fix: get_prompt goes wrong for Llama-2 #3444
Open
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
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Outdated suggestions cannot be applied.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.
Why are these changes needed?
When adding the first user flag (with a message of "None"), and then check the conversation prompt like this:
The output is "[INST] [INST]". I think this must be a tiny hidden bug for function get_prompt (Llama-2), and I figure out how to fix it.
Related issue number (if applicable)
Some other open-source repositories will use this function to mark the specific slices in the conversation. So this bug may trigger some subtle bug or hard code.
Checks
format.shto lint the changes in this PR.