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

添加对deepseek v3的支持 #2736

Open
jqhr opened this issue Jan 4, 2025 · 5 comments
Open

添加对deepseek v3的支持 #2736

jqhr opened this issue Jan 4, 2025 · 5 comments
Labels
Milestone

Comments

@jqhr
Copy link

jqhr commented Jan 4, 2025

Feature request / 功能建议

添加对deepseek v3的支持

Motivation / 动机

deepseek v3已开源,希望能跟进一下,非常感谢

Your contribution / 您的贡献

摩搭链接https://modelscope.cn/models/deepseek-ai/DeepSeek-V3/summary

@jqhr jqhr added the feature label Jan 4, 2025
@XprobeBot XprobeBot added this to the v1.x milestone Jan 4, 2025
@qinxuye
Copy link
Contributor

qinxuye commented Jan 6, 2025

deepseek v3 架构和 deepseek v2.5 是一致的。目前这个模型太大了,我们需要一些时间完成测试。

@jqhr
Copy link
Author

jqhr commented Jan 6, 2025

了解了,感谢🙏

@su400
Copy link

su400 commented Jan 7, 2025

我下载了int4版本,在384G显存的机器上勉强能载入,但出来的全是乱码。估计要二台384G显存的机器来分布推理。

@qinxuye
Copy link
Contributor

qinxuye commented Jan 7, 2025

我下载了int4版本,在384G显存的机器上勉强能载入,但出来的全是乱码。估计要二台384G显存的机器来分布推理。

int4 的模型权重是哪个的?

@frankjoey2048
Copy link

frankjoey2048 commented Jan 9, 2025

我下载了int4版本,在384G显存的机器上勉强能载入,但出来的全是乱码。估计要二台384G显存的机器来分布推理。

have you tried this? a version of 2bit https://huggingface.co/unsloth/DeepSeek-V3-GGUF/tree/main

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

No branches or pull requests

5 participants