Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[BUG] MiniCPM-o 2.6 int4版本的下载链接是404 #718

Closed
2 tasks done
JV-X opened this issue Jan 15, 2025 · 6 comments
Closed
2 tasks done

[BUG] MiniCPM-o 2.6 int4版本的下载链接是404 #718

JV-X opened this issue Jan 15, 2025 · 6 comments
Assignees

Comments

@JV-X
Copy link

JV-X commented Jan 15, 2025

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

我用尝试用 MiniCPM-o 2.6 模型在本次测试,我用的是 RTX-4090 D 显卡24G显存,但是遇到了OOM错误,于是我尝试使用量化版本,但文档里给出的下载连接是404, huggingface 和 modelscope 上都没有这个模型。

期望行为 | Expected Behavior

能在我的4090D成功运行MiniCPM-o 2.6模型,或者提供量化版本的MiniCPM-o 2.6 int4 下载链接

复现方法 | Steps To Reproduce

just follow the readme.md

运行环境 | Environment

- OS: Windows 11 with WSL2
- Python:3.10
- Transformers:4.44.2
- PyTorch:2.2.0
- CUDA (`python -c 'import torch; print(torch.version.cuda)'`):12.1

备注 | Anything else?

No response

@1WorldCapture
Copy link

+1, 期待

@learn-G-p
Copy link

+1,期待

@tc-mb
Copy link
Collaborator

tc-mb commented Jan 15, 2025

你好,我正在上传这两个库。传输花的时间比之前估计的要长,今天应该可以传好。
另外,我们的模型应该只占用18-19G的显存(bf16精度下),应该能够在24G下进行推理。
可以检查一下是否没有将读取精度设置为bf16。
希望这能帮到你。

@tc-mb tc-mb self-assigned this Jan 15, 2025
@1WorldCapture
Copy link

可以下载了,赞。另外requirements_o2.6.txt缺少两个依赖包,如果要用int4: optimum auto-gptq @tc-mb

@tc-mb
Copy link
Collaborator

tc-mb commented Jan 15, 2025

我明天补上,感谢你的反馈。

@JV-X
Copy link
Author

JV-X commented Jan 16, 2025

你好,我正在上传这两个库。传输花的时间比之前估计的要长,今天应该可以传好。 另外,我们的模型应该只占用18-19G的显存(bf16精度下),应该能够在24G下进行推理。 可以检查一下是否没有将读取精度设置为bf16。 希望这能帮到你。

感谢您的回复

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

5 participants