moss-moon-003-sft-plugin-int4运行提示not a folder containing a `.index.json` file

#1
by citibank - opened

您好,请问下plugin-int4做推理时报这个错是什么原因呢?
image.png

缺文件,在其它几个大一些的模型仓库里有一个pytorch_model.bin.index.json文件,这里没有

我在mac上,pip3 install triton一直安装不上,把triton git source下载下来编译也一直报错。请问有遇到这种情况吗?
Failed to build triton
ERROR: Could not build wheels for triton, which is required to install pyproject.toml-based projects

ly@B-FCAJMD6M-1650 python % /usr/local/Cellar/[email protected]/3.8.16/Frameworks/Python.framework/Versions/3.8/bin/python3.8 -m pip install triton

DEPRECATION: Configuring installation scheme with distutils config files is deprecated and will no longer work in the near future. If you are using a Homebrew or Linuxbrew Python, please see discussion at https://github.com/Homebrew/homebrew-core/issues/76621
ERROR: Could not find a version that satisfies the requirement triton (from versions: none)
ERROR: No matching distribution found for triton

我在mac上,pip3 install triton一直安装不上,把triton git source下载下来编译也一直报错。请问有遇到这种情况吗?
Failed to build triton
ERROR: Could not build wheels for triton, which is required to install pyproject.toml-based projects

ly@B-FCAJMD6M-1650 python % /usr/local/Cellar/[email protected]/3.8.16/Frameworks/Python.framework/Versions/3.8/bin/python3.8 -m pip install triton

DEPRECATION: Configuring installation scheme with distutils config files is deprecated and will no longer work in the near future. If you are using a Homebrew or Linuxbrew Python, please see discussion at https://github.com/Homebrew/homebrew-core/issues/76621
ERROR: Could not find a version that satisfies the requirement triton (from versions: none)
ERROR: No matching distribution found for triton

triton只支持linux,我看到主仓库issue里有人提到了https://github.com/OpenLMLab/MOSS/issues/68
,他们正在尝试解决这个问题

感谢大神回复。

请问有评估量化版本和原始版本效果对比吗? moss模型与gpt3、llama等模型效果比较评测报告在哪里可以访问查看吗?

您好,请问下plugin-int4做推理时报这个错是什么原因呢?
image.png

一样的问题,有什么解决方案吗

同样的issue,望解决

same error :is not a folder containing a .index.json file.

回复两个问题:

  1. 目前Openai triton暂时不支持windows和mac系统。
  2. 目前的量化版本仅支持单卡推理。可以在官方github repo中的moss_inference.py中根据注释将模型读取方式修改至以下方式:

model = MossForCausalLM.from_pretrained("fnlp/moss-moon-003-sft-int4").half().cuda()
infer = Inference(model, device_map="auto")

