GitLab

fix: use bool instead of uint8/byte in Deberta/DebertaV2/SEW-D to make it compatible with TensorRT (#23683)

* Use bool instead of uint8/byte in DebertaV2 to make it compatible with TensorRT

TensorRT cannot accept onnx graph with uint8/byte intermediate tensors. This PR uses bool tensors instead of unit8/byte tensors to make the exported onnx file can work with TensorRT.

* fix: use bool instead of uint8/byte in Deberta and SEW-D

---------
Co-authored-by: Yuxian Qiu <yuxianq@nvidia.com>

* doc refocused on using optimum, tflite

* minor updates to fix checks

* Apply suggestions from code review
Co-authored-by: regisss <15324346+regisss@users.noreply.github.com>

* TFLite to separate page, added links

* Removed the onnx list builder

* make style

* Update docs/source/en/serialization.mdx
Co-authored-by: regisss <15324346+regisss@users.noreply.github.com>

---------
Co-authored-by: regisss <15324346+regisss@users.noreply.github.com>

* Added lion and paged optimizers and made original tests pass.

* Added tests for paged and lion optimizers.

* Added and fixed optimizer tests.

* Style and quality checks.

---------
Co-authored-by: younesbelkada <younesbelkada@gmail.com>

* Added lion and paged optimizers and made original tests pass.

* Added tests for paged and lion optimizers.

* Added and fixed optimizer tests.

* Style and quality checks.

* Initial draft. Some tests fail.

* Fixed dtype bug.

* Fixed bug caused by torch_dtype='auto'.

* All test green for 8-bit and 4-bit layers.

* Added fix for fp32 layer norms and bf16 compute in LLaMA.

* Initial draft. Some tests fail.

* Fixed dtype bug.

* Fixed bug caused by torch_dtype='auto'.

* All test green for 8-bit and 4-bit layers.

* Added lion and paged optimizers and made original tests pass.

* Added tests for paged and lion optimizers.

* Added and fixed optimizer tests.

* Style and quality checks.

* Fixing issues for PR #23479.

* Added fix for fp32 layer norms and bf16 compute in LLaMA.

* Reverted variable name change.

* Initial draft. Some tests fail.

* Fixed dtype bug.

* Fixed bug caused by torch_dtype='auto'.

* All test green for 8-bit and 4-bit layers.

* Added lion and paged optimizers and made original tests pass.

* Added tests for paged and lion optimizers.

* Added and fixed optimizer tests.

* Style and quality checks.

* Added missing tests.

* Fixup changes.

* Added fixup changes.

* Missed some variables to rename.

* revert trainer tests

* revert test trainer

* another revert

* fix tests and safety checkers

* protect import

* simplify a bit

* Update src/transformers/trainer.py

* few fixes

* add warning

* replace with `load_in_kbit = load_in_4bit or load_in_8bit`

* fix test

* fix tests

* this time fix tests

* safety checker

* add docs

* revert torch_dtype

* Apply suggestions from code review
Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>

* multiple fixes

* update docs

* version checks and multiple fixes

* replace `is_loaded_in_kbit`

* replace `load_in_kbit`

* change methods names

* better checks

* oops

* oops

* address final comments

---------
Co-authored-by: younesbelkada <younesbelkada@gmail.com>
Co-authored-by: Younes Belkada <49240599+younesbelkada@users.noreply.github.com>
Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>

Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

* Fix some docs what layerdrop does

* Update src/transformers/models/data2vec/configuration_data2vec_audio.py
Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>

* Fix more docs

---------
Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>

Ref: https://github.com/huggingface/peft/issues/394
    Loading a quantized checkpoint into non-quantized Linear8bitLt is not supported.
    call module.cuda() before module.load_state_dict()

fix
Co-authored-by: ydshieh <ydshieh@users.noreply.github.com>

* Fix is_batched code to allow 2-D numpy arrays for audio

* Tests

* Fix typo

* Incorporate comments from PR #23223

fix blip doctest

* New TF version compatibility fixes

* Remove dummy print statement, move expand_1d

* Make a proper framework inference function

* Make a proper framework inference function

* ValueError -> TypeError

* add a dummy pipeline test

* change test name

fix
Co-authored-by: ydshieh <ydshieh@users.noreply.github.com>

docs: ko: `tasks/monocular_depth_estimation`
Co-authored-by: Hyeonseo Yun <0525yhs@gmail.com>
Co-authored-by: Sohyun Sim <96299403+sim-so@users.noreply.github.com>
Co-authored-by: Gabriel Yang <gabrielwithhappy@gmail.com>
Co-authored-by: Wonhyeong Seo <wonhseo@kakao.com>
Co-authored-by: Jungnerd <46880056+jungnerd@users.noreply.github.com>

* Making `safetensors` a core dependency.

