common, server : Feature - surface min_keep as its own parameter #5567
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
ggerganov
approved these changes
Feb 18, 2024
jordankanter
pushed a commit
to jordankanter/llama.cpp
that referenced
this pull request
Mar 13, 2024
* Feature - surface min_keep as its own parameter * Updated README with min_keep param
hodlen
pushed a commit
to hodlen/llama.cpp
that referenced
this pull request
Apr 1, 2024
* Feature - surface min_keep as its own parameter * Updated README with min_keep param
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Outdated suggestions cannot be applied.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.
Re-add the unused min_keep parameter and surface it in common and server.
This was previously set to n_probs when used by server, which had the effect of forcing samplers to return a certain number of results. This was not the documented behavior of n_probs.
This PR creates a new parameter, also named
min_keepto regain the old behavior since it was already effectively implemented.As mentioned in: #5564