model.layers.8.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 14155776
},
{
"name": "model.layers.8.self_attn.k_norm.weight",
"shape": [
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 256,
"byteOffset": 14159872
},
{
"name": "model.layers.8.self_attn.c_attn.q_weight",
"shape": [
4096,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 4194304,
"byteOffset": 14160128
},
{
"name": "model.layers.8.self_attn.c_attn.q_scale",
"shape": [
4096,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 524288,
"byteOffset": 18354432
},
{
"name": "model.layers.8.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 18878720
},
{
"name": "model.layers.8.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 20975872
},
{
"name": "model.layers.8.self_attn.q_norm.weight",
"shape": [
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 256,
"byteOffset": 21238016
},
{
"name": "model.layers.9.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 21238272
},
{
"name": "model.layers.9.mlp.down_proj.q_weight",
"shape": [
2048,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6291456,
"byteOffset": 21242368
},
{
"name": "model.layers.9.mlp.down_proj.q_scale",
"shape": [
2048,
192
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 786432,
"byteOffset": 27533824
}
],
"md5sum": "2ca481551e18546ba61ebf19e1ac842a"
},
{
"dataPath": "params_shard_29.bin",
"format": "raw-shard",
"nbytes": 21242368,
"records": [
{
"name": "model.layers.9.mlp.gate_up_proj.q_weight",
"shape": [
12288,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.9.mlp.gate_up_proj.q_scale",
"shape": [
12288,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "model.layers.9.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 14155776
},
{
"name": "model.layers.9.self_attn.k_norm.weight",
"shape": [
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 256,
"byteOffset": 14159872
},
{
"name": "model.layers.9.self_attn.c_attn.q_weight",
"shape": [
4096,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 4194304,
"byteOffset": 14160128
},
{
"name": "model.layers.9.self_attn.c_attn.q_scale",
"shape": [
4096,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 524288,
"byteOffset": 18354432
},
{
"name": "model.layers.9.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 18878720
},
{
"name": "model.layers.9.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 20975872
},
{
"name": "model.layers.9.self_attn.q_norm.weight",
"shape": [
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 256,
"byteOffset": 21238016
},
{
"name": "model.norm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 21238272
}
],
"md5sum": "efe7be6e6e1170b8af97d9793d660983"
}
]
}