Restrict generation to sampling and greedy search #201
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
This allows to: - reject unsupported arguments, - detect unsupported configurations, - avoid checking inputs multiple times, - reset cache for greedy search also.
dacorvo
changed the title
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. |
michaelbenayoun
approved these changes
Aug 28, 2023
Co-authored-by: Michael Benayoun <mickbenayoun@gmail.com>
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Outdated suggestions cannot be applied.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.
This refactors the
NeuronModelCausalLMclass to override thegeneratemethod, allowing to restrict the generation to actually supported configurations.This also introduces a simpler generation loop for sampling and greedy search, preparing the integration into TGI.