diff --git a/hf-dev-train/transformers-main/src/transformers.egg-info/PKG-INFO b/hf-dev-train/transformers-main/src/transformers.egg-info/PKG-INFO new file mode 100644 index 0000000000000000000000000000000000000000..7a1fdce9527b183506a258ad818b7dcca997679b --- /dev/null +++ b/hf-dev-train/transformers-main/src/transformers.egg-info/PKG-INFO @@ -0,0 +1,970 @@ +Metadata-Version: 2.1 +Name: transformers +Version: 4.28.0.dev0 +Summary: State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow +Home-page: https://github.com/huggingface/transformers +Author: The Hugging Face team (past and future) with the help of all our contributors (https://github.com/huggingface/transformers/graphs/contributors) +Author-email: transformers@huggingface.co +License: Apache 2.0 License +Keywords: NLP vision speech deep learning transformer pytorch tensorflow jax BERT GPT-2 Wav2Vec2 ViT +Classifier: Development Status :: 5 - Production/Stable +Classifier: Intended Audience :: Developers +Classifier: Intended Audience :: Education +Classifier: Intended Audience :: Science/Research +Classifier: License :: OSI Approved :: Apache Software License +Classifier: Operating System :: OS Independent +Classifier: Programming Language :: Python :: 3 +Classifier: Programming Language :: Python :: 3.7 +Classifier: Programming Language :: Python :: 3.8 +Classifier: Programming Language :: Python :: 3.9 +Classifier: Programming Language :: Python :: 3.10 +Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence +Requires-Python: >=3.7.0 +Description-Content-Type: text/markdown +License-File: LICENSE +Requires-Dist: importlib_metadata; python_version < "3.8" +Requires-Dist: filelock +Requires-Dist: huggingface-hub<1.0,>=0.11.0 +Requires-Dist: numpy>=1.17 +Requires-Dist: packaging>=20.0 +Requires-Dist: pyyaml>=5.1 +Requires-Dist: regex!=2019.12.17 +Requires-Dist: requests +Requires-Dist: tokenizers!=0.11.3,<0.14,>=0.11.1 +Requires-Dist: tqdm>=4.27 +Provides-Extra: ja +Requires-Dist: fugashi>=1.0; extra == "ja" +Requires-Dist: ipadic<2.0,>=1.0.0; extra == "ja" +Requires-Dist: unidic_lite>=1.0.7; extra == "ja" +Requires-Dist: unidic>=1.0.2; extra == "ja" +Requires-Dist: sudachipy>=0.6.6; extra == "ja" +Requires-Dist: sudachidict_core>=20220729; extra == "ja" +Requires-Dist: rhoknp>=1.1.0; extra == "ja" +Provides-Extra: sklearn +Requires-Dist: scikit-learn; extra == "sklearn" +Provides-Extra: tf +Requires-Dist: tensorflow<2.13,>=2.4; extra == "tf" +Requires-Dist: onnxconverter-common; extra == "tf" +Requires-Dist: tf2onnx; extra == "tf" +Requires-Dist: tensorflow-text<2.13; extra == "tf" +Requires-Dist: keras-nlp>=0.3.1; extra == "tf" +Provides-Extra: tf-cpu +Requires-Dist: tensorflow-cpu<2.13,>=2.4; extra == "tf-cpu" +Requires-Dist: onnxconverter-common; extra == "tf-cpu" +Requires-Dist: tf2onnx; extra == "tf-cpu" +Requires-Dist: tensorflow-text<2.13; extra == "tf-cpu" +Requires-Dist: keras-nlp>=0.3.1; extra == "tf-cpu" +Provides-Extra: torch +Requires-Dist: torch!=1.12.0,>=1.9; extra == "torch" +Provides-Extra: accelerate +Requires-Dist: accelerate>=0.10.0; extra == "accelerate" +Provides-Extra: retrieval +Requires-Dist: faiss-cpu; extra == "retrieval" +Requires-Dist: datasets!=2.5.0; extra == "retrieval" +Provides-Extra: flax +Requires-Dist: jax!=0.3.2,<=0.3.6,>=0.2.8; extra == "flax" +Requires-Dist: jaxlib<=0.3.6,>=0.1.65; extra == "flax" +Requires-Dist: flax>=0.4.1; extra == "flax" +Requires-Dist: optax>=0.0.8; extra == "flax" +Provides-Extra: tokenizers +Requires-Dist: tokenizers!=0.11.3,<0.14,>=0.11.1; extra == "tokenizers" +Provides-Extra: ftfy +Requires-Dist: ftfy; extra == "ftfy" +Provides-Extra: onnxruntime +Requires-Dist: onnxruntime>=1.4.0; extra == "onnxruntime" +Requires-Dist: onnxruntime-tools>=1.4.2; extra == "onnxruntime" +Provides-Extra: onnx +Requires-Dist: onnxconverter-common; extra == "onnx" +Requires-Dist: tf2onnx; extra == "onnx" +Requires-Dist: onnxruntime>=1.4.0; extra == "onnx" +Requires-Dist: onnxruntime-tools>=1.4.2; extra == "onnx" +Provides-Extra: modelcreation +Requires-Dist: cookiecutter==1.7.3; extra == "modelcreation" +Provides-Extra: sagemaker +Requires-Dist: sagemaker>=2.31.0; extra == "sagemaker" +Provides-Extra: deepspeed +Requires-Dist: deepspeed>=0.8.3; extra == "deepspeed" +Requires-Dist: accelerate>=0.10.0; extra == "deepspeed" +Provides-Extra: fairscale +Requires-Dist: fairscale>0.3; extra == "fairscale" +Provides-Extra: optuna +Requires-Dist: optuna; extra == "optuna" +Provides-Extra: ray +Requires-Dist: ray[tune]; extra == "ray" +Provides-Extra: sigopt +Requires-Dist: sigopt; extra == "sigopt" +Provides-Extra: integrations +Requires-Dist: optuna; extra == "integrations" +Requires-Dist: ray[tune]; extra == "integrations" +Requires-Dist: sigopt; extra == "integrations" +Provides-Extra: serving +Requires-Dist: pydantic; extra == "serving" +Requires-Dist: uvicorn; extra == "serving" +Requires-Dist: fastapi; extra == "serving" +Requires-Dist: starlette; extra == "serving" +Provides-Extra: audio +Requires-Dist: librosa; extra == "audio" +Requires-Dist: pyctcdecode>=0.4.0; extra == "audio" +Requires-Dist: phonemizer; extra == "audio" +Requires-Dist: kenlm; extra == "audio" +Provides-Extra: speech +Requires-Dist: torchaudio; extra == "speech" +Requires-Dist: librosa; extra == "speech" +Requires-Dist: pyctcdecode>=0.4.0; extra == "speech" +Requires-Dist: phonemizer; extra == "speech" +Requires-Dist: kenlm; extra == "speech" +Provides-Extra: torch-speech +Requires-Dist: torchaudio; extra == "torch-speech" +Requires-Dist: librosa; extra == "torch-speech" +Requires-Dist: pyctcdecode>=0.4.0; extra == "torch-speech" +Requires-Dist: phonemizer; extra == "torch-speech" +Requires-Dist: kenlm; extra == "torch-speech" +Provides-Extra: tf-speech +Requires-Dist: librosa; extra == "tf-speech" +Requires-Dist: pyctcdecode>=0.4.0; extra == "tf-speech" +Requires-Dist: phonemizer; extra == "tf-speech" +Requires-Dist: kenlm; extra == "tf-speech" +Provides-Extra: flax-speech +Requires-Dist: librosa; extra == "flax-speech" +Requires-Dist: pyctcdecode>=0.4.0; extra == "flax-speech" +Requires-Dist: phonemizer; extra == "flax-speech" +Requires-Dist: kenlm; extra == "flax-speech" +Provides-Extra: vision +Requires-Dist: Pillow; extra == "vision" +Provides-Extra: timm +Requires-Dist: timm; extra == "timm" +Provides-Extra: torch-vision +Requires-Dist: torchvision; extra == "torch-vision" +Requires-Dist: Pillow; extra == "torch-vision" +Provides-Extra: natten +Requires-Dist: natten>=0.14.6; extra == "natten" +Provides-Extra: codecarbon +Requires-Dist: codecarbon==1.2.0; extra == "codecarbon" +Provides-Extra: video +Requires-Dist: decord==0.6.0; extra == "video" +Requires-Dist: av==9.2.0; extra == "video" +Provides-Extra: sentencepiece +Requires-Dist: sentencepiece!=0.1.92,>=0.1.91; extra == "sentencepiece" +Requires-Dist: protobuf<=3.20.2; extra == "sentencepiece" +Provides-Extra: testing +Requires-Dist: pytest; extra == "testing" +Requires-Dist: pytest-xdist; extra == "testing" +Requires-Dist: timeout-decorator; extra == "testing" +Requires-Dist: parameterized; extra == "testing" +Requires-Dist: psutil; extra == "testing" +Requires-Dist: datasets!=2.5.0; extra == "testing" +Requires-Dist: dill<0.3.5; extra == "testing" +Requires-Dist: evaluate>=0.2.0; extra == "testing" +Requires-Dist: pytest-timeout; extra == "testing" +Requires-Dist: black~=23.1; extra == "testing" +Requires-Dist: sacrebleu<2.0.0,>=1.4.12; extra == "testing" +Requires-Dist: rouge-score!=0.0.7,!=0.0.8,!=0.1,!=0.1.1; extra == "testing" +Requires-Dist: nltk; extra == "testing" +Requires-Dist: GitPython<3.1.19; extra == "testing" +Requires-Dist: hf-doc-builder>=0.3.0; extra == "testing" +Requires-Dist: protobuf<=3.20.2; extra == "testing" +Requires-Dist: sacremoses; extra == "testing" +Requires-Dist: rjieba; extra == "testing" +Requires-Dist: safetensors>=0.2.1; extra == "testing" +Requires-Dist: beautifulsoup4; extra == "testing" +Requires-Dist: faiss-cpu; extra == "testing" +Requires-Dist: datasets!=2.5.0; extra == "testing" +Requires-Dist: cookiecutter==1.7.3; extra == "testing" +Provides-Extra: deepspeed-testing +Requires-Dist: deepspeed>=0.8.3; extra == "deepspeed-testing" +Requires-Dist: accelerate>=0.10.0; extra == "deepspeed-testing" +Requires-Dist: pytest; extra == "deepspeed-testing" +Requires-Dist: pytest-xdist; extra == "deepspeed-testing" +Requires-Dist: timeout-decorator; extra == "deepspeed-testing" +Requires-Dist: parameterized; extra == "deepspeed-testing" +Requires-Dist: psutil; extra == "deepspeed-testing" +Requires-Dist: datasets!=2.5.0; extra == "deepspeed-testing" +Requires-Dist: dill<0.3.5; extra == "deepspeed-testing" +Requires-Dist: evaluate>=0.2.0; extra == "deepspeed-testing" +Requires-Dist: pytest-timeout; extra == "deepspeed-testing" +Requires-Dist: black~=23.1; extra == "deepspeed-testing" +Requires-Dist: sacrebleu<2.0.0,>=1.4.12; extra == "deepspeed-testing" +Requires-Dist: rouge-score!=0.0.7,!=0.0.8,!=0.1,!=0.1.1; extra == "deepspeed-testing" +Requires-Dist: nltk; extra == "deepspeed-testing" +Requires-Dist: GitPython<3.1.19; extra == "deepspeed-testing" +Requires-Dist: hf-doc-builder>=0.3.0; extra == "deepspeed-testing" +Requires-Dist: protobuf<=3.20.2; extra == "deepspeed-testing" +Requires-Dist: sacremoses; extra == "deepspeed-testing" +Requires-Dist: rjieba; extra == "deepspeed-testing" +Requires-Dist: safetensors>=0.2.1; extra == "deepspeed-testing" +Requires-Dist: beautifulsoup4; extra == "deepspeed-testing" +Requires-Dist: faiss-cpu; extra == "deepspeed-testing" +Requires-Dist: datasets!=2.5.0; extra == "deepspeed-testing" +Requires-Dist: cookiecutter==1.7.3; extra == "deepspeed-testing" +Requires-Dist: optuna; extra == "deepspeed-testing" +Requires-Dist: sentencepiece!=0.1.92,>=0.1.91; extra == "deepspeed-testing" +Requires-Dist: protobuf<=3.20.2; extra == "deepspeed-testing" +Provides-Extra: quality +Requires-Dist: black~=23.1; extra == "quality" +Requires-Dist: datasets!=2.5.0; extra == "quality" +Requires-Dist: isort>=5.5.4; extra == "quality" +Requires-Dist: ruff<=0.0.259,>=0.0.241; extra == "quality" +Requires-Dist: GitPython<3.1.19; extra == "quality" +Requires-Dist: hf-doc-builder>=0.3.0; extra == "quality" +Provides-Extra: all +Requires-Dist: tensorflow<2.13,>=2.4; extra == "all" +Requires-Dist: onnxconverter-common; extra == "all" +Requires-Dist: tf2onnx; extra == "all" +Requires-Dist: tensorflow-text<2.13; extra == "all" +Requires-Dist: keras-nlp>=0.3.1; extra == "all" +Requires-Dist: torch!=1.12.0,>=1.9; extra == "all" +Requires-Dist: jax!=0.3.2,<=0.3.6,>=0.2.8; extra == "all" +Requires-Dist: jaxlib<=0.3.6,>=0.1.65; extra == "all" +Requires-Dist: flax>=0.4.1; extra == "all" +Requires-Dist: optax>=0.0.8; extra == "all" +Requires-Dist: sentencepiece!=0.1.92,>=0.1.91; extra == "all" +Requires-Dist: protobuf<=3.20.2; extra == "all" +Requires-Dist: tokenizers!=0.11.3,<0.14,>=0.11.1; extra == "all" +Requires-Dist: torchaudio; extra == "all" +Requires-Dist: librosa; extra == "all" +Requires-Dist: pyctcdecode>=0.4.0; extra == "all" +Requires-Dist: phonemizer; extra == "all" +Requires-Dist: kenlm; extra == "all" +Requires-Dist: Pillow; extra == "all" +Requires-Dist: optuna; extra == "all" +Requires-Dist: ray[tune]; extra == "all" +Requires-Dist: sigopt; extra == "all" +Requires-Dist: timm; extra == "all" +Requires-Dist: torchvision; extra == "all" +Requires-Dist: Pillow; extra == "all" +Requires-Dist: codecarbon==1.2.0; extra == "all" +Requires-Dist: accelerate>=0.10.0; extra == "all" +Requires-Dist: decord==0.6.0; extra == "all" +Requires-Dist: av==9.2.0; extra == "all" +Provides-Extra: docs-specific +Requires-Dist: hf-doc-builder; extra == "docs-specific" +Provides-Extra: docs +Requires-Dist: tensorflow<2.13,>=2.4; extra == "docs" +Requires-Dist: onnxconverter-common; extra == "docs" +Requires-Dist: tf2onnx; extra == "docs" +Requires-Dist: tensorflow-text<2.13; extra == "docs" +Requires-Dist: keras-nlp>=0.3.1; extra == "docs" +Requires-Dist: torch!