* Removed the redundant SiLUActivation class and now use nn.functional.silu directly.

* I apologize for adding torch.functional.silu. I have replaced it with nn.SiLU.

* Remove redundant variable in feature_extraction file

* draft

* updates

* full conversion taken from `https://gist.github.com/xenova/a452a6474428de0182b17605a98631ee`



* psuh

* nits

* updates

* more nits

* Add co author

Co-authored-by: Joshua Lochner <admin@xenova.com>

* fixup

* cleanup

* styling

* add proper path

* update

* nits

* don't  push the exit

* clean

* update whisper doc

* don't error out if tiktoken is not here

* make sure we are BC with conversion

* nit

* Update docs/source/en/model_doc/whisper.md

Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>

* merge and update

* update markdwon

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

---------

Co-authored-by: Joshua Lochner <admin@xenova.com>
Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>

* added flash attention for gpt-neo

* small change

Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>

* readme updated

* .

* changes

* removed padding_mask

* Update src/transformers/models/gpt_neo/modeling_gpt_neo.py

Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>

---------

Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>
Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>

* Fix error in convert_openai_to_hf.py: "_download() missing 1 required positional argument: root"

* Fix error in convert_openai_to_hf.py: "TypeError: byte indices must be integers or slices, not str"

* Fix decoder_attention_heads value in convert_openai_to_hf.py.

Correct the assignment for `decoder_attention_heads` in the conversion script for the Whisper model.

* Black reformat convert_openai_to_hf.py file.

* Fix Whisper model configuration defaults (for Tiny).

- Correct encoder/decoder layers and attention heads count.
- Update model width (`d_model`) to 384.

* Add docstring to the convert_openai_to_hf.py script with a doctest

* Add shebang and +x permission to the convert_openai_to_hf.py

* convert_openai_to_hf.py: reuse the read model_bytes in the _download() function

* Move convert_openai_to_hf.py doctest example to whisper.md

* whisper.md: Add an inference example to the Conversion section.

* whisper.md: remove `model.config.forced_decoder_ids` from examples (deprecated)

* whisper.md: Remove "## Format Conversion" section; not used by users

* whisper.md: Use librispeech_asr_dummy dataset and load_dataset()

* Update Dockerfile

* Update docker/transformers-all-latest-gpu/Dockerfile

* [Whisper] Block language/task args for English-only

* Update src/transformers/models/whisper/modeling_whisper.py

Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>

---------

Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>

* fixed links with 404

* make style

* fix

* fix

* fix

---------

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

* Fix dtype error

* Fix mean and std dtype

* make style

I'm adding accelerate as one of the libraries to install because otherwise when running the Trainer, the model errorr out with the error. 

ImportError: Using the `Trainer` with `PyTorch` requires `accelerate>=0.20.1`: Please run `pip install transformers[torch]` or `pip install accelerate -U`

Further context: 
1. I've tried this across different environments so I believe that the environment is not the issue. 
2. I had the latest transformers library version running. 
3. Typically even after install accelerate and import it, it wouldn't resolve the issue until I restart the notebook and try again.

Remove unexpected argument for FlaxResNetBasicLayerCollection

fix

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

fix

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

* fix tokenizer

* fix tokenizer

* translate run_scripts.md to chinese

* translate run_scripts.md to chinese

* translate run_scripts.md to chinese

* translate autoclass_tutorial.md  to chinese

* translate update

* flash attention added for DistilBert

* fixes

* removed padding_masks

* Update modeling_distilbert.py

* Update test_modeling_distilbert.py

* style fix

* first batch of structure improvements for model_docs

* second batch of structure improvements for model_docs

* more structure improvements for model_docs

* more structure improvements for model_docs

* structure improvements for cv model_docs

* more structural refactoring

* addressed feedback about image processors

Update sam.md

* Fix mixed precision error for switch transformer

* Fixup

* Update the ConversationalPipeline docstring now that we're using chat templates

* Direct access to conversation.messages

* Explain the string init

doc update

* fix

* update

* update

* fix

---------

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

fix peft integration issues

* Use Llama RoPE implementation for Falcon

+ Add copy functionalities

* Use standard cache format for Falcon

* Simplify apply_rotary_pos_emb, copy from Llama

* Remove unnecessary cache conversion test

We don't need to convert any caches anymore!

* Resolve copy complaint

* Fixed base model class name extraction from PeftModels

* Changes to first unwrap the model then extract the base model name

* Changed base_model to base_model.model to stay consistent with peft model abstractions

* Removed the redundant SiLUActivation class and now use nn.functional.silu directly.

* I apologize for adding torch.functional.silu. I have replaced it with nn.SiLU.

* tranlsate peft.md to chinese

* translate peft.md to chinese

* fix missing link

* enrich TTS pipeline docstring for clearer forward_params use

* change token leghts

* update Pipeline parameters

* correct docstring and make style

* fix tests

* make style

* change music prompt

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

* Apply suggestions from code review

Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>
Co-authored-by: Sanchit Gandhi <93869735+sanchit-gandhi@users.noreply.github.com>

* raise errors if generate_kwargs with forward-only models

* make style

---------

Co-authored-by: Sanchit Gandhi <93869735+sanchit-gandhi@users.noreply.github.com>
Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>

* remove redundant code

* update

* add typecasting

* make `attention_mask` float again

fix-exllama

* Fixing m4t.

* Trying to remove comparison ? Odd test failure.

* Adding shared. But why on earth does it hang ????

* Putting back the model weights checks the test is silently failing on
cuda.

* Fix style + unremoved comment.

* Fix Kosmos2

* Fix ProphetNet

* Fix MarianMT

* Fix M4T

* XLM ProphetNet

* ProphetNet fix

* XLM ProphetNet

* Final M4T fixes

* Tied weights keys

* Revert M4T changes

* Apply suggestions from code review

Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>

---------

Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>

Wrap _prepare_4d_causal_attention_mask as a leaf function