您好,请问下plugin-int4做推理时报这个错是什么原因呢?
image.png

{
"metadata": {
"total_size": 10783249967
},
"weight_map": {
"lm_head.bias": "pytorch_model.bin",
"lm_head.weight": "pytorch_model.bin",
"transformer.h.0.attn.causal_mask": "pytorch_model.bin",
"transformer.h.0.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.0.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.0.ln_1.bias": "pytorch_model.bin",
"transformer.h.0.ln_1.weight": "pytorch_model.bin",
"transformer.h.0.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.0.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.0.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.0.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.1.attn.causal_mask": "pytorch_model.bin",
"transformer.h.1.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.1.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.1.ln_1.bias": "pytorch_model.bin",
"transformer.h.1.ln_1.weight": "pytorch_model.bin",
"transformer.h.1.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.1.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.1.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.1.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.10.attn.causal_mask": "pytorch_model.bin",
"transformer.h.10.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.10.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.10.ln_1.bias": "pytorch_model.bin",
"transformer.h.10.ln_1.weight": "pytorch_model.bin",
"transformer.h.10.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.10.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.10.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.10.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.11.attn.causal_mask": "pytorch_model.bin",
"transformer.h.11.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.11.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.11.ln_1.bias": "pytorch_model.bin",
"transformer.h.11.ln_1.weight": "pytorch_model.bin",
"transformer.h.11.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.11.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.11.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.11.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.12.attn.causal_mask": "pytorch_model.bin",
"transformer.h.12.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.12.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.12.ln_1.bias": "pytorch_model.bin",
"transformer.h.12.ln_1.weight": "pytorch_model.bin",
"transformer.h.12.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.12.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.12.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.12.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.13.attn.causal_mask": "pytorch_model.bin",
"transformer.h.13.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.13.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.13.ln_1.bias": "pytorch_model.bin",
"transformer.h.13.ln_1.weight": "pytorch_model.bin",
"transformer.h.13.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.13.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.13.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.13.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.14.attn.causal_mask": "pytorch_model.bin",
"transformer.h.14.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.14.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.14.ln_1.bias": "pytorch_model.bin",
"transformer.h.14.ln_1.weight": "pytorch_model.bin",
"transformer.h.14.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.14.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.14.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.14.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.15.attn.causal_mask": "pytorch_model.bin",
"transformer.h.15.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.15.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.15.ln_1.bias": "pytorch_model.bin",
"transformer.h.15.ln_1.weight": "pytorch_model.bin",
"transformer.h.15.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.15.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.15.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.15.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.16.attn.causal_mask": "pytorch_model.bin",
"transformer.h.16.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.16.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.16.ln_1.bias": "pytorch_model.bin",
"transformer.h.16.ln_1.weight": "pytorch_model.bin",
"transformer.h.16.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.16.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.16.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.16.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.17.attn.causal_mask": "pytorch_model.bin",
"transformer.h.17.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.17.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.17.ln_1.bias": "pytorch_model.bin",
"transformer.h.17.ln_1.weight": "pytorch_model.bin",
"transformer.h.17.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.17.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.17.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.17.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.18.attn.causal_mask": "pytorch_model.bin",
"transformer.h.18.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.18.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.18.ln_1.bias": "pytorch_model.bin",
"transformer.h.18.ln_1.weight": "pytorch_model.bin",
"transformer.h.18.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.18.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.18.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.18.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.19.attn.causal_mask": "pytorch_model.bin",
"transformer.h.19.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.19.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.19.ln_1.bias": "pytorch_model.bin",
"transformer.h.19.ln_1.weight": "pytorch_model.bin",
"transformer.h.19.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.19.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.19.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.19.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.2.attn.causal_mask": "pytorch_model.bin",
"transformer.h.2.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.2.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.2.ln_1.bias": "pytorch_model.bin",
"transformer.h.2.ln_1.weight": "pytorch_model.bin",
"transformer.h.2.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.2.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.2.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.2.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.20.attn.causal_mask": "pytorch_model.bin",
"transformer.h.20.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.20.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.20.ln_1.bias": "pytorch_model.bin",
"transformer.h.20.ln_1.weight": "pytorch_model.bin",
"transformer.h.20.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.20.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.20.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.20.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.21.attn.causal_mask": "pytorch_model.bin",
"transformer.h.21.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.21.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.21.ln_1.bias": "pytorch_model.bin",
"transformer.h.21.ln_1.weight": "pytorch_model.bin",
"transformer.h.21.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.21.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.21.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.21.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.22.attn.causal_mask": "pytorch_model.bin",
"transformer.h.22.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.22.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.22.ln_1.bias": "pytorch_model.bin",
"transformer.h.22.ln_1.weight": "pytorch_model.bin",
"transformer.h.22.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.22.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.22.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.22.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.23.attn.causal_mask": "pytorch_model.bin",
"transformer.h.23.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.23.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.23.ln_1.bias": "pytorch_model.bin",
"transformer.h.23.ln_1.weight": "pytorch_model.bin",
"transformer.h.23.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.23.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.23.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.23.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.24.attn.causal_mask": "pytorch_model.bin",
"transformer.h.24.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.24.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.24.ln_1.bias": "pytorch_model.bin",
"transformer.h.24.ln_1.weight": "pytorch_model.bin",
"transformer.h.24.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.24.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.24.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.24.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.25.attn.causal_mask": "pytorch_model.bin",
"transformer.h.25.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.25.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.25.ln_1.bias": "pytorch_model.bin",
"transformer.h.25.ln_1.weight": "pytorch_model.bin",
"transformer.h.25.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.25.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.25.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.25.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.26.attn.causal_mask": "pytorch_model.bin",
"transformer.h.26.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.26.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.26.ln_1.bias": "pytorch_model.bin",
"transformer.h.26.ln_1.weight": "pytorch_model.bin",
"transformer.h.26.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.26.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.26.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.26.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.27.attn.causal_mask": "pytorch_model.bin",
"transformer.h.27.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.27.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.27.ln_1.bias": "pytorch_model.bin",
"transformer.h.27.ln_1.weight": "pytorch_model.bin",
"transformer.h.27.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.27.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.27.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.27.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.28.attn.causal_mask": "pytorch_model.bin",
"transformer.h.28.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.28.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.28.ln_1.bias": "pytorch_model.bin",
"transformer.h.28.ln_1.weight": "pytorch_model.bin",
"transformer.h.28.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.28.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.28.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.28.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.29.attn.causal_mask": "pytorch_model.bin",
"transformer.h.29.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.29.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.29.ln_1.bias": "pytorch_model.bin",
"transformer.h.29.ln_1.weight": "pytorch_model.bin",
"transformer.h.29.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.29.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.29.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.29.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.3.attn.causal_mask": "pytorch_model.bin",
"transformer.h.3.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.3.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.3.ln_1.bias": "pytorch_model.bin",
"transformer.h.3.ln_1.weight": "pytorch_model.bin",
"transformer.h.3.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.3.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.3.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.3.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.30.attn.causal_mask": "pytorch_model.bin",
"transformer.h.30.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.30.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.30.ln_1.bias": "pytorch_model.bin",
"transformer.h.30.ln_1.weight": "pytorch_model.bin",
"transformer.h.30.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.30.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.30.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.30.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.31.attn.causal_mask": "pytorch_model.bin",
"transformer.h.31.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.31.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.31.ln_1.bias": "pytorch_model.bin",
"transformer.h.31.ln_1.weight": "pytorch_model.bin",
"transformer.h.31.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.31.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.31.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.31.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.32.attn.causal_mask": "pytorch_model.bin",
"transformer.h.32.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.32.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.32.ln_1.bias": "pytorch_model.bin",
"transformer.h.32.ln_1.weight": "pytorch_model.bin",
"transformer.h.32.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.32.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.32.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.32.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.33.attn.causal_mask": "pytorch_model.bin",
"transformer.h.33.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.33.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.33.ln_1.bias": "pytorch_model.bin",
"transformer.h.33.ln_1.weight": "pytorch_model.bin",
"transformer.h.33.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.33.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.33.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.33.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.4.attn.causal_mask": "pytorch_model.bin",
"transformer.h.4.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.4.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.4.ln_1.bias": "pytorch_model.bin",
"transformer.h.4.ln_1.weight": "pytorch_model.bin",
"transformer.h.4.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.4.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.4.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.4.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.5.attn.causal_mask": "pytorch_model.bin",
"transformer.h.5.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.5.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.5.ln_1.bias": "pytorch_model.bin",
"transformer.h.5.ln_1.weight": "pytorch_model.bin",
"transformer.h.5.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.5.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.5.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.5.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.6.attn.causal_mask": "pytorch_model.bin",
"transformer.h.6.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.6.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.6.ln_1.bias": "pytorch_model.bin",
"transformer.h.6.ln_1.weight": "pytorch_model.bin",
"transformer.h.6.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.6.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.6.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.6.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.7.attn.causal_mask": "pytorch_model.bin",
"transformer.h.7.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.7.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.7.ln_1.bias": "pytorch_model.bin",
"transformer.h.7.ln_1.weight": "pytorch_model.bin",
"transformer.h.7.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.7.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.7.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.7.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.8.attn.causal_mask": "pytorch_model.bin",
"transformer.h.8.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.8.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.8.ln_1.bias": "pytorch_model.bin",
"transformer.h.8.ln_1.weight": "pytorch_model.bin",
"transformer.h.8.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.8.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.8.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.8.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.9.attn.causal_mask": "pytorch_model.bin",
"transformer.h.9.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.9.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.9.ln_1.bias": "pytorch_model.bin",
"transformer.h.9.ln_1.weight": "pytorch_model.bin",
"transformer.h.9.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.9.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.9.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.9.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.ln_f.bias": "pytorch_model.bin",
"transformer.ln_f.weight": "pytorch_model.bin",
"transformer.wte.weight": "pytorch_model.bin"
}
}

