-
Notifications
You must be signed in to change notification settings - Fork 608
Remove logic for appending or prepending tokens #4920
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
Conversation
Stack from ghstack (oldest at bottom): |
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/4920
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 17d39e4 with merge base 0a11e99 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
@helunwencser has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
Summary: Pull Request resolved: #4920 The runner should not prepend or append any tokens to the prompt. Users should make sure that the prompt is properly formatted as the model's chat template. This PR removes the logic for appending or prepending tokens. Test Plan: CI imported-using-ghimport Differential Revision: D61824091 Pulled By: helunwencser
This pull request was exported from Phabricator. Differential Revision: D61824091 |
c1d4884
to
17d39e4
Compare
@helunwencser merged this pull request in a922b3d. |
ghstack-source-id: faf0542 ghstack-comment-id: 2311228673 Pull Request resolved: pytorch/executorch#4920
The runner should not prepend or append any tokens to the prompt. Users should make sure that the prompt is properly formatted as the model's chat template.
This PR removes the logic for appending or prepending tokens.
Test Plan:
CI
Differential Revision: D61824091