gyou2021
gyou2021
@microsoft-github-policy-service agree @microsoft-github-policy-service agree company="Intel"
Sure. I updated the code to enable it to run out-of-box. Thank you for your comments. > Hi @gyou2021 I like the goal to avoid repetition of same logic from...
@ssarkar2 I added Qwen2-MoE test code in test_text_generation_example.py according to your comments in https://github.com/huggingface/optimum-habana/pull/1162. What's more, I created a new branch qwen2-moe following the guidance of https://github.com/huggingface/optimum/blob/main/CONTRIBUTING.md. Thank you.
Hi @imangohari1 Thank you for your comments. I added Qwen2-7B test and removed repeated Qwen1.5-7B test in tests/test_text_generation_example.py according to 0001-fea-ci-Added-qwen2-7b-bs-512.patch. Since "error: tests/test_text_generation_example.py: does not match index" showed when...
> @gyou2021 Can you please address Regiss comments? Tnx Sure. Done.
> There are quite a lot of commented code in the modeling file, can you clean that a bit please? Thank you for your comment. The code has been cleaned.
> @gyou2021 There are merge conflicts to solve edit: solved Thank you.
> Thanks for the refactoring, the code is much cleaner with the separation of the logics for training, pre-fill and decode. Here are some comments: > > * Can you...
@regisss Would you please review this PR? Thank you.
@regisss Would you please review this PR? Thank you.