保存上述json为pytorch_model.bin.index.json即可。

您好,请问下plugin-int4做推理时报这个错是什么原因呢?
image.png

{
"metadata": {
"total_size": 10783249967
},
"weight_map": {
"lm_head.bias": "pytorch_model.bin",
"lm_head.weight": "pytorch_model.bin",
"transformer.h.0.attn.causal_mask": "pytorch_model.bin",
"transformer.h.0.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.0.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.0.ln_1.bias": "pytorch_model.bin",
"transformer.h.0.ln_1.weight": "pytorch_model.bin",
"transformer.h.0.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.0.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.0.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.0.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.1.attn.causal_mask": "pytorch_model.bin",
"transformer.h.1.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.1.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.1.ln_1.bias": "pytorch_model.bin",
"transformer.h.1.ln_1.weight": "pytorch_model.bin",
"transformer.h.1.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.1.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.1.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.1.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.10.attn.causal_mask": "pytorch_model.bin",
"transformer.h.10.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.10.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.10.ln_1.bias": "pytorch_model.bin",
"transformer.h.10.ln_1.weight": "pytorch_model.bin",
"transformer.h.10.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.10.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.10.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.10.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.11.attn.causal_mask": "pytorch_model.bin",
"transformer.h.11.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.11.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.11.ln_1.bias": "pytorch_model.bin",
"transformer.h.11.ln_1.weight": "pytorch_model.bin",
"transformer.h.11.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.11.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.11.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.11.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.12.attn.causal_mask": "pytorch_model.bin",
"transformer.h.12.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.12.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.12.ln_1.bias": "pytorch_model.bin",
"transformer.h.12.ln_1.weight": "pytorch_model.bin",
"transformer.h.12.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.12.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.12.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.12.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.13.attn.causal_mask": "pytorch_model.bin",
"transformer.h.13.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.13.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.13.ln_1.bias": "pytorch_model.bin",
"transformer.h.13.ln_1.weight": "pytorch_model.bin",
"transformer.h.13.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.13.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.13.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.13.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.14.attn.causal_mask": "pytorch_model.bin",
"transformer.h.14.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.14.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.14.ln_1.bias": "pytorch_model.bin",
"transformer.h.14.ln_1.weight": "pytorch_model.bin",
"transformer.h.14.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.14.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.14.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.14.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.15.attn.causal_mask": "pytorch_model.bin",
"transformer.h.15.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.15.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.15.ln_1.bias": "pytorch_model.bin",
"transformer.h.15.ln_1.weight": "pytorch_model.bin",
"transformer.h.15.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.15.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.15.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.15.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.16.attn.causal_mask": "pytorch_model.bin",
"transformer.h.16.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.16.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.16.ln_1.bias": "pytorch_model.bin",
"transformer.h.16.ln_1.weight": "pytorch_model.bin",
"transformer.h.16.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.16.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.16.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.16.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.17.attn.causal_mask": "pytorch_model.bin",
"transformer.h.17.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.17.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.17.ln_1.bias": "pytorch_model.bin",
"transformer.h.17.ln_1.weight": "pytorch_model.bin",
"transformer.h.17.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.17.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.17.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.17.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.18.attn.causal_mask": "pytorch_model.bin",
"transformer.h.18.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.18.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.18.ln_1.bias": "pytorch_model.bin",
"transformer.h.18.ln_1.weight": "pytorch_model.bin",
"transformer.h.18.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.18.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.18.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.18.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.19.attn.causal_mask": "pytorch_model.bin",
"transformer.h.19.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.19.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.19.ln_1.bias": "pytorch_model.bin",
"transformer.h.19.ln_1.weight": "pytorch_model.bin",
"transformer.h.19.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.19.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.19.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.19.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.2.attn.causal_mask": "pytorch_model.bin",
"transformer.h.2.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.2.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.2.ln_1.bias": "pytorch_model.bin",
"transformer.h.2.ln_1.weight": "pytorch_model.bin",
"transformer.h.2.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.2.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.2.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.2.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.20.attn.causal_mask": "pytorch_model.bin",
"transformer.h.20.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.20.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.20.ln_1.bias": "pytorch_model.bin",
"transformer.h.20.ln_1.weight": "pytorch_model.bin",
"transformer.h.20.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.20.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.20.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.20.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.21.attn.causal_mask": "pytorch_model.bin",
"transformer.h.21.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.21.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.21.ln_1.bias": "pytorch_model.bin",
"transformer.h.21.ln_1.weight": "pytorch_model.bin",
"transformer.h.21.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.21.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.21.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.21.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.22.attn.causal_mask": "pytorch_model.bin",
"transformer.h.22.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.22.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.22.ln_1.bias": "pytorch_model.bin",
"transformer.h.22.ln_1.weight": "pytorch_model.bin",
"transformer.h.22.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.22.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.22.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.22.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.23.attn.causal_mask": "pytorch_model.bin",
"transformer.h.23.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.23.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.23.ln_1.bias": "pytorch_model.bin",
"transformer.h.23.ln_1.weight": "pytorch_model.bin",
"transformer.h.23.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.23.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.23.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.23.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.24.attn.causal_mask": "pytorch_model.bin",
"transformer.h.24.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.24.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.24.ln_1.bias": "pytorch_model.bin",
"transformer.h.24.ln_1.weight": "pytorch_model.bin",
"transformer.h.24.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.24.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.24.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.24.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.25.attn.causal_mask": "pytorch_model.bin",
"transformer.h.25.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.25.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.25.ln_1.bias": "pytorch_model.bin",
"transformer.h.25.ln_1.weight": "pytorch_model.bin",
"transformer.h.25.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.25.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.25.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.25.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.26.attn.causal_mask": "pytorch_model.bin",
"transformer.h.26.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.26.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.26.ln_1.bias": "pytorch_model.bin",
"transformer.h.26.ln_1.weight": "pytorch_model.bin",
"transformer.h.26.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.26.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.26.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.26.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.27.attn.causal_mask": "pytorch_model.bin",
"transformer.h.27.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.27.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.27.ln_1.bias": "pytorch_model.bin",
"transformer.h.27.ln_1.weight": "pytorch_model.bin",
"transformer.h.27.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.27.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.27.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.27.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.28.attn.causal_mask": "pytorch_model.bin",
"transformer.h.28.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.28.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.28.ln_1.bias": "pytorch_model.bin",
"transformer.h.28.ln_1.weight": "pytorch_model.bin",
"transformer.h.28.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.28.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.28.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.28.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.29.attn.causal_mask": "pytorch_model.bin",
"transformer.h.29.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.29.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.29.ln_1.bias": "pytorch_model.bin",
"transformer.h.29.ln_1.weight": "pytorch_model.bin",
"transformer.h.29.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.29.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.29.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.29.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.3.attn.causal_mask": "pytorch_model.bin",
"transformer.h.3.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.3.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.3.ln_1.bias": "pytorch_model.bin",
"transformer.h.3.ln_1.weight": "pytorch_model.bin",
"transformer.h.3.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.3.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.3.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.3.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.30.attn.causal_mask": "pytorch_model.bin",
"transformer.h.30.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.30.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.30.ln_1.bias": "pytorch_model.bin",
"transformer.h.30.ln_1.weight": "pytorch_model.bin",
"transformer.h.30.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.30.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.30.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.30.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.31.attn.causal_mask": "pytorch_model.bin",
"transformer.h.31.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.31.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.31.ln_1.bias": "pytorch_model.bin",
"transformer.h.31.ln_1.weight": "pytorch_model.bin",
"transformer.h.31.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.31.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.31.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.31.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.32.attn.causal_mask": "pytorch_model.bin",
"transformer.h.32.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.32.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.32.ln_1.bias": "pytorch_model.bin",
"transformer.h.32.ln_1.weight": "pytorch_model.bin",
"transformer.h.32.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.32.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.32.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.32.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.33.attn.causal_mask": "pytorch_model.bin",
"transformer.h.33.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.33.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.33.ln_1.bias": "pytorch_model.bin",
"transformer.h.33.ln_1.weight": "pytorch_model.bin",
"transformer.h.33.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.33.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.33.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.33.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.4.attn.causal_mask": "pytorch_model.bin",
"transformer.h.4.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.4.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.4.ln_1.bias": "pytorch_model.bin",
"transformer.h.4.ln_1.weight": "pytorch_model.bin",
"transformer.h.4.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.4.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.4.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.4.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.5.attn.causal_mask": "pytorch_model.bin",
"transformer.h.5.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.5.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.5.ln_1.bias": "pytorch_model.bin",
"transformer.h.5.ln_1.weight": "pytorch_model.bin",
"transformer.h.5.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.5.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.5.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.5.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.6.attn.causal_mask": "pytorch_model.bin",
"transformer.h.6.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.6.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.6.ln_1.bias": "pytorch_model.bin",
"transformer.h.6.ln_1.weight": "pytorch_model.bin",
"transformer.h.6.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.6.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.6.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.6.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.7.attn.causal_mask": "pytorch_model.bin",
"transformer.h.7.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.7.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.7.ln_1.bias": "pytorch_model.bin",
"transformer.h.7.ln_1.weight": "pytorch_model.bin",
"transformer.h.7.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.7.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.7.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.7.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.8.attn.causal_mask": "pytorch_model.bin",
"transformer.h.8.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.8.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.8.ln_1.bias": "pytorch_model.bin",
"transformer.h.8.ln_1.weight": "pytorch_model.bin",
"transformer.h.8.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.8.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.8.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.8.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.9.attn.causal_mask": "pytorch_model.bin",
"transformer.h.9.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.9.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.9.ln_1.bias": "pytorch_model.bin",
"transformer.h.9.ln_1.weight": "pytorch_model.bin",
"transformer.h.9.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.9.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.9.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.9.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.ln_f.bias": "pytorch_model.bin",
"transformer.ln_f.weight": "pytorch_model.bin",
"transformer.wte.weight": "pytorch_model.bin"
}
}