=1.12.0,>=1.9; extra == "docs" +Requires-Dist: jax!=0.3.2,<=0.3.6,>=0.2.8; extra == "docs" +Requires-Dist: jaxlib<=0.3.6,>=0.1.65; extra == "docs" +Requires-Dist: flax>=0.4.1; extra == "docs" +Requires-Dist: optax>=0.0.8; extra == "docs" +Requires-Dist: sentencepiece!=0.1.92,>=0.1.91; extra == "docs" +Requires-Dist: protobuf<=3.20.2; extra == "docs" +Requires-Dist: tokenizers!=0.11.3,<0.14,>=0.11.1; extra == "docs" +Requires-Dist: torchaudio; extra == "docs" +Requires-Dist: librosa; extra == "docs" +Requires-Dist: pyctcdecode>=0.4.0; extra == "docs" +Requires-Dist: phonemizer; extra == "docs" +Requires-Dist: kenlm; extra == "docs" +Requires-Dist: Pillow; extra == "docs" +Requires-Dist: optuna; extra == "docs" +Requires-Dist: ray[tune]; extra == "docs" +Requires-Dist: sigopt; extra == "docs" +Requires-Dist: timm; extra == "docs" +Requires-Dist: torchvision; extra == "docs" +Requires-Dist: Pillow; extra == "docs" +Requires-Dist: codecarbon==1.2.0; extra == "docs" +Requires-Dist: accelerate>=0.10.0; extra == "docs" +Requires-Dist: decord==0.6.0; extra == "docs" +Requires-Dist: av==9.2.0; extra == "docs" +Requires-Dist: hf-doc-builder; extra == "docs" +Provides-Extra: dev-torch +Requires-Dist: pytest; extra == "dev-torch" +Requires-Dist: pytest-xdist; extra == "dev-torch" +Requires-Dist: timeout-decorator; extra == "dev-torch" +Requires-Dist: parameterized; extra == "dev-torch" +Requires-Dist: psutil; extra == "dev-torch" +Requires-Dist: datasets!=2.5.0; extra == "dev-torch" +Requires-Dist: dill<0.3.5; extra == "dev-torch" +Requires-Dist: evaluate>=0.2.0; extra == "dev-torch" +Requires-Dist: pytest-timeout; extra == "dev-torch" +Requires-Dist: black~=23.1; extra == "dev-torch" +Requires-Dist: sacrebleu<2.0.0,>=1.4.12; extra == "dev-torch" +Requires-Dist: rouge-score!=0.0.7,!=0.0.8,!=0.1,!=0.1.1; extra == "dev-torch" +Requires-Dist: nltk; extra == "dev-torch" +Requires-Dist: GitPython<3.1.19; extra == "dev-torch" +Requires-Dist: hf-doc-builder>=0.3.0; extra == "dev-torch" +Requires-Dist: protobuf<=3.20.2; extra == "dev-torch" +Requires-Dist: sacremoses; extra == "dev-torch" +Requires-Dist: rjieba; extra == "dev-torch" +Requires-Dist: safetensors>=0.2.1; extra == "dev-torch" +Requires-Dist: beautifulsoup4; extra == "dev-torch" +Requires-Dist: faiss-cpu; extra == "dev-torch" +Requires-Dist: datasets!=2.5.0; extra == "dev-torch" +Requires-Dist: cookiecutter==1.7.3; extra == "dev-torch" +Requires-Dist: torch!=1.12.0,>=1.9; extra == "dev-torch" +Requires-Dist: sentencepiece!=0.1.92,>=0.1.91; extra == "dev-torch" +Requires-Dist: protobuf<=3.20.2; extra == "dev-torch" +Requires-Dist: tokenizers!=0.11.3,<0.14,>=0.11.1; extra == "dev-torch" +Requires-Dist: torchaudio; extra == "dev-torch" +Requires-Dist: librosa; extra == "dev-torch" +Requires-Dist: pyctcdecode>=0.4.0; extra == "dev-torch" +Requires-Dist: phonemizer; extra == "dev-torch" +Requires-Dist: kenlm; extra == "dev-torch" +Requires-Dist: Pillow; extra == "dev-torch" +Requires-Dist: optuna; extra == "dev-torch" +Requires-Dist: ray[tune]; extra == "dev-torch" +Requires-Dist: sigopt; extra == "dev-torch" +Requires-Dist: timm; extra == "dev-torch" +Requires-Dist: torchvision; extra == "dev-torch" +Requires-Dist: Pillow; extra == "dev-torch" +Requires-Dist: codecarbon==1.2.0; extra == "dev-torch" +Requires-Dist: black~=23.1; extra == "dev-torch" +Requires-Dist: datasets!=2.5.0; extra == "dev-torch" +Requires-Dist: isort>=5.5.4; extra == "dev-torch" +Requires-Dist: ruff<=0.0.259,>=0.0.241; extra == "dev-torch" +Requires-Dist: GitPython<3.1.19; extra == "dev-torch" +Requires-Dist: hf-doc-builder>=0.3.0; extra == "dev-torch" +Requires-Dist: fugashi>=1.0; extra == "dev-torch" +Requires-Dist: ipadic<2.0,>=1.0.0; extra == "dev-torch" +Requires-Dist: unidic_lite>=1.0.7; extra == "dev-torch" +Requires-Dist: unidic>=1.0.2; extra == "dev-torch" +Requires-Dist: sudachipy>=0.6.6; extra == "dev-torch" +Requires-Dist: sudachidict_core>=20220729; extra == "dev-torch" +Requires-Dist: rhoknp>=1.1.0; extra == "dev-torch" +Requires-Dist: hf-doc-builder; extra == "dev-torch" +Requires-Dist: scikit-learn; extra == "dev-torch" +Requires-Dist: cookiecutter==1.7.3; extra == "dev-torch" +Requires-Dist: onnxruntime>=1.4.0; extra == "dev-torch" +Requires-Dist: onnxruntime-tools>=1.4.2; extra == "dev-torch" +Provides-Extra: dev-tensorflow +Requires-Dist: pytest; extra == "dev-tensorflow" +Requires-Dist: pytest-xdist; extra == "dev-tensorflow" +Requires-Dist: timeout-decorator; extra == "dev-tensorflow" +Requires-Dist: parameterized; extra == "dev-tensorflow" +Requires-Dist: psutil; extra == "dev-tensorflow" +Requires-Dist: datasets!=2.5.0; extra == "dev-tensorflow" +Requires-Dist: dill<0.3.5; extra == "dev-tensorflow" +Requires-Dist: evaluate>=0.2.0; extra == "dev-tensorflow" +Requires-Dist: pytest-timeout; extra == "dev-tensorflow" +Requires-Dist: black~=23.1; extra == "dev-tensorflow" +Requires-Dist: sacrebleu<2.0.0,>=1.4.12; extra == "dev-tensorflow" +Requires-Dist: rouge-score!=0.0.7,!=0.0.8,!=0.1,!=0.1.1; extra == "dev-tensorflow" +Requires-Dist: nltk; extra == "dev-tensorflow" +Requires-Dist: GitPython<3.1.19; extra == "dev-tensorflow" +Requires-Dist: hf-doc-builder>=0.3.0; extra == "dev-tensorflow" +Requires-Dist: protobuf<=3.20.2; extra == "dev-tensorflow" +Requires-Dist: sacremoses; extra == "dev-tensorflow" +Requires-Dist: rjieba; extra == "dev-tensorflow" +Requires-Dist: safetensors>=0.2.1; extra == "dev-tensorflow" +Requires-Dist: beautifulsoup4; extra == "dev-tensorflow" +Requires-Dist: faiss-cpu; extra == "dev-tensorflow" +Requires-Dist: datasets!=2.5.0; extra == "dev-tensorflow" +Requires-Dist: cookiecutter==1.7.3; extra == "dev-tensorflow" +Requires-Dist: tensorflow<2.13,>=2.4; extra == "dev-tensorflow" +Requires-Dist: onnxconverter-common; extra == "dev-tensorflow" +Requires-Dist: tf2onnx; extra == "dev-tensorflow" +Requires-Dist: tensorflow-text<2.13; extra == "dev-tensorflow" +Requires-Dist: keras-nlp>=0.3.1; extra == "dev-tensorflow" +Requires-Dist: sentencepiece!=0.1.92,>=0.1.91; extra == "dev-tensorflow" +Requires-Dist: protobuf<=3.20.2; extra == "dev-tensorflow" +Requires-Dist: tokenizers!=0.11.3,<0.14,>=0.11.1; extra == "dev-tensorflow" +Requires-Dist: Pillow; extra == "dev-tensorflow" +Requires-Dist: black~=23.1; extra == "dev-tensorflow" +Requires-Dist: datasets!=2.5.0; extra == "dev-tensorflow" +Requires-Dist: isort>=5.5.4; extra == "dev-tensorflow" +Requires-Dist: ruff<=0.0.259,>=0.0.241; extra == "dev-tensorflow" +Requires-Dist: GitPython<3.1.19; extra == "dev-tensorflow" +Requires-Dist: hf-doc-builder>=0.3.0; extra == "dev-tensorflow" +Requires-Dist: hf-doc-builder; extra == "dev-tensorflow" +Requires-Dist: scikit-learn; extra == "dev-tensorflow" +Requires-Dist: cookiecutter==1.7.3; extra == "dev-tensorflow" +Requires-Dist: onnxconverter-common; extra == "dev-tensorflow" +Requires-Dist: tf2onnx; extra == "dev-tensorflow" +Requires-Dist: onnxruntime>=1.4.0; extra == "dev-tensorflow" +Requires-Dist: onnxruntime-tools>=1.4.2; extra == "dev-tensorflow" +Requires-Dist: librosa; extra == "dev-tensorflow" +Requires-Dist: pyctcdecode>=0.4.0; extra == "dev-tensorflow" +Requires-Dist: phonemizer; extra == "dev-tensorflow" +Requires-Dist: kenlm; extra == "dev-tensorflow" +Provides-Extra: dev +Requires-Dist: tensorflow<2.13,>=2.4; extra == "dev" +Requires-Dist: onnxconverter-common; extra == "dev" +Requires-Dist: tf2onnx; extra == "dev" +Requires-Dist: tensorflow-text<2.13; extra == "dev" +Requires-Dist: keras-nlp>=0.3.1; extra == "dev" +Requires-Dist: torch!=1.12.0,>=1.9; extra == "dev" +Requires-Dist: jax!=0.3.2,<=0.3.6,>=0.2.8; extra == "dev" +Requires-Dist: jaxlib<=0.3.6,>=0.1.65; extra == "dev" +Requires-Dist: flax>=0.4.1; extra == "dev" +Requires-Dist: optax>=0.0.8; extra == "dev" +Requires-Dist: sentencepiece!=0.1.92,>=0.1.91; extra == "dev" +Requires-Dist: protobuf<=3.20.2; extra == "dev" +Requires-Dist: tokenizers!=0.11.3,<0.14,>=0.11.1; extra == "dev" +Requires-Dist: torchaudio; extra == "dev" +Requires-Dist: librosa; extra == "dev" +Requires-Dist: pyctcdecode>=0.4.0; extra == "dev" +Requires-Dist: phonemizer; extra == "dev" +Requires-Dist: kenlm; extra == "dev" +Requires-Dist: Pillow; extra == "dev" +Requires-Dist: optuna; extra == "dev" +Requires-Dist: ray[tune]; extra == "dev" +Requires-Dist: sigopt; extra == "dev" +Requires-Dist: timm; extra == "dev" +Requires-Dist: torchvision; extra == "dev" +Requires-Dist: Pillow; extra == "dev" +Requires-Dist: codecarbon==1.2.0; extra == "dev" +Requires-Dist: accelerate>=0.10.0; extra == "dev" +Requires-Dist: decord==0.6.0; extra == "dev" +Requires-Dist: av==9.2.0; extra == "dev" +Requires-Dist: pytest; extra == "dev" +Requires-Dist: pytest-xdist; extra == "dev" +Requires-Dist: timeout-decorator; extra == "dev" +Requires-Dist: parameterized; extra == "dev" +Requires-Dist: psutil; extra == "dev" +Requires-Dist: datasets!=2.5.0; extra == "dev" +Requires-Dist: dill<0.3.5; extra == "dev" +Requires-Dist: evaluate>=0.2.0; extra == "dev" +Requires-Dist: pytest-timeout; extra == "dev" +Requires-Dist: black~=23.1; extra == "dev" +Requires-Dist: sacrebleu<2.0.0,>=1.4.12; extra == "dev" +Requires-Dist: rouge-score!=0.0.7,!=0.0.8,!=0.1,!=0.1.1; extra == "dev" +Requires-Dist: nltk; extra == "dev" +Requires-Dist: GitPython<3.1.19; extra == "dev" +Requires-Dist: hf-doc-builder>=0.3.0; extra == "dev" +Requires-Dist: protobuf<=3.20.2; extra == "dev" +Requires-Dist: sacremoses; extra == "dev" +Requires-Dist: rjieba; extra == "dev" +Requires-Dist: safetensors>=0.2.1; extra == "dev" +Requires-Dist: beautifulsoup4; extra == "dev" +Requires-Dist: faiss-cpu; extra == "dev" +Requires-Dist: datasets!=2.5.0; extra == "dev" +Requires-Dist: cookiecutter==1.7.3; extra == "dev" +Requires-Dist: black~=23.1; extra == "dev" +Requires-Dist: datasets!=2.5.0; extra == "dev" +Requires-Dist: isort>=5.5.4; extra == "dev" +Requires-Dist: ruff<=0.0.259,>=0.0.241; extra == "dev" +Requires-Dist: GitPython<3.1.19; extra == "dev" +Requires-Dist: hf-doc-builder>=0.3.0; extra == "dev" +Requires-Dist: fugashi>=1.0; extra == "dev" +Requires-Dist: ipadic<2.0,>=1.0.0; extra == "dev" +Requires-Dist: unidic_lite>=1.0.7; extra == "dev" +Requires-Dist: unidic>=1.0.2; extra == "dev" +Requires-Dist: sudachipy>=0.6.6; extra == "dev" +Requires-Dist: sudachidict_core>=20220729; extra == "dev" +Requires-Dist: rhoknp>=1.1.0; extra == "dev" +Requires-Dist: hf-doc-builder; extra == "dev" +Requires-Dist: scikit-learn; extra == "dev" +Requires-Dist: cookiecutter==1.7.3; extra == "dev" +Provides-Extra: torchhub +Requires-Dist: filelock; extra == "torchhub" +Requires-Dist: huggingface-hub<1.0,>=0.11.0; extra == "torchhub" +Requires-Dist: importlib_metadata; extra == "torchhub" +Requires-Dist: numpy>=1.17; extra == "torchhub" +Requires-Dist: packaging>=20.0; extra == "torchhub" +Requires-Dist: protobuf<=3.20.2; extra == "torchhub" +Requires-Dist: regex!=2019.12.17; extra == "torchhub" +Requires-Dist: requests; extra == "torchhub" +Requires-Dist: sentencepiece!=0.1.92,>=0.1.91; extra == "torchhub" +Requires-Dist: torch!=1.12.0,>=1.9; extra == "torchhub" +Requires-Dist: tokenizers!=0.11.3,<0.14,>=0.11.1; extra == "torchhub" +Requires-Dist: tqdm>=4.27; extra == "torchhub" + + + +

