add additional prompt formats #2140
Closed
Conversation
This file contains hidden or 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
1 participant
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Outdated suggestions cannot be applied.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.
I've added prompt formats for models that I've personally tested as being especially good for RAG:
Zephyr:
Lots of models use the name "zephyr." This new sub-class pertains to the 1.6b and 3b models from stabilityai.. Oldies but goodies (DESPITE the fact that they are "relatively" older models.).
Qwen - pertains to Qwen 2.5 that everybody knows. Not sure if it'll work with the "coder" variants, however.
Exaone - overall exceptional for RAG IMHO and any respectable RAG program should have pre-made templates for these models.
Granite - another that's very good for RAG, relatively new but IBM created especially for enterprise level customer service chat based on a company's knowledge base. Like these new ones a lot.