Add validation for model_name parameter #476
Merged
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
|
Thank you for the contribution! Could you run |
rlouf
force-pushed
the
475-validate-openai-model-names
branch
from
5a4f911
to
5d64c5f
Compare
rlouf
force-pushed
the
475-validate-openai-model-names
branch
from
5d64c5f
to
c0fd9d5
Compare
|
I fixed the code formatting and squashed the commit. Thank you for contirbuting! |
benlipkin
pushed a commit
to benlipkin/outlines
that referenced
this pull request
Jan 5, 2024
This PR introduces a validation check for the `model_name` parameter within the `openai` method of the `outlines.models` module. The aim is to ensure that only valid model names are used when calling this function. As per the current implementation, any string passed as the `model_name` would be accepted. The change enforces the function to only accept `gpt-4` or `gpt-3.5-turbo` as valid model names. If any other model name is passed, a ValueError is raised, informing the user about the invalid input and suggesting the correct model names. This change also adds tests to `tests/models/test_openai.py`. To ensure an invalid model raises a value error. Note: I added `gpt-4-1106-preview` in the tests, so when or if it's added to the suite of models supported by outlines, that will need to be updated, along with the mode in `openai.py` Co-authored-by: Stephen Witkowski <stephen.witkowski@proton.me>
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Outdated suggestions cannot be applied.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 PR introduces a validation check for the
model_nameparameter within theopenaimethod of theoutlines.modelsmodule. The aim is to ensure that only valid model names are used when calling this function. As per the current implementation, any string passed as themodel_namewould be accepted.The change enforces the function to only accept
gpt-4orgpt-3.5-turboas valid model names. If any other model name is passed, a ValueError is raised, informing the user about the invalid input and suggesting the correct model names.This change also adds tests to
tests/models/test_openai.py. To ensure an invalid model raises a value error.Note: I added
gpt-4-1106-previewin the tests, so when or if it's added to the suite of models supported by outlines, that will need to be updated, along with the mode inopenai.py