-
Notifications
You must be signed in to change notification settings - Fork 120
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
Support Qwen in model builder #739
Conversation
cc @kunal-vaishnavi for review |
Thanks @kunal-vaishnavi, updated. I realized we will need to introduce the Qwen tokenizer as well for it to run e2e in OGA. I'm putting Qwen in "Under Development" column for now. |
What tokenizer does Qwen use? Does it use same tokenizer as llama? |
Synced up with @wenbingl. There needs a small change to support Qwen tokenizer. He will add the change. |
a quick PR is here: microsoft/onnxruntime-extensions#781 |
Thank you for the quick response @wenbingl, @yufenglee! I have validated your fix enables the qwen generation e2e. Should I wait for the PR in extension to merge, and then include the commit update in this PR? |
Yes, let's wait so that Qwen can be supported end-to-end with this PR. |
the PR in ort-extensions was merged. |
Updated. @kunal-vaishnavi PTAL. |
Resolves #718
cc @spandantiwari-amd