Refactor gguf scripts to improve metadata handling #11909
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
Added contents method to ReaderField class Added endianess property to GGUFReader class
compilade
reviewed
Feb 16, 2025
compilade
approved these changes
Feb 16, 2025
There was a problem hiding this comment.
I did not test gguf_convert_endian or gguf_new_metadata, but I did test ReaderField.contents() in #11909 (comment) and gguf_dump, with both Numpy 1.26.4 and 2.2.0.
This is good and should finally completely fix #10127 even for big-endian models.
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Outdated suggestions cannot be applied.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.
I've had these changes locally for quite a while and more or less forgotten about them, it's high time to make a PR as it fixes a few issues (endianess check) as well as improving and deduplicating metadata handling/rendering across all scripts.
Supercedes #11905