server: allow to specify tokens as strings in logit_bias #5003
Conversation
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
cebtenzzre
reviewed
Jan 17, 2024
z80maniac
force-pushed
the
logit-bias-string
branch
from
958660b to
1e45913
Compare
z80maniac
force-pushed
the
logit-bias-string
branch
from
1e45913 to
44d3269
Compare
z80maniac
force-pushed
the
logit-bias-string
branch
from
44d3269 to
cfaa525
Compare
ggerganov
approved these changes
Feb 9, 2024
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
|
Thanks for this PR. |
I'm not interested in |
jordankanter
pushed a commit
to jordankanter/llama.cpp
that referenced
this pull request
Mar 13, 2024
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Outdated suggestions cannot be applied.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.
Currently, the
logit_biasparam in theserveraccepts token IDs as input. But first these token IDs need to be retrieved from somewhere. It is possible to pass a string to/tokenizeand then use the result. However, it's pretty cumbersome since it requires to code for a completely different endpoint and makes an additional network call.This PR allows to pass the initial string to the
logit_biasparam. This string will then be converted to tokens and the specified bias will be applied to all these tokens.