+ + + + Hugging Face Transformers Library + +
+
+

+ +

+ + Build + + + GitHub + + + Documentation + + + GitHub release + + + Contributor Covenant + + DOI +

+ +

+

+ English | + 简体中文 | + 繁體中文 | + 한국어 | + Español | + 日本語 | + हिन्दी +

+

+ +

+

State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow

+

+ +

+ +

+ +🤗 Transformers provides thousands of pretrained models to perform tasks on different modalities such as text, vision, and audio. + +These models can be applied on: + +* 📝 Text, for tasks like text classification, information extraction, question answering, summarization, translation, text generation, in over 100 languages. +* 🖼️ Images, for tasks like image classification, object detection, and segmentation. +* 🗣️ Audio, for tasks like speech recognition and audio classification. + +Transformer models can also perform tasks on **several modalities combined**, such as table question answering, optical character recognition, information extraction from scanned documents, video classification, and visual question answering. + +🤗 Transformers provides APIs to quickly download and use those pretrained models on a given text, fine-tune them on your own datasets and then share them with the community on our [model hub](https://huggingface.co/models). At the same time, each python module defining an architecture is fully standalone and can be modified to enable quick research experiments. + +🤗 Transformers is backed by the three most popular deep learning libraries — [Jax](https://jax.readthedocs.io/en/latest/), [PyTorch](https://pytorch.org/) and [TensorFlow](https://www.tensorflow.org/) — with a seamless integration between them. It's straightforward to train your models with one before loading them for inference with the other. + +## Online demos + +You can test most of our models directly on their pages from the [model hub](https://huggingface.co/models). We also offer [private model hosting, versioning, & an inference API](https://huggingface.co/pricing) for public and private models. + +Here are a few examples: + + In Natural Language Processing: +- [Masked word completion with BERT](https://huggingface.co/bert-base-uncased?text=Paris+is+the+%5BMASK%5D+of+France) +- [Name Entity Recognition with Electra](https://huggingface.co/dbmdz/electra-large-discriminator-finetuned-conll03-english?text=My+name+is+Sarah+and+I+live+in+London+city) +- [Text generation with GPT-2](https://huggingface.co/gpt2?text=A+long+time+ago%2C+) +- [Natural Language Inference with RoBERTa](https://huggingface.co/roberta-large-mnli?text=The+dog+was+lost.+Nobody+lost+any+animal) +- [Summarization with BART](https://huggingface.co/facebook/bart-large-cnn?text=The+tower+is+324+metres+%281%2C063+ft%29+tall%2C+about+the+same+height+as+an+81-storey+building%2C+and+the+tallest+structure+in+Paris.+Its+base+is+square%2C+measuring+125+metres+%28410+ft%29+on+each+side.+During+its+construction%2C+the+Eiffel+Tower+surpassed+the+Washington+Monument+to+become+the+tallest+man-made+structure+in+the+world%2C+a+title+it+held+for+41+years+until+the+Chrysler+Building+in+New+York+City+was+finished+in+1930.+It+was+the+first+structure+to+reach+a+height+of+300+metres.+Due+to+the+addition+of+a+broadcasting+aerial+at+the+top+of+the+tower+in+1957%2C+it+is+now+taller+than+the+Chrysler+Building+by+5.2+metres+%2817+ft%29.+Excluding+transmitters%2C+the+Eiffel+Tower+is+the+second+tallest+free-standing+structure+in+France+after+the+Millau+Viaduct) +- [Question answering with DistilBERT](https://huggingface.co/distilbert-base-uncased-distilled-squad?text=Which+name+is+also+used+to+describe+the+Amazon+rainforest+in+English%3F&context=The+Amazon+rainforest+%28Portuguese%3A+Floresta+Amaz%C3%B4nica+or+Amaz%C3%B4nia%3B+Spanish%3A+Selva+Amaz%C3%B3nica%2C+Amazon%C3%ADa+or+usually+Amazonia%3B+French%3A+For%C3%AAt+amazonienne%3B+Dutch%3A+Amazoneregenwoud%29%2C+also+known+in+English+as+Amazonia+or+the+Amazon+Jungle%2C+is+a+moist+broadleaf+forest+that+covers+most+of+the+Amazon+basin+of+South+America.+This+basin+encompasses+7%2C000%2C000+square+kilometres+%282%2C700%2C000+sq+mi%29%2C+of+which+5%2C500%2C000+square+kilometres+%282%2C100%2C000+sq+mi%29+are+covered+by+the+rainforest.+This+region+includes+territory+belonging+to+nine+nations.+The+majority+of+the+forest+is+contained+within+Brazil%2C+with+60%25+of+the+rainforest%2C+followed+by+Peru+with+13%25%2C+Colombia+with+10%25%2C+and+with+minor+amounts+in+Venezuela%2C+Ecuador%2C+Bolivia%2C+Guyana%2C+Suriname+and+French+Guiana.+States+or+departments+in+four+nations+contain+%22Amazonas%22+in+their+names.+The+Amazon+represents+over+half+of+the+planet%27s+remaining+rainforests%2C+and+comprises+the+largest+and+most+biodiverse+tract+of+tropical+rainforest+in+the+world%2C+with+an+estimated+390+billion+individual+trees+divided+into+16%2C000+species) +- [Translation with T5](https://huggingface.co/t5-base?text=My+name+is+Wolfgang+and+I+live+in+Berlin) + +In Computer Vision: +- [Image classification with ViT](https://huggingface.co/google/vit-base-patch16-224) +- [Object Detection with DETR](https://huggingface.co/facebook/detr-resnet-50) +- [Semantic Segmentation with SegFormer](https://huggingface.co/nvidia/segformer-b0-finetuned-ade-512-512) +- [Panoptic Segmentation with MaskFormer](https://huggingface.co/facebook/maskformer-swin-small-coco) +- [Depth Estimation with DPT](https://huggingface.co/docs/transformers/model_doc/dpt) +- [Video Classification with VideoMAE](https://huggingface.co/docs/transformers/model_doc/videomae) +- [Universal Segmentation with OneFormer](https://huggingface.co/shi-labs/oneformer_ade20k_dinat_large) + +In Audio: +- [Automatic Speech Recognition with Wav2Vec2](https://huggingface.co/facebook/wav2vec2-base-960h) +- [Keyword Spotting with Wav2Vec2](https://huggingface.co/superb/wav2vec2-base-superb-ks) +- [Audio Classification with Audio Spectrogram Transformer](https://huggingface.co/MIT/ast-finetuned-audioset-10-10-0.4593) + +In Multimodal tasks: +- [Table Question Answering with TAPAS](https://huggingface.co/google/tapas-base-finetuned-wtq) +- [Visual Question Answering with ViLT](https://huggingface.co/dandelin/vilt-b32-finetuned-vqa) +- [Zero-shot Image Classification with CLIP](https://huggingface.co/openai/clip-vit-large-patch14) +- [Document Question Answering with LayoutLM](https://huggingface.co/impira/layoutlm-document-qa) +- [Zero-shot Video Classification with X-CLIP](https://huggingface.co/docs/transformers/model_doc/xclip) + +**[Write With Transformer](https://transformer.huggingface.co)**, built by the Hugging Face team, is the official demo of this repo’s text generation capabilities. + +## If you are looking for custom support from the Hugging Face team + + + HuggingFace Expert Acceleration Program +
+ +## Quick tour + +To immediately use a model on a given input (text, image, audio, ...), we provide the `pipeline` API. Pipelines group together a pretrained model with the preprocessing that was used during that model's training. Here is how to quickly use a pipeline to classify positive versus negative texts: + +```python +>>> from transformers import pipeline + +# Allocate a pipeline for sentiment-analysis +>>> classifier = pipeline('sentiment-analysis') +>>> classifier('We are very happy to introduce pipeline to the transformers repository.') +[{'label': 'POSITIVE', 'score': 0.9996980428695679}] +``` + +The second line of code downloads and caches the pretrained model used by the pipeline, while the third evaluates it on the given text. Here the answer is "positive" with a confidence of 99.97%. + +Many tasks have a pre-trained `pipeline` ready to go, in NLP but also in computer vision and speech. For example, we can easily extract detected objects in an image: + +``` python +>>> import requests +>>> from PIL import Image +>>> from transformers import pipeline + +# Download an image with cute cats +>>> url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/coco_sample.png" +>>> image_data = requests.get(url, stream=True).raw +>>> image = Image.open(image_data) + +# Allocate a pipeline for object detection +>>> object_detector = pipeline('object-detection') +>>> object_detector(image) +[{'score': 0.9982201457023621, + 'label': 'remote', + 'box': {'xmin': 40, 'ymin': 70, 'xmax': 175, 'ymax': 117}}, + {'score': 0.9960021376609802, + 'label': 'remote', + 'box': {'xmin': 333, 'ymin': 72, 'xmax': 368, 'ymax': 187}}, + {'score': 0.9954745173454285, + 'label': 'couch', + 'box': {'xmin': 0, 'ymin': 1, 'xmax': 639, 'ymax': 473}}, + {'score': 0.9988006353378296, + 'label': 'cat', + 'box': {'xmin': 13, 'ymin': 52, 'xmax': 314, 'ymax': 470}}, + {'score': 0.9986783862113953, + 'label': 'cat', + 'box': {'xmin': 345, 'ymin': 23, 'xmax': 640, 'ymax': 368}}] +``` + +Here we get a list of objects detected in the image, with a box surrounding the object and a confidence score. Here is the original image on the left, with the predictions displayed on the right: + +

