Refactor gguf scripts to improve metadata handling #11909
Merged
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
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.
|
@CISC Can you confirm if this is ready to be merged? |
|
@ngxson Yes, it's ready, @compilade will add tests in another PR. |
|
@compilade Thanks. :) Remember to tag the new version, though maybe not before after your PR? |
mglambda
pushed a commit
to mglambda/llama.cpp
that referenced
this pull request
Mar 8, 2025
* Refactor gguf scripts to improve metadata handling Added contents method to ReaderField class Added endianess property to GGUFReader class * update scripts * fix import * remove unused import * attempt to work around flake and pyright errors * second attempt * give up, ignore type * bump version * apply newbyteorder fixes
arthw
pushed a commit
to arthw/llama.cpp
that referenced
this pull request
Mar 19, 2025
* Refactor gguf scripts to improve metadata handling Added contents method to ReaderField class Added endianess property to GGUFReader class * update scripts * fix import * remove unused import * attempt to work around flake and pyright errors * second attempt * give up, ignore type * bump version * apply newbyteorder fixes
mostlyuseful
pushed a commit
to mostlyuseful/llama.cpp
that referenced
this pull request
May 12, 2025
* Refactor gguf scripts to improve metadata handling Added contents method to ReaderField class Added endianess property to GGUFReader class * update scripts * fix import * remove unused import * attempt to work around flake and pyright errors * second attempt * give up, ignore type * bump version * apply newbyteorder fixes
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