…e#34395)

* Skip DeepSpeed ZeRO Stage 3 model initialization when it is intended to be quantized.

* Propagate the quantization state using a context manager

* make fixup

FIX Broken repr of TorchAoConfig

The __repr__ method references a non-existent self.kwargs. This is now
fixed.

There does not appear to be a uniform way of defining __repr__ for
quantization configs. I copied the method as implemented for HQQ:

https://github.com/huggingface/transformers/blob/e2ac16b28a0b8b900e136750309ca40c49d975c5/src/transformers/utils/quantization_config.py#L285-L287

* save/load sub-configs

* nit forgot these

* fix copies

* move test to common

* use dict for sub-configs

* add load-save-laod test

* clean up modeling check

* oops this are correct keys

* fix some tests, missed some composite configs

* this model was missed

* DistillBERT is ExecuTorch compatible

* [run_slow] distilbert

* [run_slow] distilbert

---------

Co-authored-by: Guang Yang <[email protected]>

Revert "Fix Whisper CI (huggingface#34541)"

This reverts commit eb81144.

)

* Fix assistant tokens when truncated

* fix test

* fix test

* step

…4558)

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

---------

Co-authored-by: ydshieh <[email protected]>

)

* Changing __repr__ in torchao

* small update

* make style

* small update

* add LinearActivationQuantizedTensor

* remove some cases

* update imports & handle return None

* update

fix-torch-interpolation-ci

…xtraction (huggingface#34450)

* fix stablelm qkv_bias

* fix stablelm qkv_bias and use_parallel_residual

* remove original_model.config for stablelm gguf test

* docs: ko: convbert.md

* Update _toctree.yml

* feat: nmt draft