+ + +

+ +You can learn more about the tasks supported by the `pipeline` API in [this tutorial](https://huggingface.co/docs/transformers/task_summary). + +In addition to `pipeline`, to download and use any of the pretrained models on your given task, all it takes is three lines of code. Here is the PyTorch version: +```python +>>> from transformers import AutoTokenizer, AutoModel + +>>> tokenizer = AutoTokenizer.from_pretrained("bert-base-uncased") +>>> model = AutoModel.from_pretrained("bert-base-uncased") + +>>> inputs = tokenizer("Hello world!", return_tensors="pt") +>>> outputs = model(**inputs) +``` + +And here is the equivalent code for TensorFlow: +```python +>>> from transformers import AutoTokenizer, TFAutoModel + +>>> tokenizer = AutoTokenizer.from_pretrained("bert-base-uncased") +>>> model = TFAutoModel.from_pretrained("bert-base-uncased") + +>>> inputs = tokenizer("Hello world!", return_tensors="tf") +>>> outputs = model(**inputs) +``` + +The tokenizer is responsible for all the preprocessing the pretrained model expects, and can be called directly on a single string (as in the above examples) or a list. It will output a dictionary that you can use in downstream code or simply directly pass to your model using the ** argument unpacking operator. + +The model itself is a regular [Pytorch `nn.Module`](https://pytorch.org/docs/stable/nn.html#torch.nn.Module) or a [TensorFlow `tf.keras.Model`](https://www.tensorflow.org/api_docs/python/tf/keras/Model) (depending on your backend) which you can use as usual. [This tutorial](https://huggingface.co/docs/transformers/training) explains how to integrate such a model into a classic PyTorch or TensorFlow training loop, or how to use our `Trainer` API to quickly fine-tune on a new dataset. + +## Why should I use transformers? + +1. Easy-to-use state-of-the-art models: + - High performance on natural language understanding & generation, computer vision, and audio tasks. + - Low barrier to entry for educators and practitioners. + - Few user-facing abstractions with just three classes to learn. + - A unified API for using all our pretrained models. + +1. Lower compute costs, smaller carbon footprint: + - Researchers can share trained models instead of always retraining. + - Practitioners can reduce compute time and production costs. + - Dozens of architectures with over 60,000 pretrained models across all modalities. + +1. Choose the right framework for every part of a model's lifetime: + - Train state-of-the-art models in 3 lines of code. + - Move a single model between TF2.0/PyTorch/JAX frameworks at will. + - Seamlessly pick the right framework for training, evaluation and production. + +1. Easily customize a model or an example to your needs: + - We provide examples for each architecture to reproduce the results published by its original authors. + - Model internals are exposed as consistently as possible. + - Model files can be used independently of the library for quick experiments. + +## Why shouldn't I use transformers? + +- This library is not a modular toolbox of building blocks for neural nets. The code in the model files is not refactored with additional abstractions on purpose, so that researchers can quickly iterate on each of the models without diving into additional abstractions/files. +- The training API is not intended to work on any model but is optimized to work with the models provided by the library. For generic machine learning loops, you should use another library (possibly, [Accelerate](https://huggingface.co/docs/accelerate)). +- While we strive to present as many use cases as possible, the scripts in our [examples folder](https://github.com/huggingface/transformers/tree/main/examples) are just that: examples. It is expected that they won't work out-of-the box on your specific problem and that you will be required to change a few lines of code to adapt them to your needs. + +## Installation + +### With pip + +This repository is tested on Python 3.6+, Flax 0.3.2+, PyTorch 1.3.1+ and TensorFlow 2.3+. + +You should install 🤗 Transformers in a [virtual environment](https://docs.python.org/3/library/venv.html). If you're unfamiliar with Python virtual environments, check out the [user guide](https://packaging.python.org/guides/installing-using-pip-and-virtual-environments/). + +First, create a virtual environment with the version of Python you're going to use and activate it. + +Then, you will need to install at least one of Flax, PyTorch or TensorFlow. +Please refer to [TensorFlow installation page](https://www.tensorflow.org/install/), [PyTorch installation page](https://pytorch.org/get-started/locally/#start-locally) and/or [Flax](https://github.com/google/flax#quick-install) and [Jax](https://github.com/google/jax#installation) installation pages regarding the specific installation command for your platform. + +When one of those backends has been installed, 🤗 Transformers can be installed using pip as follows: + +```bash +pip install transformers +``` + +If you'd like to play with the examples or need the bleeding edge of the code and can't wait for a new release, you must [install the library from source](https://huggingface.co/docs/transformers/installation#installing-from-source). + +### With conda + +Since Transformers version v4.0.0, we now have a conda channel: `huggingface`. + +🤗 Transformers can be installed using conda as follows: + +```shell script +conda install -c huggingface transformers +``` + +Follow the installation pages of Flax, PyTorch or TensorFlow to see how to install them with conda. + +> **_NOTE:_** On Windows, you may be prompted to activate Developer Mode in order to benefit from caching. If this is not an option for you, please let us know in [this issue](https://github.com/huggingface/huggingface_hub/issues/1062). + +## Model architectures + +**[All the model checkpoints](https://huggingface.co/models)** provided by 🤗 Transformers are seamlessly integrated from the huggingface.co [model hub](https://huggingface.co/models) where they are uploaded directly by [users](https://huggingface.co/users) and [organizations](https://huggingface.co/organizations). + +Current number of checkpoints: ![](https://img.shields.io/endpoint?url=https://huggingface.co/api/shields/models&color=brightgreen) + +🤗 Transformers currently provides the following architectures (see [here](https://huggingface.co/docs/transformers/model_summary) for a high-level summary of each them): + +1. **[ALBERT](https://huggingface.co/docs/transformers/model_doc/albert)** (from Google Research and the Toyota Technological Institute at Chicago) released with the paper [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://arxiv.org/abs/1909.11942), by Zhenzhong Lan, Mingda Chen, Sebastian Goodman, Kevin Gimpel, Piyush Sharma, Radu Soricut. +1. **[ALIGN](https://huggingface.co/docs/transformers/model_doc/align)** (from Google Research) released with the paper [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://arxiv.org/abs/2102.05918) by Chao Jia, Yinfei Yang, Ye Xia, Yi-Ting Chen, Zarana Parekh, Hieu Pham, Quoc V. Le, Yunhsuan Sung, Zhen Li, Tom Duerig. +1. **[AltCLIP](https://huggingface.co/docs/transformers/model_doc/altclip)** (from BAAI) released with the paper [AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilities](https://arxiv.org/abs/2211.06679) by Chen, Zhongzhi and Liu, Guang and Zhang, Bo-Wen and Ye, Fulong and Yang, Qinghong and Wu, Ledell. +1. **[Audio Spectrogram Transformer](https://huggingface.co/docs/transformers/model_doc/audio-spectrogram-transformer)** (from MIT) released with the paper [AST: Audio Spectrogram Transformer](https://arxiv.org/abs/2104.01778) by Yuan Gong, Yu-An Chung, James Glass. +1. **[BART](https://huggingface.co/docs/transformers/model_doc/bart)** (from Facebook) released with the paper [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://arxiv.org/abs/1910.13461) by Mike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman Mohamed, Omer Levy, Ves Stoyanov and Luke Zettlemoyer. +1. **[BARThez](https://huggingface.co/docs/transformers/model_doc/barthez)** (from École polytechnique) released with the paper [BARThez: a Skilled Pretrained French Sequence-to-Sequence Model](https://arxiv.org/abs/2010.12321) by Moussa Kamal Eddine, Antoine J.-P. Tixier, Michalis Vazirgiannis. +1. **[BARTpho](https://huggingface.co/docs/transformers/model_doc/bartpho)** (from VinAI Research) released with the paper [BARTpho: Pre-trained Sequence-to-Sequence Models for Vietnamese](https://arxiv.org/abs/2109.09701) by Nguyen Luong Tran, Duong Minh Le and Dat Quoc Nguyen. +1. **[BEiT](https://huggingface.co/docs/transformers/model_doc/beit)** (from Microsoft) released with the paper [BEiT: BERT Pre-Training of Image Transformers](https://arxiv.org/abs/2106.08254) by Hangbo Bao, Li Dong, Furu Wei. +1. **[BERT](https://huggingface.co/docs/transformers/model_doc/bert)** (from Google) released with the paper [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://arxiv.org/abs/1810.04805) by Jacob Devlin, Ming-Wei Chang, Kenton Lee and Kristina Toutanova. +1. **[BERT For Sequence Generation](https://huggingface.co/docs/transformers/model_doc/bert-generation)** (from Google) released with the paper [Leveraging Pre-trained Checkpoints for Sequence Generation Tasks](https://arxiv.org/abs/1907.12461) by Sascha Rothe, Shashi Narayan, Aliaksei Severyn. +1. **[BERTweet](https://huggingface.co/docs/transformers/model_doc/bertweet)** (from VinAI Research) released with the paper [BERTweet: A pre-trained language model for English Tweets](https://aclanthology.org/2020.emnlp-demos.2/) by Dat Quoc Nguyen, Thanh Vu and Anh Tuan Nguyen. +1. **[BigBird-Pegasus](https://huggingface.co/docs/transformers/model_doc/bigbird_pegasus)** (from Google Research) released with the paper [Big Bird: Transformers for Longer Sequences](https://arxiv.org/abs/2007.14062) by Manzil Zaheer, Guru Guruganesh, Avinava Dubey, Joshua Ainslie, Chris Alberti, Santiago Ontanon, Philip Pham, Anirudh Ravula, Qifan Wang, Li Yang, Amr Ahmed. +1. **[BigBird-RoBERTa](https://huggingface.co/docs/transformers/model_doc/big_bird)** (from Google Research) released with the paper [Big Bird: Transformers for Longer Sequences](https://arxiv.org/abs/2007.14062) by Manzil Zaheer, Guru Guruganesh, Avinava Dubey, Joshua Ainslie, Chris Alberti, Santiago Ontanon, Philip Pham, Anirudh Ravula, Qifan Wang, Li Yang, Amr Ahmed. +1. **[BioGpt](https://huggingface.co/docs/transformers/model_doc/biogpt)** (from Microsoft Research AI4Science) released with the paper [BioGPT: generative pre-trained transformer for biomedical text generation and mining](https://academic.oup.com/bib/advance-article/doi/10.1093/bib/bbac409/6713511?guestAccessKey=a66d9b5d-4f83-4017-bb52-405815c907b9) by Renqian Luo, Liai Sun, Yingce Xia, Tao Qin, Sheng Zhang, Hoifung Poon and Tie-Yan Liu. +1. **[BiT](https://huggingface.co/docs/transformers/model_doc/bit)** (from Google AI) released with the paper [Big Transfer (BiT): General Visual Representation Learning](https://arxiv.org/abs/1912.11370) by Alexander Kolesnikov, Lucas Beyer, Xiaohua Zhai, Joan Puigcerver, Jessica Yung, Sylvain Gelly, Neil Houlsby. +1. **[Blenderbot](https://huggingface.co/docs/transformers/model_doc/blenderbot)** (from Facebook) released with the paper [Recipes for building an open-domain chatbot](https://arxiv.org/abs/2004.13637) by Stephen Roller, Emily Dinan, Naman Goyal, Da Ju, Mary Williamson, Yinhan Liu, Jing Xu, Myle Ott, Kurt Shuster, Eric M. Smith, Y-Lan Boureau, Jason Weston. +1. **[BlenderbotSmall](https://huggingface.co/docs/transformers/model_doc/blenderbot-small)** (from Facebook) released with the paper [Recipes for building an open-domain chatbot](https://arxiv.org/abs/2004.13637) by Stephen Roller, Emily Dinan, Naman Goyal, Da Ju, Mary Williamson, Yinhan Liu, Jing Xu, Myle Ott, Kurt Shuster, Eric M. Smith, Y-Lan Boureau, Jason Weston. +1. **[BLIP](https://huggingface.co/docs/transformers/model_doc/blip)** (from Salesforce) released with the paper [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://arxiv.org/abs/2201.12086) by Junnan Li, Dongxu Li, Caiming Xiong, Steven Hoi. +1. **[BLIP-2](https://huggingface.co/docs/transformers/model_doc/blip-2)** (from Salesforce) released with the paper [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://arxiv.org/abs/2301.12597) by Junnan Li, Dongxu Li, Silvio Savarese, Steven Hoi. +1. **[BLOOM](https://huggingface.co/docs/transformers/model_doc/bloom)** (from BigScience workshop) released by the [BigScience Workshop](https://bigscience.huggingface.co/). +1. **[BORT](https://huggingface.co/docs/transformers/model_doc/bort)** (from Alexa) released with the paper [Optimal Subarchitecture Extraction For BERT](https://arxiv.org/abs/2010.10499) by Adrian de Wynter and Daniel J. Perry. +1. **[BridgeTower](https://huggingface.co/docs/transformers/model_doc/bridgetower)** (from Harbin Institute of Technology/Microsoft Research Asia/Intel Labs) released with the paper [BridgeTower: Building Bridges Between Encoders in Vision-Language Representation Learning](https://arxiv.org/abs/2206.08657) by Xiao Xu, Chenfei Wu, Shachar Rosenman, Vasudev Lal, Wanxiang Che, Nan