To be merged later, I'm creating the PR so we can try it out.

* Update setup.py

* Remove duplicates.

* Even more redundant.

fix
Co-authored-by: ydshieh <ydshieh@users.noreply.github.com>

* Update modeling_open_llama.py

Fix typo in `use_memorry_efficient_attention` parameter name

* Update configuration_open_llama.py

Fix typo in `use_memorry_efficient_attention` parameter name

* Update configuration_open_llama.py

Take care of backwards compatibility ensuring that the previous parameter name is taken into account if used

* Update configuration_open_llama.py

format to adjust the line length

* Update configuration_open_llama.py

proper code formatting using `make fixup`

* Update configuration_open_llama.py

pop the argument not to let it be set later down the line

* Add PerSAM args

* Make attn_sim optional

* Rename to attention_similarity

* Add docstrigns

* Improve docstrings

Bump requests in /examples/research_projects/lxmert

Bumps [requests](https://github.com/psf/requests) from 2.22.0 to 2.31.0.
- [Release notes](https://github.com/psf/requests/releases)
- [Changelog](https://github.com/psf/requests/blob/main/HISTORY.md)
- [Commits](https://github.com/psf/requests/compare/v2.22.0...v2.31.0

)

---
updated-dependencies:
- dependency-name: requests
  dependency-type: direct:production
...
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

Bump requests in /examples/research_projects/visual_bert

Bumps [requests](https://github.com/psf/requests) from 2.22.0 to 2.31.0.
- [Release notes](https://github.com/psf/requests/releases)
- [Changelog](https://github.com/psf/requests/blob/main/HISTORY.md)
- [Commits](https://github.com/psf/requests/compare/v2.22.0...v2.31.0

)

---
updated-dependencies:
- dependency-name: requests
  dependency-type: direct:production
...
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

Bump requests in /examples/research_projects/decision_transformer

Bumps [requests](https://github.com/psf/requests) from 2.27.1 to 2.31.0.
- [Release notes](https://github.com/psf/requests/releases)
- [Changelog](https://github.com/psf/requests/blob/main/HISTORY.md)
- [Commits](https://github.com/psf/requests/compare/v2.27.1...v2.31.0

)

---
updated-dependencies:
- dependency-name: requests
  dependency-type: direct:production
...
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

* First draft

* Remove print statements

* Add conditional generation

* Add more tests

* Remove scripts

* Remove BLIP specific linkes

* Add support for pix2struct

* Add fast test

* Address comment

* Fix style

* fix

* fix

---------
Co-authored-by: ydshieh <ydshieh@users.noreply.github.com>

* Fix SAM tests and use smaller checkpoints

* Override test_model_from_pretrained to use sam-vit-base as well

* make fixup

* Fix wav2vec2 is_batched check to include 2-D numpy arrays

* address comment

* Add tests

* oops

* oops

* Switch to np array
Co-authored-by: Sanchit Gandhi <93869735+sanchit-gandhi@users.noreply.github.com>

* Switch to np array

* condition merge

* Specify mono channel only in comment

* oops, add other comment too

* make style

* Switch list check from falsiness to empty

---------
Co-authored-by: Sanchit Gandhi <93869735+sanchit-gandhi@users.noreply.github.com>

* Fixed bug where LLaMA layer norm would change input type.

* make fix-copies

---------
Co-authored-by: younesbelkada <younesbelkada@gmail.com>

* Fix deepspeed recursion

* Better fix

* fix logger bug

* Update tests/mixed_int8/test_mixed_int8.py
Co-authored-by: Zachary Mueller <muellerzr@gmail.com>

* import `PartialState`

---------
Co-authored-by: Zachary Mueller <muellerzr@gmail.com>

* Fix tensor device while attention_mask is not None

* Fix tensor device while attention_mask is not None

See https://github.com/huggingface/transformers/pull/23625

* Debug example code for MegaForCausalLM

set ignore_mismatched_sizes=True in model loading code

* Fix up

fix
Co-authored-by: ydshieh <ydshieh@users.noreply.github.com>

* fix

* fix

* fix

---------
Co-authored-by: ydshieh <ydshieh@users.noreply.github.com>

fix
Co-authored-by: ydshieh <ydshieh@users.noreply.github.com>

* remove redundant shit right

* fix failing tests

* this time fix tests

* Fix: Change tensors to integers in torch.split() for torch.dynamo and torch.compile compatibility

* Applied the suggested fix to the utils/check_copies.py test

* Applied the suggested fix by changing the original function that gets copied