-
Notifications
You must be signed in to change notification settings - Fork 608
support phi4 in ios demo app #10659
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 phi4 in ios demo app #10659
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/10659
Note: Links to docs will display an error until the docs builds have been completed. ❗ 1 Active SEVsThere are 1 currently active SEVs. If your PR is affected, please view them below: ❌ 1 New Failure, 1 Unrelated FailureAs of commit 0e17a9b with merge base 385d860 ( NEW FAILURE - The following job has failed:
FLAKY - The following job failed but was likely due to flakiness present on trunk:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
This PR needs a
|
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Any special tokens to handle?
Co-authored-by: Jack <[email protected]>
no, the token is handled by the runner.cpp logic because it's in the PTEs metadata. But we should really move this logic (and the template) to the HF tokenizer. The tokenizer.json contains information about both stop tokens and template. |
Yeah we should definitely do that, but I think the prompt templating should be outside of the tokenizer |
As titled --------- Co-authored-by: Jack <[email protected]>
As titled