Duan. +1. **[ByT5](https://huggingface.co/docs/transformers/model_doc/byt5)** (from Google Research) released with the paper [ByT5: Towards a token-free future with pre-trained byte-to-byte models](https://arxiv.org/abs/2105.13626) by Linting Xue, Aditya Barua, Noah Constant, Rami Al-Rfou, Sharan Narang, Mihir Kale, Adam Roberts, Colin Raffel. +1. **[CamemBERT](https://huggingface.co/docs/transformers/model_doc/camembert)** (from Inria/Facebook/Sorbonne) released with the paper [CamemBERT: a Tasty French Language Model](https://arxiv.org/abs/1911.03894) by Louis Martin*, Benjamin Muller*, Pedro Javier Ortiz Suárez*, Yoann Dupont, Laurent Romary, Éric Villemonte de la Clergerie, Djamé Seddah and Benoît Sagot. +1. **[CANINE](https://huggingface.co/docs/transformers/model_doc/canine)** (from Google Research) released with the paper [CANINE: Pre-training an Efficient Tokenization-Free Encoder for Language Representation](https://arxiv.org/abs/2103.06874) by Jonathan H. Clark, Dan Garrette, Iulia Turc, John Wieting. +1. **[Chinese-CLIP](https://huggingface.co/docs/transformers/model_doc/chinese_clip)** (from OFA-Sys) released with the paper [Chinese CLIP: Contrastive Vision-Language Pretraining in Chinese](https://arxiv.org/abs/2211.01335) by An Yang, Junshu Pan, Junyang Lin, Rui Men, Yichang Zhang, Jingren Zhou, Chang Zhou. +1. **[CLAP](https://huggingface.co/docs/transformers/model_doc/clap)** (from LAION-AI) released with the paper [Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation]https://arxiv.org/abs/2211.06687) by Yusong Wu, Ke Chen, Tianyu Zhang, Yuchen Hui, Taylor Berg-Kirkpatrick, Shlomo Dubnov. +1. **[CLIP](https://huggingface.co/docs/transformers/model_doc/clip)** (from OpenAI) released with the paper [Learning Transferable Visual Models From Natural Language Supervision](https://arxiv.org/abs/2103.00020) by Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, Ilya Sutskever. +1. **[CLIPSeg](https://huggingface.co/docs/transformers/model_doc/clipseg)** (from University of Göttingen) released with the paper [Image Segmentation Using Text and Image Prompts](https://arxiv.org/abs/2112.10003) by Timo Lüddecke and Alexander Ecker. +1. **[CodeGen](https://huggingface.co/docs/transformers/model_doc/codegen)** (from Salesforce) released with the paper [A Conversational Paradigm for Program Synthesis](https://arxiv.org/abs/2203.13474) by Erik Nijkamp, Bo Pang, Hiroaki Hayashi, Lifu Tu, Huan Wang, Yingbo Zhou, Silvio Savarese, Caiming Xiong. +1. **[Conditional DETR](https://huggingface.co/docs/transformers/model_doc/conditional_detr)** (from Microsoft Research Asia) released with the paper [Conditional DETR for Fast Training Convergence](https://arxiv.org/abs/2108.06152) by Depu Meng, Xiaokang Chen, Zejia Fan, Gang Zeng, Houqiang Li, Yuhui Yuan, Lei Sun, Jingdong Wang. +1. **[ConvBERT](https://huggingface.co/docs/transformers/model_doc/convbert)** (from YituTech) released with the paper [ConvBERT: Improving BERT with Span-based Dynamic Convolution](https://arxiv.org/abs/2008.02496) by Zihang Jiang, Weihao Yu, Daquan Zhou, Yunpeng Chen, Jiashi Feng, Shuicheng Yan. +1. **[ConvNeXT](https://huggingface.co/docs/transformers/model_doc/convnext)** (from Facebook AI) released with the paper [A ConvNet for the 2020s](https://arxiv.org/abs/2201.03545) by Zhuang Liu, Hanzi Mao, Chao-Yuan Wu, Christoph Feichtenhofer, Trevor Darrell, Saining Xie. +1. **[ConvNeXTV2](https://huggingface.co/docs/transformers/model_doc/convnextv2)** (from Facebook AI) released with the paper [ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders](https://arxiv.org/abs/2301.00808) by Sanghyun Woo, Shoubhik Debnath, Ronghang Hu, Xinlei Chen, Zhuang Liu, In So Kweon, Saining Xie. +1. **[CPM](https://huggingface.co/docs/transformers/model_doc/cpm)** (from Tsinghua University) released with the paper [CPM: A Large-scale Generative Chinese Pre-trained Language Model](https://arxiv.org/abs/2012.00413) by Zhengyan Zhang, Xu Han, Hao Zhou, Pei Ke, Yuxian Gu, Deming Ye, Yujia Qin, Yusheng Su, Haozhe Ji, Jian Guan, Fanchao Qi, Xiaozhi Wang, Yanan Zheng, Guoyang Zeng, Huanqi Cao, Shengqi Chen, Daixuan Li, Zhenbo Sun, Zhiyuan Liu, Minlie Huang, Wentao Han, Jie Tang, Juanzi Li, Xiaoyan Zhu, Maosong Sun. +1. **[CTRL](https://huggingface.co/docs/transformers/model_doc/ctrl)** (from Salesforce) released with the paper [CTRL: A Conditional Transformer Language Model for Controllable Generation](https://arxiv.org/abs/1909.05858) by Nitish Shirish Keskar*, Bryan McCann*, Lav R. Varshney, Caiming Xiong and Richard Socher. +1. **[CvT](https://huggingface.co/docs/transformers/model_doc/cvt)** (from Microsoft) released with the paper [CvT: Introducing Convolutions to Vision Transformers](https://arxiv.org/abs/2103.15808) by Haiping Wu, Bin Xiao, Noel Codella, Mengchen Liu, Xiyang Dai, Lu Yuan, Lei Zhang. +1. **[Data2Vec](https://huggingface.co/docs/transformers/model_doc/data2vec)** (from Facebook) released with the paper [Data2Vec: A General Framework for Self-supervised Learning in Speech, Vision and Language](https://arxiv.org/abs/2202.03555) by Alexei Baevski, Wei-Ning Hsu, Qiantong Xu, Arun Babu, Jiatao Gu, Michael Auli. +1. **[DeBERTa](https://huggingface.co/docs/transformers/model_doc/deberta)** (from Microsoft) released with the paper [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://arxiv.org/abs/2006.03654) by Pengcheng He, Xiaodong Liu, Jianfeng Gao, Weizhu Chen. +1. **[DeBERTa-v2](https://huggingface.co/docs/transformers/model_doc/deberta-v2)** (from Microsoft) released with the paper [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://arxiv.org/abs/2006.03654) by Pengcheng He, Xiaodong Liu, Jianfeng Gao, Weizhu Chen. +1. **[Decision Transformer](https://huggingface.co/docs/transformers/model_doc/decision_transformer)** (from Berkeley/Facebook/Google) released with the paper [Decision Transformer: Reinforcement Learning via Sequence Modeling](https://arxiv.org/abs/2106.01345) by Lili Chen, Kevin Lu, Aravind Rajeswaran, Kimin Lee, Aditya Grover, Michael Laskin, Pieter Abbeel, Aravind Srinivas, Igor Mordatch. +1. **[Deformable DETR](https://huggingface.co/docs/transformers/model_doc/deformable_detr)** (from SenseTime Research) released with the paper [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://arxiv.org/abs/2010.04159) by Xizhou Zhu, Weijie Su, Lewei Lu, Bin Li, Xiaogang Wang, Jifeng Dai. +1. **[DeiT](https://huggingface.co/docs/transformers/model_doc/deit)** (from Facebook) released with the paper [Training data-efficient image transformers & distillation through attention](https://arxiv.org/abs/2012.12877) by Hugo Touvron, Matthieu Cord, Matthijs Douze, Francisco Massa, Alexandre Sablayrolles, Hervé Jégou. +1. **[DETA](https://huggingface.co/docs/transformers/model_doc/deta)** (from The University of Texas at Austin) released with the paper [NMS Strikes Back](https://arxiv.org/abs/2212.06137) by Jeffrey Ouyang-Zhang, Jang Hyun Cho, Xingyi Zhou, Philipp Krähenbühl. +1. **[DETR](https://huggingface.co/docs/transformers/model_doc/detr)** (from Facebook) released with the paper [End-to-End Object Detection with Transformers](https://arxiv.org/abs/2005.12872) by Nicolas Carion, Francisco Massa, Gabriel Synnaeve, Nicolas Usunier, Alexander Kirillov, Sergey Zagoruyko. +1. **[DialoGPT](https://huggingface.co/docs/transformers/model_doc/dialogpt)** (from Microsoft Research) released with the paper [DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation](https://arxiv.org/abs/1911.00536) by Yizhe Zhang, Siqi Sun, Michel Galley, Yen-Chun Chen, Chris Brockett, Xiang Gao, Jianfeng Gao, Jingjing Liu, Bill Dolan. +1. **[DiNAT](https://huggingface.co/docs/transformers/model_doc/dinat)** (from SHI Labs) released with the paper [Dilated Neighborhood Attention Transformer](https://arxiv.org/abs/2209.15001) by Ali Hassani and Humphrey Shi. +1. **[DistilBERT](https://huggingface.co/docs/transformers/model_doc/distilbert)** (from HuggingFace), released together with the paper [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://arxiv.org/abs/1910.01108) by Victor Sanh, Lysandre Debut and Thomas Wolf. The same method has been applied to compress GPT2 into [DistilGPT2](https://github.com/huggingface/transformers/tree/main/examples/research_projects/distillation), RoBERTa into [DistilRoBERTa](https://github.com/huggingface/transformers/tree/main/examples/research_projects/distillation), Multilingual BERT into [DistilmBERT](https://github.com/huggingface/transformers/tree/main/examples/research_projects/distillation) and a German version of DistilBERT. +1. **[DiT](https://huggingface.co/docs/transformers/model_doc/dit)** (from Microsoft Research) released with the paper [DiT: Self-supervised Pre-training for Document Image Transformer](https://arxiv.org/abs/2203.02378) by Junlong Li, Yiheng Xu, Tengchao Lv, Lei Cui, Cha Zhang, Furu Wei. +1. **[Donut](https://huggingface.co/docs/transformers/model_doc/donut)** (from NAVER), released together with the paper [OCR-free Document Understanding Transformer](https://arxiv.org/abs/2111.15664) by Geewook Kim, Teakgyu Hong, Moonbin Yim, Jeongyeon Nam, Jinyoung Park, Jinyeong Yim, Wonseok Hwang, Sangdoo Yun, Dongyoon Han, Seunghyun Park. +1. **[DPR](https://huggingface.co/docs/transformers/model_doc/dpr)** (from Facebook) released with the paper [Dense Passage Retrieval for Open-Domain Question Answering](https://arxiv.org/abs/2004.04906) by Vladimir Karpukhin, Barlas Oğuz, Sewon Min, Patrick Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, and Wen-tau Yih. +1. **[DPT](https://huggingface.co/docs/transformers/master/model_doc/dpt)** (from Intel Labs) released with the paper [Vision Transformers for Dense Prediction](https://arxiv.org/abs/2103.13413) by René Ranftl, Alexey Bochkovskiy, Vladlen Koltun. +1. **[EfficientFormer](https://huggingface.co/docs/transformers/model_doc/efficientformer)** (from Snap Research) released with the paper [EfficientFormer: Vision Transformers at MobileNetSpeed](https://arxiv.org/abs/2206.01191) by Yanyu Li, Geng Yuan, Yang Wen, Ju Hu, Georgios Evangelidis, Sergey Tulyakov, Yanzhi Wang, Jian Ren. +1. **[EfficientNet](https://huggingface.co/docs/transformers/model_doc/efficientnet)** (from Google Brain) released with the paper [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://arxiv.org/abs/1905.11946) by Mingxing Tan, Quoc V. Le. +1. **[ELECTRA](https://huggingface.co/docs/transformers/model_doc/electra)** (from Google Research/Stanford University) released with the paper [ELECTRA: Pre-training text encoders as discriminators rather than generators](https://arxiv.org/abs/2003.10555) by Kevin Clark, Minh-Thang Luong, Quoc V. Le, Christopher D. Manning. +1. **[EncoderDecoder](https://huggingface.co/docs/transformers/model_doc/encoder-decoder)** (from Google Research) released with the paper [Leveraging Pre-trained Checkpoints for Sequence Generation Tasks](https://arxiv.org/abs/1907.12461) by Sascha Rothe, Shashi Narayan, Aliaksei Severyn. +1. **[ERNIE](https://huggingface.co/docs/transformers/model_doc/ernie)** (from Baidu) released with the paper [ERNIE: Enhanced Representation through Knowledge Integration](https://arxiv.org/abs/1904.09223) by Yu Sun, Shuohuan Wang, Yukun Li, Shikun Feng, Xuyi Chen, Han Zhang, Xin Tian, Danxiang Zhu, Hao Tian, Hua Wu. +1. **[ErnieM](https://huggingface.co/docs/transformers/model_doc/ernie_m)** (from Baidu) released with the paper [ERNIE-M: Enhanced Multilingual Representation by Aligning Cross-lingual Semantics with Monolingual Corpora](https://arxiv.org/abs/2012.15674) by Xuan Ouyang, Shuohuan Wang, Chao Pang, Yu Sun, Hao Tian, Hua Wu, Haifeng Wang. +1. **[ESM](https://huggingface.co/docs/transformers/model_doc/esm)** (from Meta AI) are transformer protein language models. **ESM-1b** was released with the paper [Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences](https://www.pnas.org/content/118/15/e2016239118) by Alexander Rives, Joshua Meier, Tom Sercu, Siddharth Goyal, Zeming Lin, Jason Liu, Demi Guo, Myle Ott, C. Lawrence Zitnick, Jerry Ma, and Rob Fergus. **ESM-1v** was released with the paper [Language models enable zero-shot prediction of the effects of mutations on protein function](https://doi.org/10.1101/2021.07.09.450648) by Joshua Meier, Roshan Rao, Robert Verkuil, Jason Liu, Tom Sercu and Alexander Rives. **ESM-2 and ESMFold** were released with the paper [Language models of protein sequences at the scale of evolution enable accurate structure prediction](https://doi.org/10.1101/2022.07.20.500902) by Zeming Lin, Halil Akin, Roshan Rao, Brian Hie, Zhongkai Zhu, Wenting Lu, Allan dos Santos Costa, Maryam Fazel-Zarandi, Tom Sercu, Sal Candido, Alexander Rives. +1. **[FLAN-T5](https://huggingface.co/docs/transformers/model_doc/flan-t5)** (from Google AI) released in the repository [google-research/t5x](https://github.com/google-research/t5x/blob/main/docs/models.md#flan-t5-checkpoints) by Hyung Won Chung, Le Hou, Shayne Longpre, Barret Zoph, Yi Tay, William Fedus, Eric Li, Xuezhi Wang, Mostafa Dehghani, Siddhartha Brahma, Albert Webson, Shixiang Shane Gu, Zhuyun Dai, Mirac Suzgun, Xinyun Chen, Aakanksha Chowdhery, Sharan Narang, Gaurav Mishra, Adams Yu, Vincent Zhao, Yanping Huang, Andrew