Set default params for Watsonx chat & text models #260
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
vazirim
reviewed
Jan 15, 2025
pyproject.toml
Outdated
There was a problem hiding this comment.
We just removed the upper bound on LiteLLM per user's request. See the latest in main, including changes to watsonx examples. Please merge that.
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Outdated suggestions cannot be applied.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.
As of LiteLLM 1.52.1, model prefix
watsonx/points to the/chatendpoint. See change here. This endpoint has several differences in accepted parameters, and more sane defaults. It supportsjson_objectas aresponse_format, and the endpoint supports tool calling (future work for PDL). Rather than handle different LiteLLM dependency versions pointing to different APIs, this PR also bumps the minimum LiteLLM version needed. One thing to note,set_default_granite_model_parametersis only called for granite models of course. This means that using Granite, the default will be greedy decoding/temp = 0, and for any other model, the default is temp = 1. That could be a surprising difference in behavior.