feat: update defaults to use latest model versions for gpt-4 and gpt-3.5 #138
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
koffeeking
approved these changes
May 24, 2024
casret
approved these changes
May 24, 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Outdated suggestions cannot be applied.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.
This pull request introduces updates to the default model configurations in the
config.luafile to leverage the latest versions of OpenAI's models. Specifically, thegpt-4omodel has replaced the previousgpt-4-1106-previewmodel, and thegpt-3.5-turbomodel has replaced thegpt-3.5-turbo-1106model. These changes have been applied across various sections of the configuration to ensure consistency and improved performance.The primary motivation for this update is to take advantage of the enhanced capabilities and optimizations available in the latest model versions. By transitioning to
gpt-4oandgpt-3.5-turbo, users can expect more accurate and efficient AI responses, whether they are engaging in chat-based interactions or utilizing the models for command-based tasks. The new gpt-4o model is also 50% cheaper.In addition to updating the model names, the associated parameters such as temperature and top_p values remain unchanged to retain the existing behavior of the AI. This ensures a smooth transition for users while benefiting from the advancements in the underlying AI technology.