Dai, Hongkun Yu, Slav Petrov, Ed H. Chi, Jeff Dean, Jacob Devlin, Adam Roberts, Denny Zhou, Quoc V. Le, and Jason Wei +1. **[FLAN-UL2](https://huggingface.co/docs/transformers/model_doc/flan-ul2)** (from Google AI) released in the repository [google-research/t5x](https://github.com/google-research/t5x/blob/main/docs/models.md#flan-ul2-checkpoints) by Hyung Won Chung, Le Hou, Shayne Longpre, Barret Zoph, Yi Tay, William Fedus, Eric Li, Xuezhi Wang, Mostafa Dehghani, Siddhartha Brahma, Albert Webson, Shixiang Shane Gu, Zhuyun Dai, Mirac Suzgun, Xinyun Chen, Aakanksha Chowdhery, Sharan Narang, Gaurav Mishra, Adams Yu, Vincent Zhao, Yanping Huang, Andrew Dai, Hongkun Yu, Slav Petrov, Ed H. Chi, Jeff Dean, Jacob Devlin, Adam Roberts, Denny Zhou, Quoc V. Le, and Jason Wei +1. **[FlauBERT](https://huggingface.co/docs/transformers/model_doc/flaubert)** (from CNRS) released with the paper [FlauBERT: Unsupervised Language Model Pre-training for French](https://arxiv.org/abs/1912.05372) by Hang Le, Loïc Vial, Jibril Frej, Vincent Segonne, Maximin Coavoux, Benjamin Lecouteux, Alexandre Allauzen, Benoît Crabbé, Laurent Besacier, Didier Schwab. +1. **[FLAVA](https://huggingface.co/docs/transformers/model_doc/flava)** (from Facebook AI) released with the paper [FLAVA: A Foundational Language And Vision Alignment Model](https://arxiv.org/abs/2112.04482) by Amanpreet Singh, Ronghang Hu, Vedanuj Goswami, Guillaume Couairon, Wojciech Galuba, Marcus Rohrbach, and Douwe Kiela. +1. **[FNet](https://huggingface.co/docs/transformers/model_doc/fnet)** (from Google Research) released with the paper [FNet: Mixing Tokens with Fourier Transforms](https://arxiv.org/abs/2105.03824) by James Lee-Thorp, Joshua Ainslie, Ilya Eckstein, Santiago Ontanon. +1. **[Funnel Transformer](https://huggingface.co/docs/transformers/model_doc/funnel)** (from CMU/Google Brain) released with the paper [Funnel-Transformer: Filtering out Sequential Redundancy for Efficient Language Processing](https://arxiv.org/abs/2006.03236) by Zihang Dai, Guokun Lai, Yiming Yang, Quoc V. Le. +1. **[GIT](https://huggingface.co/docs/transformers/model_doc/git)** (from Microsoft Research) released with the paper [GIT: A Generative Image-to-text Transformer for Vision and Language](https://arxiv.org/abs/2205.14100) by Jianfeng Wang, Zhengyuan Yang, Xiaowei Hu, Linjie Li, Kevin Lin, Zhe Gan, Zicheng Liu, Ce Liu, Lijuan Wang. +1. **[GLPN](https://huggingface.co/docs/transformers/model_doc/glpn)** (from KAIST) released with the paper [Global-Local Path Networks for Monocular Depth Estimation with Vertical CutDepth](https://arxiv.org/abs/2201.07436) by Doyeon Kim, Woonghyun Ga, Pyungwhan Ahn, Donggyu Joo, Sehwan Chun, Junmo Kim. +1. **[GPT](https://huggingface.co/docs/transformers/model_doc/openai-gpt)** (from OpenAI) released with the paper [Improving Language Understanding by Generative Pre-Training](https://blog.openai.com/language-unsupervised/) by Alec Radford, Karthik Narasimhan, Tim Salimans and Ilya Sutskever. +1. **[GPT Neo](https://huggingface.co/docs/transformers/model_doc/gpt_neo)** (from EleutherAI) released in the repository [EleutherAI/gpt-neo](https://github.com/EleutherAI/gpt-neo) by Sid Black, Stella Biderman, Leo Gao, Phil Wang and Connor Leahy. +1. **[GPT NeoX](https://huggingface.co/docs/transformers/model_doc/gpt_neox)** (from EleutherAI) released with the paper [GPT-NeoX-20B: An Open-Source Autoregressive Language Model](https://arxiv.org/abs/2204.06745) by Sid Black, Stella Biderman, Eric Hallahan, Quentin Anthony, Leo Gao, Laurence Golding, Horace He, Connor Leahy, Kyle McDonell, Jason Phang, Michael Pieler, USVSN Sai Prashanth, Shivanshu Purohit, Laria Reynolds, Jonathan Tow, Ben Wang, Samuel Weinbach +1. **[GPT NeoX Japanese](https://huggingface.co/docs/transformers/model_doc/gpt_neox_japanese)** (from ABEJA) released by Shinya Otani, Takayoshi Makabe, Anuj Arora, and Kyo Hattori. +1. **[GPT-2](https://huggingface.co/docs/transformers/model_doc/gpt2)** (from OpenAI) released with the paper [Language Models are Unsupervised Multitask Learners](https://blog.openai.com/better-language-models/) by Alec Radford*, Jeffrey Wu*, Rewon Child, David Luan, Dario Amodei** and Ilya Sutskever**. +1. **[GPT-J](https://huggingface.co/docs/transformers/model_doc/gptj)** (from EleutherAI) released in the repository [kingoflolz/mesh-transformer-jax](https://github.com/kingoflolz/mesh-transformer-jax/) by Ben Wang and Aran Komatsuzaki. +1. **[GPT-Sw3](https://huggingface.co/docs/transformers/model_doc/gpt-sw3)** (from AI-Sweden) released with the paper [Lessons Learned from GPT-SW3: Building the First Large-Scale Generative Language Model for Swedish](http://www.lrec-conf.org/proceedings/lrec2022/pdf/2022.lrec-1.376.pdf) by Ariel Ekgren, Amaru Cuba Gyllensten, Evangelia Gogoulou, Alice Heiman, Severine Verlinden, Joey Öhman, Fredrik Carlsson, Magnus Sahlgren. +1. **[GPTSAN-japanese](https://huggingface.co/docs/transformers/model_doc/gptsan-japanese)** released in the repository [tanreinama/GPTSAN](https://github.com/tanreinama/GPTSAN/blob/main/report/model.md) by Toshiyuki Sakamoto(tanreinama). +1. **[Graphormer](https://huggingface.co/docs/transformers/model_doc/graphormer)** (from Microsoft) released with the paper [Do Transformers Really Perform Bad for Graph Representation?](https://arxiv.org/abs/2106.05234) by Chengxuan Ying, Tianle Cai, Shengjie Luo, Shuxin Zheng, Guolin Ke, Di He, Yanming Shen, Tie-Yan Liu. +1. **[GroupViT](https://huggingface.co/docs/transformers/model_doc/groupvit)** (from UCSD, NVIDIA) released with the paper [GroupViT: Semantic Segmentation Emerges from Text Supervision](https://arxiv.org/abs/2202.11094) by Jiarui Xu, Shalini De Mello, Sifei Liu, Wonmin Byeon, Thomas Breuel, Jan Kautz, Xiaolong Wang. +1. **[Hubert](https://huggingface.co/docs/transformers/model_doc/hubert)** (from Facebook) released with the paper [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://arxiv.org/abs/2106.07447) by Wei-Ning Hsu, Benjamin Bolte, Yao-Hung Hubert Tsai, Kushal Lakhotia, Ruslan Salakhutdinov, Abdelrahman Mohamed. +1. **[I-BERT](https://huggingface.co/docs/transformers/model_doc/ibert)** (from Berkeley) released with the paper [I-BERT: Integer-only BERT Quantization](https://arxiv.org/abs/2101.01321) by Sehoon Kim, Amir Gholami, Zhewei Yao, Michael W. Mahoney, Kurt Keutzer. +1. **[ImageGPT](https://huggingface.co/docs/transformers/model_doc/imagegpt)** (from OpenAI) released with the paper [Generative Pretraining from Pixels](https://openai.com/blog/image-gpt/) by Mark Chen, Alec Radford, Rewon Child, Jeffrey Wu, Heewoo Jun, David Luan, Ilya Sutskever. +1. **[Informer](https://huggingface.co/docs/transformers/model_doc/informer)** (from Beihang University, UC Berkeley, Rutgers University, SEDD Company) released with the paper [Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting](https://arxiv.org/abs/2012.07436) by Haoyi Zhou, Shanghang Zhang, Jieqi Peng, Shuai Zhang, Jianxin Li, Hui Xiong, and Wancai Zhang. +1. **[Jukebox](https://huggingface.co/docs/transformers/model_doc/jukebox)** (from OpenAI) released with the paper [Jukebox: A Generative Model for Music](https://arxiv.org/pdf/2005.00341.pdf) by Prafulla Dhariwal, Heewoo Jun, Christine Payne, Jong Wook Kim, Alec Radford, Ilya Sutskever. +1. **[LayoutLM](https://huggingface.co/docs/transformers/model_doc/layoutlm)** (from Microsoft Research Asia) released with the paper [LayoutLM: Pre-training of Text and Layout for Document Image Understanding](https://arxiv.org/abs/1912.13318) by Yiheng Xu, Minghao Li, Lei Cui, Shaohan Huang, Furu Wei, Ming Zhou. +1. **[LayoutLMv2](https://huggingface.co/docs/transformers/model_doc/layoutlmv2)** (from Microsoft Research Asia) released with the paper [LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding](https://arxiv.org/abs/2012.14740) by Yang Xu, Yiheng Xu, Tengchao Lv, Lei Cui, Furu Wei, Guoxin Wang, Yijuan Lu, Dinei Florencio, Cha Zhang, Wanxiang Che, Min Zhang, Lidong Zhou. +1. **[LayoutLMv3](https://huggingface.co/docs/transformers/model_doc/layoutlmv3)** (from Microsoft Research Asia) released with the paper [LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking](https://arxiv.org/abs/2204.08387) by Yupan Huang, Tengchao Lv, Lei Cui, Yutong Lu, Furu Wei. +1. **[LayoutXLM](https://huggingface.co/docs/transformers/model_doc/layoutxlm)** (from Microsoft Research Asia) released with the paper [LayoutXLM: Multimodal Pre-training for Multilingual Visually-rich Document Understanding](https://arxiv.org/abs/2104.08836) by Yiheng Xu, Tengchao Lv, Lei Cui, Guoxin Wang, Yijuan Lu, Dinei Florencio, Cha Zhang, Furu Wei. +1. **[LED](https://huggingface.co/docs/transformers/model_doc/led)** (from AllenAI) released with the paper [Longformer: The Long-Document Transformer](https://arxiv.org/abs/2004.05150) by Iz Beltagy, Matthew E. Peters, Arman Cohan. +1. **[LeViT](https://huggingface.co/docs/transformers/model_doc/levit)** (from Meta AI) released with the paper [LeViT: A Vision Transformer in ConvNet's Clothing for Faster Inference](https://arxiv.org/abs/2104.01136) by Ben Graham, Alaaeldin El-Nouby, Hugo Touvron, Pierre Stock, Armand Joulin, Hervé Jégou, Matthijs Douze. +1. **[LiLT](https://huggingface.co/docs/transformers/model_doc/lilt)** (from South China University of Technology) released with the paper [LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding](https://arxiv.org/abs/2202.13669) by Jiapeng Wang, Lianwen Jin, Kai Ding. +1. **[LLaMA](https://huggingface.co/docs/transformers/main/model_doc/llama)** (from The FAIR team of Meta AI) released with the paper [LLaMA: Open and Efficient Foundation Language Models](https://arxiv.org/abs/2302.13971) by Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timothée Lacroix, Baptiste Rozière, Naman Goyal, Eric Hambro, Faisal Azhar, Aurelien Rodriguez, Armand Joulin, Edouard Grave, Guillaume Lample. +1. **[Longformer](https://huggingface.co/docs/transformers/model_doc/longformer)** (from AllenAI) released with the paper [Longformer: The Long-Document Transformer](https://arxiv.org/abs/2004.05150) by Iz Beltagy, Matthew E. Peters, Arman Cohan. +1. **[LongT5](https://huggingface.co/docs/transformers/model_doc/longt5)** (from Google AI) released with the paper [LongT5: Efficient Text-To-Text Transformer for Long Sequences](https://arxiv.org/abs/2112.07916) by Mandy Guo, Joshua Ainslie, David Uthus, Santiago Ontanon, Jianmo Ni, Yun-Hsuan Sung, Yinfei Yang. +1. **[LUKE](https://huggingface.co/docs/transformers/model_doc/luke)** (from Studio Ousia) released with the paper [LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention](https://arxiv.org/abs/2010.01057) by Ikuya Yamada, Akari Asai, Hiroyuki Shindo, Hideaki Takeda, Yuji Matsumoto. +1. **[LXMERT](https://huggingface.co/docs/transformers/model_doc/lxmert)** (from UNC Chapel Hill) released with the paper [LXMERT: Learning Cross-Modality Encoder Representations from Transformers for Open-Domain Question Answering](https://arxiv.org/abs/1908.07490) by Hao Tan and Mohit Bansal. +1. **[M-CTC-T](https://huggingface.co/docs/transformers/model_doc/mctct)** (from Facebook) released with the paper [Pseudo-Labeling For Massively Multilingual Speech Recognition](https://arxiv.org/abs/2111.00161) by Loren Lugosch, Tatiana Likhomanenko, Gabriel Synnaeve, and Ronan Collobert. +1. **[M2M100](https://huggingface.co/docs/transformers/model_doc/m2m_100)** (from Facebook) released with the paper [Beyond English-Centric Multilingual Machine Translation](https://arxiv.org/abs/2010.11125) by Angela Fan, Shruti Bhosale, Holger Schwenk, Zhiyi Ma, Ahmed El-Kishky, Siddharth Goyal, Mandeep Baines, Onur Celebi, Guillaume Wenzek, Vishrav Chaudhary, Naman Goyal, Tom Birch, Vitaliy Liptchinsky, Sergey Edunov, Edouard Grave, Michael Auli, Armand Joulin. +1. **[MarianMT](https://huggingface.co/docs/transformers/model_doc/marian)** Machine translation models trained using [OPUS](http://opus.nlpl.eu/) data by Jörg Tiedemann. The [Marian Framework](https://marian-nmt.github.io/) is being developed by the Microsoft Translator Team. +1. **[MarkupLM](https://huggingface.co/docs/transformers/model_doc/markuplm)** (from Microsoft Research Asia) released with the paper [MarkupLM: Pre-training of Text and Markup Language for Visually-rich Document Understanding](https://arxiv.org/abs/2110.08518) by Junlong Li, Yiheng Xu, Lei Cui, Furu Wei. +1. **[Mask2Former](https://huggingface.co/docs/transformers/model_doc/mask2former)** (from FAIR and UIUC) released with the paper [Masked-attention Mask Transformer for Universal Image Segmentation](https://arxiv.org/abs/2112.01527) by Bowen Cheng, Ishan Misra, Alexander G. Schwing, Alexander Kirillov, Rohit Girdhar. +1. **[MaskFormer](https://huggingface.co/docs/transformers/model_doc/maskformer)** (from Meta and UIUC) released with the paper [Per-Pixel Classification is Not All You Need for Semantic Segmentation](https://arxiv.org/abs/2107.06278) by Bowen Cheng, Alexander G. Schwing, Alexander Kirillov. +1. **[mBART](https://huggingface.co/docs/transformers/model_doc/mbart)** (from Facebook) released with the paper [Multilingual Denoising Pre-training for Neural Machine Translation](https://arxiv.org/abs/2001.08210) by Yinhan