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.

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

请问V100单卡能跑得动 glm-10b-ch 的推理和 finetune 吗？ #99

Closed
tianxinliao opened this issue Nov 14, 2022 · 3 comments · Fixed by #102
Closed

请问V100单卡能跑得动 glm-10b-ch 的推理和 finetune 吗？ #99

tianxinliao opened this issue Nov 14, 2022 · 3 comments · Fixed by #102

Comments

@tianxinliao
Copy link

我在 V100 单卡上可以跑得动 glm-10b 英文的推理，但是跑 quickstart 中的任务时把模型改成 glm-10b-ch 就会 OOM
@BAAI-OpenPlatform
Copy link
Collaborator

我们正在尝试复现您的问题，请耐心等待。

@BAAI-OpenPlatform
Copy link
Collaborator

可以在加载模型的时候将model=loader.get_model() 改成model = loader.get_model().half()
通过这种方式将模型转化为float16， 在V100里就可以装下了。而且这样不会影响预测结果，因为GLM模型本身训练的时候就是float16。

@marscrazy marscrazy linked a pull request Nov 15, 2022 that will close this issue
Fix readme file and issue_99 #102
Merged
@tianxinliao
Copy link
Author

可以了，谢谢

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

Fix readme file and issue_99
2 participants
@tianxinliao @BAAI-OpenPlatform