保存上述json为pytorch_model.bin.index.json即可。

您好,请问下plugin-int4做推理时报这个错是什么原因呢?
image.png

{
"metadata": {
"total_size": 10783249967
},
"weight_map": {
"lm_head.bias": "pytorch_model.bin",
"lm_head.weight": "pytorch_model.bin",
"transformer.h.0.attn.causal_mask": "pytorch_model.bin",
"transformer.h.0.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.0.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.0.ln_1.bias": "pytorch_model.bin",
"transformer.h.0.ln_1.weight": "pytorch_model.bin",
"transformer.h.0.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.0.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.0.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.0.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.1.attn.causal_mask": "pytorch_model.bin",
"transformer.h.1.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.1.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.1.ln_1.bias": "pytorch_model.bin",
"transformer.h.1.ln_1.weight": "pytorch_model.bin",
"transformer.h.1.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.1.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.1.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.1.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.10.attn.causal_mask": "pytorch_model.bin",
"transformer.h.10.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.10.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.10.ln_1.bias": "pytorch_model.bin",
"transformer.h.10.ln_1.weight": "pytorch_model.bin",
"transformer.h.10.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.10.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.10.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.10.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.11.attn.causal_mask": "pytorch_model.bin",
"transformer.h.11.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.11.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.11.ln_1.bias": "pytorch_model.bin",
"transformer.h.11.ln_1.weight": "pytorch_model.bin",
"transformer.h.11.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.11.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.11.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.11.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.12.attn.causal_mask": "pytorch_model.bin",
"transformer.h.12.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.12.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.12.ln_1.bias": "pytorch_model.bin",
"transformer.h.12.ln_1.weight": "pytorch_model.bin",
"transformer.h.12.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.12.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.12.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.12.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.13.attn.causal_mask": "pytorch_model.bin",
"transformer.h.13.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.13.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.13.ln_1.bias": "pytorch_model.bin",
"transformer.h.13.ln_1.weight": "pytorch_model.bin",
"transformer.h.13.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.13.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.13.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.13.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.14.attn.causal_mask": "pytorch_model.bin",
"transformer.h.14.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.14.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.14.ln_1.bias": "pytorch_model.bin",
"transformer.h.14.ln_1.weight": "pytorch_model.bin",
"transformer.h.14.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.14.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.14.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.14.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.15.attn.causal_mask": "pytorch_model.bin",
"transformer.h.15.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.15.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.15.ln_1.bias": "pytorch_model.bin",
"transformer.h.15.ln_1.weight": "pytorch_model.bin",
"transformer.h.15.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.15.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.15.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.15.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.16.attn.causal_mask": "pytorch_model.bin",
"transformer.h.16.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.16.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.16.ln_1.bias": "pytorch_model.bin",
"transformer.h.16.ln_1.weight": "pytorch_model.bin",
"transformer.h.16.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.16.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.16.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.16.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.17.attn.causal_mask": "pytorch_model.bin",
"transformer.h.17.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.17.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.17.ln_1.bias": "pytorch_model.bin",
"transformer.h.17.ln_1.weight": "pytorch_model.bin",
"transformer.h.17.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.17.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.17.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.17.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.18.attn.causal_mask": "pytorch_model.bin",
"transformer.h.18.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.18.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.18.ln_1.bias": "pytorch_model.bin",
"transformer.h.18.ln_1.weight": "pytorch_model.bin",
"transformer.h.18.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.18.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.18.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.18.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.19.attn.causal_mask": "pytorch_model.bin",
"transformer.h.19.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.19.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.19.ln_1.bias": "pytorch_model.bin",
"transformer.h.19.ln_1.weight": "pytorch_model.bin",
"transformer.h.19.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.19.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.19.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.19.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.2.attn.causal_mask": "pytorch_model.bin",
"transformer.h.2.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.2.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.2.ln_1.bias": "pytorch_model.bin",
"transformer.h.2.ln_1.weight": "pytorch_model.bin",
"transformer.h.2.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.2.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.2.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.2.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.20.attn.causal_mask": "pytorch_model.bin",
"transformer.h.20.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.20.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.20.ln_1.bias": "pytorch_model.bin",
"transformer.h.20.ln_1.weight": "pytorch_model.bin",
"transformer.h.20.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.20.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.20.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.20.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.21.attn.causal_mask": "pytorch_model.bin",
"transformer.h.21.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.21.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.21.ln_1.bias": "pytorch_model.bin",
"transformer.h.21.ln_1.weight": "pytorch_model.bin",
"transformer.h.21.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.21.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.21.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.21.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.22.attn.causal_mask": "pytorch_model.bin",
"transformer.h.22.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.22.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.22.ln_1.bias": "pytorch_model.bin",
"transformer.h.22.ln_1.weight": "pytorch_model.bin",
"transformer.h.22.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.22.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.22.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.22.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.23.attn.causal_mask": "pytorch_model.bin",
"transformer.h.23.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.23.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.23.ln_1.bias": "pytorch_model.bin",
"transformer.h.23.ln_1.weight": "pytorch_model.bin",
"transformer.h.23.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.23.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.23.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.23.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.24.attn.causal_mask": "pytorch_model.bin",
"transformer.h.24.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.24.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.24.ln_1.bias": "pytorch_model.bin",
"transformer.h.24.ln_1.weight": "pytorch_model.bin",
"transformer.h.24.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.24.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.24.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.24.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.25.attn.causal_mask": "pytorch_model.bin",
"transformer.h.25.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.25.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.25.ln_1.bias": "pytorch_model.bin",
"transformer.h.25.ln_1.weight": "pytorch_model.bin",
"transformer.h.25.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.25.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.25.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.25.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.26.attn.causal_mask": "pytorch_model.bin",
"transformer.h.26.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.26.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.26.ln_1.bias": "pytorch_model.bin",
"transformer.h.26.ln_1.weight": "pytorch_model.bin",
"transformer.h.26.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.26.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.26.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.26.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.27.attn.causal_mask": "pytorch_model.bin",
"transformer.h.27.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.27.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.27.ln_1.bias": "pytorch_model.bin",
"transformer.h.27.ln_1.weight": "pytorch_model.bin",
"transformer.h.27.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.27.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.27.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.27.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.28.attn.causal_mask": "pytorch_model.bin",
"transformer.h.28.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.28.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.28.ln_1.bias": "pytorch_model.bin",
"transformer.h.28.ln_1.weight": "pytorch_model.bin",
"transformer.h.28.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.28.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.28.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.28.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.29.attn.causal_mask": "pytorch_model.bin",
"transformer.h.29.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.29.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.29.ln_1.bias": "pytorch_model.bin",
"transformer.h.29.ln_1.weight": "pytorch_model.bin",
"transformer.h.29.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.29.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.29.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.29.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.3.attn.causal_mask": "pytorch_model.bin",
"transformer.h.3.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.3.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.3.ln_1.bias": "pytorch_model.bin",
"transformer.h.3.ln_1.weight": "pytorch_model.bin",
"transformer.h.3.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.3.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.3.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.3.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.30.attn.causal_mask": "pytorch_model.bin",
"transformer.h.30.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.30.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.30.ln_1.bias": "pytorch_model.bin",
"transformer.h.30.ln_1.weight": "pytorch_model.bin",
"transformer.h.30.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.30.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.30.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.30.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.31.attn.causal_mask": "pytorch_model.bin",
"transformer.h.31.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.31.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.31.ln_1.bias": "pytorch_model.bin",
"transformer.h.31.ln_1.weight": "pytorch_model.bin",
"transformer.h.31.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.31.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.31.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.31.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.32.attn.causal_mask": "pytorch_model.bin",
"transformer.h.32.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.32.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.32.ln_1.bias": "pytorch_model.bin",
"transformer.h.32.ln_1.weight": "pytorch_model.bin",
"transformer.h.32.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.32.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.32.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.32.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.33.attn.causal_mask": "pytorch_model.bin",
"transformer.h.33.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.33.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.33.ln_1.bias": "pytorch_model.bin",
"transformer.h.33.ln_1.weight": "pytorch_model.bin",
"transformer.h.33.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.33.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.33.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.33.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.4.attn.causal_mask": "pytorch_model.bin",
"transformer.h.4.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.4.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.4.ln_1.bias": "pytorch_model.bin",
"transformer.h.4.ln_1.weight": "pytorch_model.bin",
"transformer.h.4.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.4.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.4.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.4.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.5.attn.causal_mask": "pytorch_model.bin",
"transformer.h.5.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.5.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.5.ln_1.bias": "pytorch_model.bin",
"transformer.h.5.ln_1.weight": "pytorch_model.bin",
"transformer.h.5.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.5.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.5.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.5.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.6.attn.causal_mask": "pytorch_model.bin",
"transformer.h.6.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.6.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.6.ln_1.bias": "pytorch_model.bin",
"transformer.h.6.ln_1.weight": "pytorch_model.bin",
"transformer.h.6.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.6.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.6.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.6.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.7.attn.causal_mask": "pytorch_model.bin",
"transformer.h.7.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.7.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.7.ln_1.bias": "pytorch_model.bin",
"transformer.h.7.ln_1.weight": "pytorch_model.bin",
"transformer.h.7.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.7.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.7.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.7.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.8.attn.causal_mask": "pytorch_model.bin",
"transformer.h.8.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.8.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.8.ln_1.bias": "pytorch_model.bin",
"transformer.h.8.ln_1.weight": "pytorch_model.bin",
"transformer.h.8.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.8.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.8.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.8.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.9.attn.causal_mask": "pytorch_model.bin",
"transformer.h.9.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.9.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.9.ln_1.bias": "pytorch_model.bin",
"transformer.h.9.ln_1.weight": "pytorch_model.bin",
"transformer.h.9.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.9.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.9.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.9.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.ln_f.bias": "pytorch_model.bin",
"transformer.ln_f.weight": "pytorch_model.bin",
"transformer.wte.weight": "pytorch_model.bin"
}
}