Liu, Jiatao Gu, Naman Goyal, Xian Li, Sergey Edunov, Marjan Ghazvininejad, Mike Lewis, Luke Zettlemoyer. +1. **[mBART-50](https://huggingface.co/docs/transformers/model_doc/mbart)** (from Facebook) released with the paper [Multilingual Translation with Extensible Multilingual Pretraining and Finetuning](https://arxiv.org/abs/2008.00401) by Yuqing Tang, Chau Tran, Xian Li, Peng-Jen Chen, Naman Goyal, Vishrav Chaudhary, Jiatao Gu, Angela Fan. +1. **[MEGA](https://huggingface.co/docs/transformers/main/model_doc/mega)** (from Facebook) released with the paper [Mega: Moving Average Equipped Gated Attention](https://arxiv.org/abs/2209.10655) by Xuezhe Ma, Chunting Zhou, Xiang Kong, Junxian He, Liangke Gui, Graham Neubig, Jonathan May, and Luke Zettlemoyer. +1. **[Megatron-BERT](https://huggingface.co/docs/transformers/model_doc/megatron-bert)** (from NVIDIA) released with the paper [Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism](https://arxiv.org/abs/1909.08053) by Mohammad Shoeybi, Mostofa Patwary, Raul Puri, Patrick LeGresley, Jared Casper and Bryan Catanzaro. +1. **[Megatron-GPT2](https://huggingface.co/docs/transformers/model_doc/megatron_gpt2)** (from NVIDIA) released with the paper [Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism](https://arxiv.org/abs/1909.08053) by Mohammad Shoeybi, Mostofa Patwary, Raul Puri, Patrick LeGresley, Jared Casper and Bryan Catanzaro. +1. **[MGP-STR](https://huggingface.co/docs/transformers/model_doc/mgp-str)** (from Alibaba Research) released with the paper [Multi-Granularity Prediction for Scene Text Recognition](https://arxiv.org/abs/2209.03592) by Peng Wang, Cheng Da, and Cong Yao. +1. **[mLUKE](https://huggingface.co/docs/transformers/model_doc/mluke)** (from Studio Ousia) released with the paper [mLUKE: The Power of Entity Representations in Multilingual Pretrained Language Models](https://arxiv.org/abs/2110.08151) by Ryokan Ri, Ikuya Yamada, and Yoshimasa Tsuruoka. +1. **[MobileBERT](https://huggingface.co/docs/transformers/model_doc/mobilebert)** (from CMU/Google Brain) released with the paper [MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices](https://arxiv.org/abs/2004.02984) by Zhiqing Sun, Hongkun Yu, Xiaodan Song, Renjie Liu, Yiming Yang, and Denny Zhou. +1. **[MobileNetV1](https://huggingface.co/docs/transformers/model_doc/mobilenet_v1)** (from Google Inc.) released with the paper [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://arxiv.org/abs/1704.04861) by Andrew G. Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, Hartwig Adam. +1. **[MobileNetV2](https://huggingface.co/docs/transformers/model_doc/mobilenet_v2)** (from Google Inc.) released with the paper [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://arxiv.org/abs/1801.04381) by Mark Sandler, Andrew Howard, Menglong Zhu, Andrey Zhmoginov, Liang-Chieh Chen. +1. **[MobileViT](https://huggingface.co/docs/transformers/model_doc/mobilevit)** (from Apple) released with the paper [MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer](https://arxiv.org/abs/2110.02178) by Sachin Mehta and Mohammad Rastegari. +1. **[MPNet](https://huggingface.co/docs/transformers/model_doc/mpnet)** (from Microsoft Research) released with the paper [MPNet: Masked and Permuted Pre-training for Language Understanding](https://arxiv.org/abs/2004.09297) by Kaitao Song, Xu Tan, Tao Qin, Jianfeng Lu, Tie-Yan Liu. +1. **[MT5](https://huggingface.co/docs/transformers/model_doc/mt5)** (from Google AI) released with the paper [mT5: A massively multilingual pre-trained text-to-text transformer](https://arxiv.org/abs/2010.11934) by Linting Xue, Noah Constant, Adam Roberts, Mihir Kale, Rami Al-Rfou, Aditya Siddhant, Aditya Barua, Colin Raffel. +1. **[MVP](https://huggingface.co/docs/transformers/model_doc/mvp)** (from RUC AI Box) released with the paper [MVP: Multi-task Supervised Pre-training for Natural Language Generation](https://arxiv.org/abs/2206.12131) by Tianyi Tang, Junyi Li, Wayne Xin Zhao and Ji-Rong Wen. +1. **[NAT](https://huggingface.co/docs/transformers/model_doc/nat)** (from SHI Labs) released with the paper [Neighborhood Attention Transformer](https://arxiv.org/abs/2204.07143) by Ali Hassani, Steven Walton, Jiachen Li, Shen Li, and Humphrey Shi. +1. **[Nezha](https://huggingface.co/docs/transformers/model_doc/nezha)** (from Huawei Noah’s Ark Lab) released with the paper [NEZHA: Neural Contextualized Representation for Chinese Language Understanding](https://arxiv.org/abs/1909.00204) by Junqiu Wei, Xiaozhe Ren, Xiaoguang Li, Wenyong Huang, Yi Liao, Yasheng Wang, Jiashu Lin, Xin Jiang, Xiao Chen and Qun Liu. +1. **[NLLB](https://huggingface.co/docs/transformers/model_doc/nllb)** (from Meta) released with the paper [No Language Left Behind: Scaling Human-Centered Machine Translation](https://arxiv.org/abs/2207.04672) by the NLLB team. +1. **[NLLB-MOE](https://huggingface.co/docs/transformers/main/model_doc/nllb-moe)** (from Meta) released with the paper [No Language Left Behind: Scaling Human-Centered Machine Translation](https://arxiv.org/abs/2207.04672) by the NLLB team. +1. **[Nyströmformer](https://huggingface.co/docs/transformers/model_doc/nystromformer)** (from the University of Wisconsin - Madison) released with the paper [Nyströmformer: A Nyström-Based Algorithm for Approximating Self-Attention](https://arxiv.org/abs/2102.03902) by Yunyang Xiong, Zhanpeng Zeng, Rudrasis Chakraborty, Mingxing Tan, Glenn Fung, Yin Li, Vikas Singh. +1. **[OneFormer](https://huggingface.co/docs/transformers/model_doc/oneformer)** (from SHI Labs) released with the paper [OneFormer: One Transformer to Rule Universal Image Segmentation](https://arxiv.org/abs/2211.06220) by Jitesh Jain, Jiachen Li, MangTik Chiu, Ali Hassani, Nikita Orlov, Humphrey Shi. +1. **[OPT](https://huggingface.co/docs/transformers/master/model_doc/opt)** (from Meta AI) released with the paper [OPT: Open Pre-trained Transformer Language Models](https://arxiv.org/abs/2205.01068) by Susan Zhang, Stephen Roller, Naman Goyal, Mikel Artetxe, Moya Chen, Shuohui Chen et al. +1. **[OWL-ViT](https://huggingface.co/docs/transformers/model_doc/owlvit)** (from Google AI) released with the paper [Simple Open-Vocabulary Object Detection with Vision Transformers](https://arxiv.org/abs/2205.06230) by Matthias Minderer, Alexey Gritsenko, Austin Stone, Maxim Neumann, Dirk Weissenborn, Alexey Dosovitskiy, Aravindh Mahendran, Anurag Arnab, Mostafa Dehghani, Zhuoran Shen, Xiao Wang, Xiaohua Zhai, Thomas Kipf, and Neil Houlsby. +1. **[Pegasus](https://huggingface.co/docs/transformers/model_doc/pegasus)** (from Google) released with the paper [PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization](https://arxiv.org/abs/1912.08777) by Jingqing Zhang, Yao Zhao, Mohammad Saleh and Peter J. Liu. +1. **[PEGASUS-X](https://huggingface.co/docs/transformers/model_doc/pegasus_x)** (from Google) released with the paper [Investigating Efficiently Extending Transformers for Long Input Summarization](https://arxiv.org/abs/2208.04347) by Jason Phang, Yao Zhao, and Peter J. Liu. +1. **[Perceiver IO](https://huggingface.co/docs/transformers/model_doc/perceiver)** (from Deepmind) released with the paper [Perceiver IO: A General Architecture for Structured Inputs & Outputs](https://arxiv.org/abs/2107.14795) by Andrew Jaegle, Sebastian Borgeaud, Jean-Baptiste Alayrac, Carl Doersch, Catalin Ionescu, David Ding, Skanda Koppula, Daniel Zoran, Andrew Brock, Evan Shelhamer, Olivier Hénaff, Matthew M. Botvinick, Andrew Zisserman, Oriol Vinyals, João Carreira. +1. **[PhoBERT](https://huggingface.co/docs/transformers/model_doc/phobert)** (from VinAI Research) released with the paper [PhoBERT: Pre-trained language models for Vietnamese](https://www.aclweb.org/anthology/2020.findings-emnlp.92/) by Dat Quoc Nguyen and Anh Tuan Nguyen. +1. **[Pix2Struct](https://huggingface.co/docs/transformers/main/model_doc/pix2struct)** (from Google) released with the paper [Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding](https://arxiv.org/abs/2210.03347) by Kenton Lee, Mandar Joshi, Iulia Turc, Hexiang Hu, Fangyu Liu, Julian Eisenschlos, Urvashi Khandelwal, Peter Shaw, Ming-Wei Chang, Kristina Toutanova. +1. **[PLBart](https://huggingface.co/docs/transformers/model_doc/plbart)** (from UCLA NLP) released with the paper [Unified Pre-training for Program Understanding and Generation](https://arxiv.org/abs/2103.06333) by Wasi Uddin Ahmad, Saikat Chakraborty, Baishakhi Ray, Kai-Wei Chang. +1. **[PoolFormer](https://huggingface.co/docs/transformers/model_doc/poolformer)** (from Sea AI Labs) released with the paper [MetaFormer is Actually What You Need for Vision](https://arxiv.org/abs/2111.11418) by Yu, Weihao and Luo, Mi and Zhou, Pan and Si, Chenyang and Zhou, Yichen and Wang, Xinchao and Feng, Jiashi and Yan, Shuicheng. +1. **[ProphetNet](https://huggingface.co/docs/transformers/model_doc/prophetnet)** (from Microsoft Research) released with the paper [ProphetNet: Predicting Future N-gram for Sequence-to-Sequence Pre-training](https://arxiv.org/abs/2001.04063) by Yu Yan, Weizhen Qi, Yeyun Gong, Dayiheng Liu, Nan Duan, Jiusheng Chen, Ruofei Zhang and Ming Zhou. +1. **[QDQBert](https://huggingface.co/docs/transformers/model_doc/qdqbert)** (from NVIDIA) released with the paper [Integer Quantization for Deep Learning Inference: Principles and Empirical Evaluation](https://arxiv.org/abs/2004.09602) by Hao Wu, Patrick Judd, Xiaojie Zhang, Mikhail Isaev and Paulius Micikevicius. +1. **[RAG](https://huggingface.co/docs/transformers/model_doc/rag)** (from Facebook) released with the paper [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://arxiv.org/abs/2005.11401) by Patrick Lewis, Ethan Perez, Aleksandara Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, Sebastian Riedel, Douwe Kiela. +1. **[REALM](https://huggingface.co/docs/transformers/model_doc/realm.html)** (from Google Research) released with the paper [REALM: Retrieval-Augmented Language Model Pre-Training](https://arxiv.org/abs/2002.08909) by Kelvin Guu, Kenton Lee, Zora Tung, Panupong Pasupat and Ming-Wei Chang. +1. **[Reformer](https://huggingface.co/docs/transformers/model_doc/reformer)** (from Google Research) released with the paper [Reformer: The Efficient Transformer](https://arxiv.org/abs/2001.04451) by Nikita Kitaev, Łukasz Kaiser, Anselm Levskaya. +1. **[RegNet](https://huggingface.co/docs/transformers/model_doc/regnet)** (from META Platforms) released with the paper [Designing Network Design Space](https://arxiv.org/abs/2003.13678) by Ilija Radosavovic, Raj Prateek Kosaraju, Ross Girshick, Kaiming He, Piotr Dollár. +1. **[RemBERT](https://huggingface.co/docs/transformers/model_doc/rembert)** (from Google Research) released with the paper [Rethinking embedding coupling in pre-trained language models](https://arxiv.org/abs/2010.12821) by Hyung Won Chung, Thibault Févry, Henry Tsai, M. Johnson, Sebastian Ruder. +1. **[ResNet](https://huggingface.co/docs/transformers/model_doc/resnet)** (from Microsoft Research) released with the paper [Deep Residual Learning for Image Recognition](https://arxiv.org/abs/1512.03385) by Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun. +1. **[RoBERTa](https://huggingface.co/docs/transformers/model_doc/roberta)** (from Facebook), released together with the paper [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://arxiv.org/abs/1907.11692) by Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, Veselin Stoyanov. +1. **[RoBERTa-PreLayerNorm](https://huggingface.co/docs/transformers/model_doc/roberta-prelayernorm)** (from Facebook) released with the paper [fairseq: A Fast, Extensible Toolkit for Sequence Modeling](https://arxiv.org/abs/1904.01038) by Myle Ott, Sergey Edunov, Alexei Baevski, Angela Fan, Sam Gross, Nathan Ng, David Grangier, Michael Auli. +1. **[RoCBert](https://huggingface.co/docs/transformers/model_doc/roc_bert)** (from WeChatAI) released with the paper [RoCBert: Robust Chinese Bert with Multimodal Contrastive Pretraining](https://aclanthology.org/2022.acl-long.65.pdf) by HuiSu, WeiweiShi, XiaoyuShen, XiaoZhou, TuoJi, JiaruiFang, JieZhou. +1. **[RoFormer](https://huggingface.co/docs/transformers/model_doc/roformer)** (from ZhuiyiTechnology), released together with the paper [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://arxiv.org/abs/2104.09864) by Jianlin Su and Yu Lu and Shengfeng Pan and Bo Wen and Yunfeng Liu. +1. **[SegFormer](https://huggingface.co/docs/transformers/model_doc/segformer)** (from NVIDIA) released with the paper [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://arxiv.org/abs/2105.15203) by Enze Xie, Wenhai Wang, Zhiding Yu, Anima Anandkumar, Jose M. Alvarez, Ping Luo. +1. **[SEW](https://huggingface.co/docs/transformers/model_doc/sew)** (from ASAPP) released with the paper [Performance-Efficiency Trade-offs in Unsupervised Pre-training for Speech Recognition](https://arxiv.org/abs/2109.06870) by Felix Wu, Kwangyoun Kim, Jing Pan, Kyu Han, Kilian Q. Weinberger, Yoav Artzi. +1. **[SEW-D](https://huggingface.co/docs/transformers/model_doc/sew_d)** (from ASAPP) released with the paper [Performance-Efficiency Trade-offs in Unsupervised Pre-training for Speech Recognition](https://arxiv.org/abs/2109.06870) by