Update llm_llama_cpp.py to support .gguf files. Update README. Closes #10. #16
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
…ect that change. Closes simonw#10.
|
Thanks for this. I'm going to remove the file extension check entirely and merge this - I don't want to get caught out in the future if they change the extension again. The README updates are excellent. |
simonw
added a commit
that referenced
this pull request
Sep 22, 2023
simonw
added a commit
that referenced
this pull request
Sep 22, 2023
simonw
added a commit
that referenced
this pull request
Sep 22, 2023
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.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 updated llm_llama_cpp.py to accept .gguf files instead of .bin files as they are the new standard (per discussion in #10). I updated the README to reflect that change and use .gguf models in place of the .bin files and added an example for the new python model, which may be of particular interest to users.
I removed the instructions for installing via the wheel since that will use the old code which would reject downloads with .gguf. I thought this was a better solution than explaining the difference and potentially having users have an out of date version which won't be able to use new models. I'm happy to discuss alternatives, though.