保存上述json为pytorch_model.bin.index.json即可。

这个文件的内容是哪里来的?为啥不放在仓库里

您好,请问下plugin-int4做推理时报这个错是什么原因呢?
image.png

{
"metadata": {
"total_size": 10783249967
},
"weight_map": {
"lm_head.bias": "pytorch_model.bin",
"lm_head.weight": "pytorch_model.bin",
"transformer.h.0.attn.causal_mask": "pytorch_model.bin",
"transformer.h.0.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.0.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.0.ln_1.bias": "pytorch_model.bin",
"transformer.h.0.ln_1.weight": "pytorch_model.bin",
"transformer.h.0.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.0.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.0.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.0.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.1.attn.causal_mask": "pytorch_model.bin",
"transformer.h.1.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.1.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.1.ln_1.bias": "pytorch_model.bin",
"transformer.h.1.ln_1.weight": "pytorch_model.bin",
"transformer.h.1.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.1.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.1.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.1.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.10.attn.causal_mask": "pytorch_model.bin",
"transformer.h.10.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.10.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.10.ln_1.bias": "pytorch_model.bin",
"transformer.h.10.ln_1.weight": "pytorch_model.bin",
"transformer.h.10.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.10.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.10.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.10.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.11.attn.causal_mask": "pytorch_model.bin",
"transformer.h.11.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.11.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.11.ln_1.bias": "pytorch_model.bin",
"transformer.h.11.ln_1.weight": "pytorch_model.bin",
"transformer.h.11.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.11.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.11.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.11.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.12.attn.causal_mask": "pytorch_model.bin",
"transformer.h.12.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.12.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.12.ln_1.bias": "pytorch_model.bin",
"transformer.h.12.ln_1.weight": "pytorch_model.bin",
"transformer.h.12.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.12.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.12.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.12.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.13.attn.causal_mask": "pytorch_model.bin",
"transformer.h.13.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.13.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.13.ln_1.bias": "pytorch_model.bin",
"transformer.h.13.ln_1.weight": "pytorch_model.bin",
"transformer.h.13.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.13.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.13.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.13.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.14.attn.causal_mask": "pytorch_model.bin",
"transformer.h.14.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.14.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.14.ln_1.bias": "pytorch_model.bin",
"transformer.h.14.ln_1.weight": "pytorch_model.bin",
"transformer.h.14.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.14.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.14.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.14.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.15.attn.causal_mask": "pytorch_model.bin",
"transformer.h.15.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.15.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.15.ln_1.bias": "pytorch_model.bin",
"transformer.h.15.ln_1.weight": "pytorch_model.bin",
"transformer.h.15.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.15.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.15.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.15.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.16.attn.causal_mask": "pytorch_model.bin",
"transformer.h.16.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.16.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.16.ln_1.bias": "pytorch_model.bin",
"transformer.h.16.ln_1.weight": "pytorch_model.bin",
"transformer.h.16.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.16.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.16.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.16.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.17.attn.causal_mask": "pytorch_model.bin",
"transformer.h.17.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.17.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.17.ln_1.bias": "pytorch_model.bin",
"transformer.h.17.ln_1.weight": "pytorch_model.bin",
"transformer.h.17.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.17.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.17.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.17.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.18.attn.causal_mask": "pytorch_model.bin",
"transformer.h.18.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.18.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.18.ln_1.bias": "pytorch_model.bin",
"transformer.h.18.ln_1.weight": "pytorch_model.bin",
"transformer.h.18.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.18.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.18.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.18.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.19.attn.causal_mask": "pytorch_model.bin",
"transformer.h.19.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.19.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.19.ln_1.bias": "pytorch_model.bin",
"transformer.h.19.ln_1.weight": "pytorch_model.bin",
"transformer.h.19.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.19.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.19.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.19.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.2.attn.causal_mask": "pytorch_model.bin",
"transformer.h.2.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.2.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.2.ln_1.bias": "pytorch_model.bin",
"transformer.h.2.ln_1.weight": "pytorch_model.bin",
"transformer.h.2.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.2.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.2.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.2.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.20.attn.causal_mask": "pytorch_model.bin",
"transformer.h.20.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.20.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.20.ln_1.bias": "pytorch_model.bin",
"transformer.h.20.ln_1.weight": "pytorch_model.bin",
"transformer.h.20.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.20.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.20.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.20.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.21.attn.causal_mask": "pytorch_model.bin",
"transformer.h.21.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.21.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.21.ln_1.bias": "pytorch_model.bin",
"transformer.h.21.ln_1.weight": "pytorch_model.bin",
"transformer.h.21.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.21.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.21.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.21.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.22.attn.causal_mask": "pytorch_model.bin",
"transformer.h.22.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.22.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.22.ln_1.bias": "pytorch_model.bin",
"transformer.h.22.ln_1.weight": "pytorch_model.bin",
"transformer.h.22.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.22.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.22.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.22.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.23.attn.causal_mask": "pytorch_model.bin",
"transformer.h.23.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.23.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.23.ln_1.bias": "pytorch_model.bin",
"transformer.h.23.ln_1.weight": "pytorch_model.bin",
"transformer.h.23.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.23.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.23.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.23.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.24.attn.causal_mask": "pytorch_model.bin",
