🔂 Fix repetition penalty #125
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
There was an error occurring because the logits processor was expecting input_ids to be a torch tensor.
Since they are mostly used in the logits processor, this will prevent having to convert them to torch tensor at each decode step. Functionally it should be the same, but slightly more efficient.
|
@tengomucho There are some failing tests 😕 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
What does this PR do?
The generator was crashing when the request parameter container a repetition_penalty > 1.0. This was due to the logits processor expecting params to be torch tensors.
So this is now fixed, and a test has been added to detect any possible regression.