Use a different model to guess pip and respond #80
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
If we finetune a model it will learn to always respond in python surrounded with backticks so it won't be able to produce pip packages well. We need to have a different model.
PCSwingle
reviewed
Feb 16, 2024
| model = "gpt-3.5-turbo" | ||
| else: | ||
| model = llm_model | ||
|
|
||
| custom_llm_provider = self.config.get("llm_custom_provider") |
There was a problem hiding this comment.
What if the user is using a different llm provider (like ollama)? It would be kind of annoying to have to change the pip model as well. But I guess that's a very niche scenario so it probably doesn't matter.
There was a problem hiding this comment.
It should only be an issue if they are using ollama with a rawdog fine tuned model. Otherwise they'll just get the same model for both llm_model and pip_model which is what they would want.
PCSwingle
approved these changes
Feb 16, 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Outdated suggestions cannot be applied.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.
If we finetune a model it will learn to always respond in python surrounded with backticks so it won't be able to produce pip packages well. We need to have a different model.