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.

Sign up for GitHub

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

Jump to bottom

同学你的量化支持INT8吗 #104

Open

af-74413592 opened this issue Mar 30, 2023 · 0 comments

af-74413592 commented Mar 30, 2023

上图是第一张卡是chatglm-tuning，下图是alpaca-lora微调llama的那个库，显存占用是你的一半不到。
假如调用起bitsandbytes库的CUDA 8-bit技术。应该就不用这么大的显存了。

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment