🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
fix: add identity reverse_op to dequantize ops for save_pretrained (#44983)
fix: add identity reverse_op to dequantize operations for save_pretrained Dequantize operations (Mxfp4Dequantize, Fp8Dequantize, MetalDequantize) raise NotImplementedError on reverse_op, causing save_pretrained to fail for models loaded with dequantize=True. Add _IdentityOp as the reverse_op so dequantized weights are saved as-is.
H
Hyungkeun Park committed
ecdf95c66c88e08f5e2aaadeb7a7c03739565aa8
Parent: 12b6b57
Committed by GitHub <[email protected]>
on 3/27/2026, 5:09:03 PM