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

Update ITREX version in ONNXRT WOQ example and fix bugs in hf models #1333

Merged
merged 2 commits into from
Oct 19, 2023

Conversation

yuwenzho
Copy link
Contributor

Type of Change

bug fix
API not change

Description

  1. Update ITREX version in ONNXRT WOQ example since ITREX v1.2 was released.
  2. Fix accuracy tuning failed of huggingface question answering models
    2.1 Update outdated models on test machines (exported with torch1.13 -> exported with torch2.0)
    2.2 Update PostTrainingQuantConfig setting

How has this PR been tested?

CI, extension test

Dependency Change?

no

Signed-off-by: yuwenzho <[email protected]>
Signed-off-by: yuwenzho <[email protected]>
@yuwenzho yuwenzho added the bug fix Something isn't working label Oct 19, 2023
@yuwenzho
Copy link
Contributor Author

pass extension test of hf models.

@chensuyue
Copy link
Contributor

pass extension test of hf models.

Did you test WOQ with llama?

@yuwenzho
Copy link
Contributor Author

pass extension test of hf models.

Did you test WOQ with llama?

Extension test of llama-7b int8 quantization.
Module import of intel_extension_for_transformers evaluate API works fine.

@chensuyue chensuyue merged commit d817328 into master Oct 19, 2023
10 checks passed
@chensuyue chensuyue deleted the yuwenzho/fix_example branch October 19, 2023 06:36
bmyrcha pushed a commit that referenced this pull request Oct 24, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
bug fix Something isn't working
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants