[BUG] <title>使用Qwen-VL-Chat-Int4报错
lzh1998-jansen opened this issue · comments
是否已有关于该错误的issue或讨论? | Is there an existing issue / discussion for this?
- 我已经搜索过已有的issues和讨论 | I have searched the existing issues / discussions
该问题是否在FAQ中有解答? | Is there an existing answer for this in FAQ?
- 我已经搜索过FAQ | I have searched FAQ
当前行为 | Current Behavior
我按照README给出的教程,安装环境、以及安装autoaptq,autogptq 尝试过本项目给出的命令,以及 autogptq官方的 whl 安装命令,都进行尝试过,都可以安装成功。 但是,执行代码,预测的时候均报错,
期望行为 | Expected Behavior
解决此问题,能完成量化模型的应用
复现方法 | Steps To Reproduce
No response
运行环境 | Environment
- OS:
- Python:
- Transformers:
- PyTorch:
- CUDA (`python -c 'import torch; print(torch.version.cuda)'`):
运行环境 torch :2.1.2+cu121
nvcc: 11.8
其他依赖、均满足readme 要求,
备注 | Anything else?
No response