Add ability to ban tokens on exl3 backend#432
Closed
ethanj801 wants to merge 2 commits into
Closed
Conversation
Contributor
Author
|
One could argue this sampler class should be present in exl3 rather than here (happy to move it there if desired). |
Contributor
Author
|
Going to move this into exl3 and then update tabby when exl3 updates |
This file contains hidden or 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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Is your pull request related to a problem? Please describe.
TabbyAPI exposes the fields
ban_eos_tokenandbanned_tokenswhich can be used to allow for generation to continue indefinitely or to ban certain desired tokens. However this feature does nothing when using the exl3 backend. This PR resolves this.Why should this feature be added?
These fields are present (or have equivalent features) across OAI compatible implementations (e.g. textgen). It also is present in TabbyAPI's own exl2 implementation.