"transformer.h.24.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.24.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.24.ln_1.bias": "pytorch_model.bin",
"transformer.h.24.ln_1.weight": "pytorch_model.bin",
"transformer.h.24.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.24.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.24.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.24.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.25.attn.causal_mask": "pytorch_model.bin",
"transformer.h.25.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.25.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.25.ln_1.bias": "pytorch_model.bin",
"transformer.h.25.ln_1.weight": "pytorch_model.bin",
"transformer.h.25.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.25.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.25.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.25.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.26.attn.causal_mask": "pytorch_model.bin",
"transformer.h.26.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.26.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.26.ln_1.bias": "pytorch_model.bin",
"transformer.h.26.ln_1.weight": "pytorch_model.bin",
"transformer.h.26.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.26.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.26.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.26.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.27.attn.causal_mask": "pytorch_model.bin",
"transformer.h.27.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.27.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.27.ln_1.bias": "pytorch_model.bin",
"transformer.h.27.ln_1.weight": "pytorch_model.bin",
"transformer.h.27.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.27.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.27.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.27.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.28.attn.causal_mask": "pytorch_model.bin",
"transformer.h.28.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.28.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.28.ln_1.bias": "pytorch_model.bin",
"transformer.h.28.ln_1.weight": "pytorch_model.bin",
"transformer.h.28.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.28.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.28.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.28.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.29.attn.causal_mask": "pytorch_model.bin",
"transformer.h.29.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.29.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.29.ln_1.bias": "pytorch_model.bin",
"transformer.h.29.ln_1.weight": "pytorch_model.bin",
"transformer.h.29.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.29.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.29.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.29.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.3.attn.causal_mask": "pytorch_model.bin",
"transformer.h.3.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.3.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.3.ln_1.bias": "pytorch_model.bin",
"transformer.h.3.ln_1.weight": "pytorch_model.bin",
"transformer.h.3.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.3.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.3.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.3.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.30.attn.causal_mask": "pytorch_model.bin",
"transformer.h.30.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.30.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.30.ln_1.bias": "pytorch_model.bin",
"transformer.h.30.ln_1.weight": "pytorch_model.bin",
"transformer.h.30.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.30.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.30.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.30.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.31.attn.causal_mask": "pytorch_model.bin",
"transformer.h.31.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.31.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.31.ln_1.bias": "pytorch_model.bin",
"transformer.h.31.ln_1.weight": "pytorch_model.bin",
"transformer.h.31.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.31.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.31.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.31.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.32.attn.causal_mask": "pytorch_model.bin",
"transformer.h.32.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.32.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.32.ln_1.bias": "pytorch_model.bin",
"transformer.h.32.ln_1.weight": "pytorch_model.bin",
"transformer.h.32.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.32.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.32.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.32.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.33.attn.causal_mask": "pytorch_model.bin",
"transformer.h.33.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.33.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.33.ln_1.bias": "pytorch_model.bin",
"transformer.h.33.ln_1.weight": "pytorch_model.bin",
"transformer.h.33.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.33.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.33.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.33.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.4.attn.causal_mask": "pytorch_model.bin",
"transformer.h.4.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.4.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.4.ln_1.bias": "pytorch_model.bin",
"transformer.h.4.ln_1.weight": "pytorch_model.bin",
"transformer.h.4.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.4.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.4.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.4.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.5.attn.causal_mask": "pytorch_model.bin",
"transformer.h.5.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.5.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.5.ln_1.bias": "pytorch_model.bin",
"transformer.h.5.ln_1.weight": "pytorch_model.bin",
"transformer.h.5.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.5.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.5.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.5.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.6.attn.causal_mask": "pytorch_model.bin",
"transformer.h.6.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.6.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.6.ln_1.bias": "pytorch_model.bin",
"transformer.h.6.ln_1.weight": "pytorch_model.bin",
"transformer.h.6.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.6.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.6.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.6.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.7.attn.causal_mask": "pytorch_model.bin",
"transformer.h.7.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.7.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.7.ln_1.bias": "pytorch_model.bin",
"transformer.h.7.ln_1.weight": "pytorch_model.bin",
"transformer.h.7.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.7.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.7.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.7.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.8.attn.causal_mask": "pytorch_model.bin",
"transformer.h.8.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.8.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.8.ln_1.bias": "pytorch_model.bin",
"transformer.h.8.ln_1.weight": "pytorch_model.bin",
"transformer.h.8.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.8.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.8.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.8.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.9.attn.causal_mask": "pytorch_model.bin",
"transformer.h.9.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.9.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.9.ln_1.bias": "pytorch_model.bin",
"transformer.h.9.ln_1.weight": "pytorch_model.bin",
"transformer.h.9.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.9.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.9.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.9.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.ln_f.bias": "pytorch_model.bin",
"transformer.ln_f.weight": "pytorch_model.bin",
"transformer.wte.weight": "pytorch_model.bin"
}
}

