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

New Model, support DeepSeek MoE model #560

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

New Model, support DeepSeek MoE model #560

wants to merge 1 commit into from

Conversation

xiaobochen123
Copy link

No description provided.

@casper-hansen
Copy link
Owner

Hi @xiaobochen123, thank you for the PR.

I have two questions:

  1. Are you able to provide a model on Huggingface for testing?
  2. Did you test the perplexity to verify the quantized model's performance is good?

@xiaobochen123
Copy link
Author

Hi，@casper-hansen
Q1：https://huggingface.co/deepseek-ai/deepseek-moe-16b-base
Q2： How to test the perplexity?

@casper-hansen
Copy link
Owner

@xiaobochen123

  1. I meant if you could provide an AWQ version of DeepSeek MoE on Huggingface for me to test out?
  2. You can use examples/eval.py. It evaluates perplexity by default.

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

Successfully merging this pull request may close these issues.
2 participants
@xiaobochen123 @casper-hansen