Skip to content

adjust rtol on certain tasks for Qwen2.5 models to match measured #27

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

Open
wants to merge 4 commits into
base: main
Choose a base branch
from

Conversation

derekk-nm
Copy link
Contributor

SUMMARY:
adjust rtol on certain tasks to match measured. research will need to review to approve the values.

TEST PLAN:

  • Qwen/Qwen2.5-7B-Instruct: accuracy
  • RedHatAI/Qwen2.5-7B-Instruct-FP8-dynamic: accuracy
  • RedHatAI/Qwen2.5-7B-Instruct-quantized.w4a16: accuracy
  • RedHatAI/Qwen2.5-7B-Instruct-quantized.w8a8: accuracy
  • RedHatAI/Qwen2.5-7B-quantized.w4a16: accuracy

@derekk-nm derekk-nm requested a review from dhuangnm April 24, 2025 12:28
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

Successfully merging this pull request may close these issues.

1 participant