保存上述json为pytorch_model.bin.index.json即可。

您好,请问下plugin-int4做推理时报这个错是什么原因呢?
image.png

{
"metadata": {
"total_size": 10783249967
},
"weight_map": {
"lm_head.bias": "pytorch_model.bin",
"lm_head.weight": "pytorch_model.bin",
"transformer.h.0.attn.causal_mask": "pytorch_model.bin",
"transformer.h.0.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.0.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.0.ln_1.bias": "pytorch_model.bin",
"transformer.h.0.ln_1.weight": "pytorch_model.bin",
"transformer.h.0.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.0.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.0.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.0.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.1.attn.causal_mask": "pytorch_model.bin",
"transformer.h.1.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.1.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.1.ln_1.bias": "pytorch_model.bin",
"transformer.h.1.ln_1.weight": "pytorch_model.bin",
"transformer.h.1.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.1.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.1.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.1.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.10.attn.causal_mask": "pytorch_model.bin",
"transformer.h.10.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.10.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.10.ln_1.bias": "pytorch_model.bin",
"transformer.h.10.ln_1.weight": "pytorch_model.bin",
"transformer.h.10.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.10.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.10.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.10.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.11.attn.causal_mask": "pytorch_model.bin",
"transformer.h.11.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.11.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.11.ln_1.bias": "pytorch_model.bin",
"transformer.h.11.ln_1.weight": "pytorch_model.bin",
"transformer.h.11.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.11.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.11.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.11.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.12.attn.causal_mask": "pytorch_model.bin",
"transformer.h.12.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.12.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.12.ln_1.bias": "pytorch_model.bin",
"transformer.h.12.ln_1.weight": "pytorch_model.bin",
"transformer.h.12.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.12.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.12.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.12.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.13.attn.causal_mask": "pytorch_model.bin",
"transformer.h.13.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.13.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.13.ln_1.bias": "pytorch_model.bin",
"transformer.h.13.ln_1.weight": "pytorch_model.bin",
"transformer.h.13.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.13.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.13.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.13.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.14.attn.causal_mask": "pytorch_model.bin",
"transformer.h.14.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.14.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.14.ln_1.bias": "pytorch_model.bin",
"transformer.h.14.ln_1.weight": "pytorch_model.bin",
"transformer.h.14.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.14.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.14.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.14.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.15.attn.causal_mask": "pytorch_model.bin",
"transformer.h.15.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.15.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.15.ln_1.bias": "pytorch_model.bin",
"transformer.h.15.ln_1.weight": "pytorch_model.bin",
"transformer.h.15.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.15.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.15.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.15.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.16.attn.causal_mask": "pytorch_model.bin",
"transformer.h.16.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.16.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.16.ln_1.bias": "pytorch_model.bin",
"transformer.h.16.ln_1.weight": "pytorch_model.bin",
"transformer.h.16.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.16.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.16.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.16.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.17.attn.causal_mask": "pytorch_model.bin",
"transformer.h.17.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.17.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.17.ln_1.bias": "pytorch_model.bin",
"transformer.h.17.ln_1.weight": "pytorch_model.bin",
"transformer.h.17.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.17.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.17.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.17.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.18.attn.causal_mask": "pytorch_model.bin",
"transformer.h.18.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.18.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.18.ln_1.bias": "pytorch_model.bin",
"transformer.h.18.ln_1.weight": "pytorch_model.bin",
"transformer.h.18.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.18.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.18.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.18.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.19.attn.causal_mask": "pytorch_model.bin",
"transformer.h.19.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.19.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.19.ln_1.bias": "pytorch_model.bin",
"transformer.h.19.ln_1.weight": "pytorch_model.bin",
"transformer.h.19.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.19.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.19.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.19.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.2.attn.causal_mask": "pytorch_model.bin",
"transformer.h.2.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.2.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.2.ln_1.bias": "pytorch_model.bin",
"transformer.h.2.ln_1.weight": "pytorch_model.bin",
"transformer.h.2.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.2.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.2.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.2.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.20.attn.causal_mask": "pytorch_model.bin",
"transformer.h.20.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.20.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.20.ln_1.bias": "pytorch_model.bin",
"transformer.h.20.ln_1.weight": "pytorch_model.bin",
"transformer.h.20.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.20.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.20.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.20.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.21.attn.causal_mask": "pytorch_model.bin",
"transformer.h.21.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.21.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.21.ln_1.bias": "pytorch_model.bin",
"transformer.h.21.ln_1.weight": "pytorch_model.bin",
"transformer.h.21.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.21.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.21.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.21.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.22.attn.causal_mask": "pytorch_model.bin",
"transformer.h.22.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.22.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.22.ln_1.bias": "pytorch_model.bin",
"transformer.h.22.ln_1.weight": "pytorch_model.bin",
"transformer.h.22.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.22.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.22.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.22.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.23.attn.causal_mask": "pytorch_model.bin",
"transformer.h.23.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.23.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.23.ln_1.bias": "pytorch_model.bin",
"transformer.h.23.ln_1.weight": "pytorch_model.bin",
"transformer.h.23.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.23.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.23.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.23.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.24.attn.causal_mask": "pytorch_model.bin",
