PR #33122 remove to restriction for 4-bit model

remove to restriction for 4-bit model #33122

SunMarc merged 5 commits into main from remove_to_4bit

remove to restiction for 4-bit model

08f9c937

matthewdouglas commented on 2024-08-26

matthewdouglas added Quantization

Update src/transformers/modeling_utils.py

bb12e883

bitsandbytes: prevent dtype casting while allowing device movement wi…

d064b48a

matthewdouglas commented on 2024-08-27

quality fix

22f60881

matthewdouglas marked this pull request as ready for review 1 year ago

matthewdouglas requested a review from

ArthurZucker 1 year ago

matthewdouglas requested a review from

LysandreJik 1 year ago

LysandreJik approved these changes on 2024-08-30

Improve warning message for .to() and .cuda() on bnb quantized models

462ac2c3

ArthurZucker approved these changes on 2024-08-30

SunMarc merged 9ea1eacd into main 1 year ago

SunMarc deleted the remove_to_4bit branch 1 year ago

Reviewers

ArthurZucker

LysandreJik

matthewdouglas

Assignees

No one assigned

Labels

Quantization

Milestone

No milestone