Add conversion support for CodeLlama 34B #25737
Closed
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
There hasn't been any architectural changes, and I was able to convert the 34B by simply adding in the intermediate size for the model.
|
Doesn't seem to work for 7B and 13B variants. |
|
Conversion doesn't account for the modified tokenizer and the new rope theta value. Closing the PR until someone else implements the new changes. |
|
See #25740 |
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Outdated suggestions cannot be applied.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.
There hasn't been any architectural changes, and I was able to convert the 34B by simply adding in the intermediate size for the model. I have converted the 34B model and it appears to work well.
What does this PR do?
This PR should make it possible to convert the CodeLlama models, recently released by Meta AI.