fix: accept **kwargs in Params4bit and Int8Params constructors#1900
Open
ajmeese7 wants to merge 1 commit intobitsandbytes-foundation:mainfrom
Open
fix: accept **kwargs in Params4bit and Int8Params constructors#1900ajmeese7 wants to merge 1 commit intobitsandbytes-foundation:mainfrom
ajmeese7 wants to merge 1 commit intobitsandbytes-foundation:mainfrom
Conversation
accelerate's set_module_tensor_to_device passes the old parameter's __dict__ as **kwargs when reconstituting quantized parameters. Transformers >= 5.x adds _is_hf_initialized to every parameter's __dict__, but Params4bit.__new__ and Int8Params.__new__ had fixed signatures — causing TypeError on any model loaded with BitsAndBytesConfig + device_map="auto". Add **kwargs to both constructors so unexpected attributes are silently ignored instead of crashing.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
accelerate's
set_module_tensor_to_devicepasses the old parameter's__dict__as**kwargswhen reconstituting quantized parameters. Transformers >= 5.x adds_is_hf_initializedto every parameter's__dict__, butParams4bit.__new__andInt8Params.__new__had fixed signatures, causing TypeError on any model loaded with BitsAndBytesConfig +device_map="auto".Add
**kwargsto both constructors so unexpected attributes are silently ignored instead of crashing.