"transformer.h.24.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.24.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.24.ln_1.bias": "pytorch_model.bin",
"transformer.h.24.ln_1.weight": "pytorch_model.bin",
"transformer.h.24.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.24.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.24.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.24.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.25.attn.causal_mask": "pytorch_model.bin",
"transformer.h.25.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.25.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.25.ln_1.bias": "pytorch_model.bin",
"transformer.h.25.ln_1.weight": "pytorch_model.bin",
"transformer.h.25.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.25.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.25.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.25.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.26.attn.causal_mask": "pytorch_model.bin",
"transformer.h.26.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.26.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.26.ln_1.bias": "pytorch_model.bin",
"transformer.h.26.ln_1.weight": "pytorch_model.bin",
"transformer.h.26.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.26.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.26.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.26.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.27.attn.causal_mask": "pytorch_model.bin",
"transformer.h.27.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.27.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.27.ln_1.bias": "pytorch_model.bin",
"transformer.h.27.ln_1.weight": "pytorch_model.bin",
"transformer.h.27.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.27.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.27.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.27.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.28.attn.causal_mask": "pytorch_model.bin",
"transformer.h.28.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.28.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.28.ln_1.bias": "pytorch_model.bin",
"transformer.h.28.ln_1.weight": "pytorch_model.bin",
"transformer.h.28.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.28.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.28.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.28.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.29.attn.causal_mask": "pytorch_model.bin",
"transformer.h.29.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.29.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.29.ln_1.bias": "pytorch_model.bin",
"transformer.h.29.ln_1.weight": "pytorch_model.bin",
"transformer.h.29.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.29.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.29.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.29.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.3.attn.causal_mask": "pytorch_model.bin",
"transformer.h.3.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.3.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.3.ln_1.bias": "pytorch_model.bin",
"transformer.h.3.ln_1.weight": "pytorch_model.bin",
"transformer.h.3.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.3.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.3.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.3.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.30.attn.causal_mask": "pytorch_model.bin",
"transformer.h.30.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.30.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.30.ln_1.bias": "pytorch_model.bin",
"transformer.h.30.ln_1.weight": "pytorch_model.bin",
"transformer.h.30.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.30.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.30.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.30.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.31.attn.causal_mask": "pytorch_model.bin",
"transformer.h.31.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.31.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.31.ln_1.bias": "pytorch_model.bin",
"transformer.h.31.ln_1.weight": "pytorch_model.bin",
"transformer.h.31.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.31.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.31.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.31.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.32.attn.causal_mask": "pytorch_model.bin",
"transformer.h.32.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.32.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.32.ln_1.bias": "pytorch_model.bin",
"transformer.h.32.ln_1.weight": "pytorch_model.bin",
"transformer.h.32.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.32.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.32.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.32.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.33.attn.causal_mask": "pytorch_model.bin",
"transformer.h.33.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.33.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.33.ln_1.bias": "pytorch_model.bin",
"transformer.h.33.ln_1.weight": "pytorch_model.bin",
"transformer.h.33.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.33.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.33.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.33.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.4.attn.causal_mask": "pytorch_model.bin",
"transformer.h.4.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.4.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.4.ln_1.bias": "pytorch_model.bin",
"transformer.h.4.ln_1.weight": "pytorch_model.bin",
"transformer.h.4.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.4.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.4.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.4.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.5.attn.causal_mask": "pytorch_model.bin",
"transformer.h.5.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.5.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.5.ln_1.bias": "pytorch_model.bin",
"transformer.h.5.ln_1.weight": "pytorch_model.bin",
"transformer.h.5.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.5.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.5.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.5.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.6.attn.causal_mask": "pytorch_model.bin",
"transformer.h.6.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.6.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.6.ln_1.bias": "pytorch_model.bin",
"transformer.h.6.ln_1.weight": "pytorch_model.bin",
"transformer.h.6.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.6.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.6.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.6.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.7.attn.causal_mask": "pytorch_model.bin",
"transformer.h.7.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.7.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.7.ln_1.bias": "pytorch_model.bin",
"transformer.h.7.ln_1.weight": "pytorch_model.bin",
"transformer.h.7.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.7.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.7.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.7.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.8.attn.causal_mask": "pytorch_model.bin",
"transformer.h.8.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.8.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.8.ln_1.bias": "pytorch_model.bin",
"transformer.h.8.ln_1.weight": "pytorch_model.bin",
"transformer.h.8.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.8.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.8.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.8.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.h.9.attn.causal_mask": "pytorch_model.bin",
"transformer.h.9.attn.out_proj.weight": "pytorch_model.bin",
"transformer.h.9.attn.qkv_proj.weight": "pytorch_model.bin",
"transformer.h.9.ln_1.bias": "pytorch_model.bin",
"transformer.h.9.ln_1.weight": "pytorch_model.bin",
"transformer.h.9.mlp.fc_in.bias": "pytorch_model.bin",
"transformer.h.9.mlp.fc_in.weight": "pytorch_model.bin",
"transformer.h.9.mlp.fc_out.bias": "pytorch_model.bin",
"transformer.h.9.mlp.fc_out.weight": "pytorch_model.bin",
"transformer.ln_f.bias": "pytorch_model.bin",
"transformer.ln_f.weight": "pytorch_model.bin",
"transformer.wte.weight": "pytorch_model.bin"
}
}

保存上述json为pytorch_model.bin.index.json即可。

这个文件的内容是哪里来的?为啥不放在仓库里

这是我自己修改的,不是官方的。

This comment has been hidden

Sign up or log in to comment