Felix Wu, Kwangyoun Kim, Jing Pan, Kyu Han, Kilian Q. Weinberger, Yoav Artzi. +1. **[SpeechT5](https://huggingface.co/docs/transformers/model_doc/speecht5)** (from Microsoft Research) released with the paper [SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing](https://arxiv.org/abs/2110.07205) by Junyi Ao, Rui Wang, Long Zhou, Chengyi Wang, Shuo Ren, Yu Wu, Shujie Liu, Tom Ko, Qing Li, Yu Zhang, Zhihua Wei, Yao Qian, Jinyu Li, Furu Wei. +1. **[SpeechToTextTransformer](https://huggingface.co/docs/transformers/model_doc/speech_to_text)** (from Facebook), released together with the paper [fairseq S2T: Fast Speech-to-Text Modeling with fairseq](https://arxiv.org/abs/2010.05171) by Changhan Wang, Yun Tang, Xutai Ma, Anne Wu, Dmytro Okhonko, Juan Pino. +1. **[SpeechToTextTransformer2](https://huggingface.co/docs/transformers/model_doc/speech_to_text_2)** (from Facebook), released together with the paper [Large-Scale Self- and Semi-Supervised Learning for Speech Translation](https://arxiv.org/abs/2104.06678) by Changhan Wang, Anne Wu, Juan Pino, Alexei Baevski, Michael Auli, Alexis Conneau. +1. **[Splinter](https://huggingface.co/docs/transformers/model_doc/splinter)** (from Tel Aviv University), released together with the paper [Few-Shot Question Answering by Pretraining Span Selection](https://arxiv.org/abs/2101.00438) by Ori Ram, Yuval Kirstain, Jonathan Berant, Amir Globerson, Omer Levy. +1. **[SqueezeBERT](https://huggingface.co/docs/transformers/model_doc/squeezebert)** (from Berkeley) released with the paper [SqueezeBERT: What can computer vision teach NLP about efficient neural networks?](https://arxiv.org/abs/2006.11316) by Forrest N. Iandola, Albert E. Shaw, Ravi Krishna, and Kurt W. Keutzer. +1. **[Swin Transformer](https://huggingface.co/docs/transformers/model_doc/swin)** (from Microsoft) released with the paper [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://arxiv.org/abs/2103.14030) by Ze Liu, Yutong Lin, Yue Cao, Han Hu, Yixuan Wei, Zheng Zhang, Stephen Lin, Baining Guo. +1. **[Swin Transformer V2](https://huggingface.co/docs/transformers/model_doc/swinv2)** (from Microsoft) released with the paper [Swin Transformer V2: Scaling Up Capacity and Resolution](https://arxiv.org/abs/2111.09883) by Ze Liu, Han Hu, Yutong Lin, Zhuliang Yao, Zhenda Xie, Yixuan Wei, Jia Ning, Yue Cao, Zheng Zhang, Li Dong, Furu Wei, Baining Guo. +1. **[Swin2SR](https://huggingface.co/docs/transformers/model_doc/swin2sr)** (from University of Würzburg) released with the paper [Swin2SR: SwinV2 Transformer for Compressed Image Super-Resolution and Restoration](https://arxiv.org/abs/2209.11345) by Marcos V. Conde, Ui-Jin Choi, Maxime Burchi, Radu Timofte. +1. **[SwitchTransformers](https://huggingface.co/docs/transformers/model_doc/switch_transformers)** (from Google) released with the paper [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://arxiv.org/abs/2101.03961) by William Fedus, Barret Zoph, Noam Shazeer. +1. **[T5](https://huggingface.co/docs/transformers/model_doc/t5)** (from Google AI) released with the paper [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://arxiv.org/abs/1910.10683) by Colin Raffel and Noam Shazeer and Adam Roberts and Katherine Lee and Sharan Narang and Michael Matena and Yanqi Zhou and Wei Li and Peter J. Liu. +1. **[T5v1.1](https://huggingface.co/docs/transformers/model_doc/t5v1.1)** (from Google AI) released in the repository [google-research/text-to-text-transfer-transformer](https://github.com/google-research/text-to-text-transfer-transformer/blob/main/released_checkpoints.md#t511) by Colin Raffel and Noam Shazeer and Adam Roberts and Katherine Lee and Sharan Narang and Michael Matena and Yanqi Zhou and Wei Li and Peter J. Liu. +1. **[Table Transformer](https://huggingface.co/docs/transformers/model_doc/table-transformer)** (from Microsoft Research) released with the paper [PubTables-1M: Towards Comprehensive Table Extraction From Unstructured Documents](https://arxiv.org/abs/2110.00061) by Brandon Smock, Rohith Pesala, Robin Abraham. +1. **[TAPAS](https://huggingface.co/docs/transformers/model_doc/tapas)** (from Google AI) released with the paper [TAPAS: Weakly Supervised Table Parsing via Pre-training](https://arxiv.org/abs/2004.02349) by Jonathan Herzig, Paweł Krzysztof Nowak, Thomas Müller, Francesco Piccinno and Julian Martin Eisenschlos. +1. **[TAPEX](https://huggingface.co/docs/transformers/model_doc/tapex)** (from Microsoft Research) released with the paper [TAPEX: Table Pre-training via Learning a Neural SQL Executor](https://arxiv.org/abs/2107.07653) by Qian Liu, Bei Chen, Jiaqi Guo, Morteza Ziyadi, Zeqi Lin, Weizhu Chen, Jian-Guang Lou. +1. **[Time Series Transformer](https://huggingface.co/docs/transformers/model_doc/time_series_transformer)** (from HuggingFace). +1. **[TimeSformer](https://huggingface.co/docs/transformers/model_doc/timesformer)** (from Facebook) released with the paper [Is Space-Time Attention All You Need for Video Understanding?](https://arxiv.org/abs/2102.05095) by Gedas Bertasius, Heng Wang, Lorenzo Torresani. +1. **[Trajectory Transformer](https://huggingface.co/docs/transformers/model_doc/trajectory_transformers)** (from the University of California at Berkeley) released with the paper [Offline Reinforcement Learning as One Big Sequence Modeling Problem](https://arxiv.org/abs/2106.02039) by Michael Janner, Qiyang Li, Sergey Levine +1. **[Transformer-XL](https://huggingface.co/docs/transformers/model_doc/transfo-xl)** (from Google/CMU) released with the paper [Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context](https://arxiv.org/abs/1901.02860) by Zihang Dai*, Zhilin Yang*, Yiming Yang, Jaime Carbonell, Quoc V. Le, Ruslan Salakhutdinov. +1. **[TrOCR](https://huggingface.co/docs/transformers/model_doc/trocr)** (from Microsoft), released together with the paper [TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models](https://arxiv.org/abs/2109.10282) by Minghao Li, Tengchao Lv, Lei Cui, Yijuan Lu, Dinei Florencio, Cha Zhang, Zhoujun Li, Furu Wei. +1. **[TVLT](https://huggingface.co/docs/transformers/model_doc/tvlt)** (from UNC Chapel Hill) released with the paper [TVLT: Textless Vision-Language Transformer](https://arxiv.org/abs/2209.14156) by Zineng Tang, Jaemin Cho, Yixin Nie, Mohit Bansal. +1. **[UL2](https://huggingface.co/docs/transformers/model_doc/ul2)** (from Google Research) released with the paper [Unifying Language Learning Paradigms](https://arxiv.org/abs/2205.05131v1) by Yi Tay, Mostafa Dehghani, Vinh Q. Tran, Xavier Garcia, Dara Bahri, Tal Schuster, Huaixiu Steven Zheng, Neil Houlsby, Donald Metzler +1. **[UniSpeech](https://huggingface.co/docs/transformers/model_doc/unispeech)** (from Microsoft Research) released with the paper [UniSpeech: Unified Speech Representation Learning with Labeled and Unlabeled Data](https://arxiv.org/abs/2101.07597) by Chengyi Wang, Yu Wu, Yao Qian, Kenichi Kumatani, Shujie Liu, Furu Wei, Michael Zeng, Xuedong Huang. +1. **[UniSpeechSat](https://huggingface.co/docs/transformers/model_doc/unispeech-sat)** (from Microsoft Research) released with the paper [UNISPEECH-SAT: UNIVERSAL SPEECH REPRESENTATION LEARNING WITH SPEAKER AWARE PRE-TRAINING](https://arxiv.org/abs/2110.05752) by Sanyuan Chen, Yu Wu, Chengyi Wang, Zhengyang Chen, Zhuo Chen, Shujie Liu, Jian Wu, Yao Qian, Furu Wei, Jinyu Li, Xiangzhan Yu. +1. **[UPerNet](https://huggingface.co/docs/transformers/model_doc/upernet)** (from Peking University) released with the paper [Unified Perceptual Parsing for Scene Understanding](https://arxiv.org/abs/1807.10221) by Tete Xiao, Yingcheng Liu, Bolei Zhou, Yuning Jiang, Jian Sun. +1. **[VAN](https://huggingface.co/docs/transformers/model_doc/van)** (from Tsinghua University and Nankai University) released with the paper [Visual Attention Network](https://arxiv.org/abs/2202.09741) by Meng-Hao Guo, Cheng-Ze Lu, Zheng-Ning Liu, Ming-Ming Cheng, Shi-Min Hu. +1. **[VideoMAE](https://huggingface.co/docs/transformers/model_doc/videomae)** (from Multimedia Computing Group, Nanjing University) released with the paper [VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training](https://arxiv.org/abs/2203.12602) by Zhan Tong, Yibing Song, Jue Wang, Limin Wang. +1. **[ViLT](https://huggingface.co/docs/transformers/model_doc/vilt)** (from NAVER AI Lab/Kakao Enterprise/Kakao Brain) released with the paper [ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision](https://arxiv.org/abs/2102.03334) by Wonjae Kim, Bokyung Son, Ildoo Kim. +1. **[Vision Transformer (ViT)](https://huggingface.co/docs/transformers/model_doc/vit)** (from Google AI) released with the paper [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://arxiv.org/abs/2010.11929) by Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, Neil Houlsby. +1. **[VisualBERT](https://huggingface.co/docs/transformers/model_doc/visual_bert)** (from UCLA NLP) released with the paper [VisualBERT: A Simple and Performant Baseline for Vision and Language](https://arxiv.org/pdf/1908.03557) by Liunian Harold Li, Mark Yatskar, Da Yin, Cho-Jui Hsieh, Kai-Wei Chang. +1. **[ViT Hybrid](https://huggingface.co/docs/transformers/model_doc/vit_hybrid)** (from Google AI) released with the paper [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://arxiv.org/abs/2010.11929) by Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, Neil Houlsby. +1. **[ViTMAE](https://huggingface.co/docs/transformers/model_doc/vit_mae)** (from Meta AI) released with the paper [Masked Autoencoders Are Scalable Vision Learners](https://arxiv.org/abs/2111.06377) by Kaiming He, Xinlei Chen, Saining Xie, Yanghao Li, Piotr Dollár, Ross Girshick. +1. **[ViTMSN](https://huggingface.co/docs/transformers/model_doc/vit_msn)** (from Meta AI) released with the paper [Masked Siamese Networks for Label-Efficient Learning](https://arxiv.org/abs/2204.07141) by Mahmoud Assran, Mathilde Caron, Ishan Misra, Piotr Bojanowski, Florian Bordes, Pascal Vincent, Armand Joulin, Michael Rabbat, Nicolas Ballas. +1. **[Wav2Vec2](https://huggingface.co/docs/transformers/model_doc/wav2vec2)** (from Facebook AI) released with the paper [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://arxiv.org/abs/2006.11477) by Alexei Baevski, Henry Zhou, Abdelrahman Mohamed, Michael Auli. +1. **[Wav2Vec2-Conformer](https://huggingface.co/docs/transformers/model_doc/wav2vec2-conformer)** (from Facebook AI) released with the paper [FAIRSEQ S2T: Fast Speech-to-Text Modeling with FAIRSEQ](https://arxiv.org/abs/2010.05171) by Changhan Wang, Yun Tang, Xutai Ma, Anne Wu, Sravya Popuri, Dmytro Okhonko, Juan Pino. +1. **[Wav2Vec2Phoneme](https://huggingface.co/docs/transformers/model_doc/wav2vec2_phoneme)** (from Facebook AI) released with the paper [Simple and Effective Zero-shot Cross-lingual Phoneme Recognition](https://arxiv.org/abs/2109.11680) by Qiantong Xu, Alexei Baevski, Michael Auli. +1. **[WavLM](https://huggingface.co/docs/transformers/model_doc/wavlm)** (from Microsoft Research) released with the paper [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://arxiv.org/abs/2110.13900) by Sanyuan Chen, Chengyi Wang, Zhengyang Chen, Yu Wu, Shujie Liu, Zhuo Chen, Jinyu Li, Naoyuki Kanda, Takuya Yoshioka, Xiong Xiao, Jian Wu, Long Zhou, Shuo Ren, Yanmin Qian, Yao Qian, Jian Wu, Michael Zeng, Furu Wei. +1. **[Whisper](https://huggingface.co/docs/transformers/model_doc/whisper)** (from OpenAI) released with the paper [Robust Speech Recognition via Large-Scale Weak Supervision](https://cdn.openai.com/papers/whisper.pdf) by Alec Radford, Jong Wook Kim, Tao Xu, Greg Brockman, Christine McLeavey, Ilya Sutskever. +1. **[X-CLIP](https://huggingface.co/docs/transformers/model_doc/xclip)** (from Microsoft Research) released with the paper [Expanding Language-Image Pretrained Models for General Video Recognition](https://arxiv.org/abs/2208.02816) by Bolin Ni, Houwen Peng, Minghao Chen, Songyang Zhang, Gaofeng Meng, Jianlong Fu, Shiming Xiang, Haibin Ling. +1. **[X-MOD](https://huggingface.co/docs/transformers/model_doc/xmod)** (from Meta AI) released with the paper [Lifting the Curse of Multilinguality by Pre-training Modular Transformers](http://dx.doi.org/10.18653/v1/2022.naacl-main.255) by Jonas Pfeiffer, Naman Goyal, Xi Lin, Xian Li, James Cross, Sebastian Riedel, Mikel Artetxe. +1. **[XGLM](https://huggingface.co/docs/transformers/model_doc/xglm)** (From Facebook AI) released with the paper [Few-shot Learning with Multilingual Language Models](https://arxiv.org/abs/2112.10668) by Xi Victoria Lin, Todor Mihaylov, Mikel Artetxe, Tianlu Wang, Shuohui Chen, Daniel Simig, Myle Ott, Naman Goyal, Shruti Bhosale, Jingfei Du, Ramakanth Pasunuru, Sam Shleifer, Punit Singh Koura, Vishrav Chaudhary, Brian O'Horo, Jeff Wang, Luke Zettlemoyer, Zornitsa Kozareva, Mona Diab, Veselin Stoyanov, Xian Li. +1. **[XLM](https://huggingface.co/docs/transformers/model_doc/xlm)** (from Facebook) released together with the paper [Cross-lingual Language Model Pretraining](https://arxiv.org/abs/1901.07291) by Guillaume Lample and Alexis Conneau. +1. **[XLM-ProphetNet](https://huggingface.co/docs/transformers/model_doc/xlm-prophetnet)** (from Microsoft Research) released with the paper [ProphetNet: Predicting Future N-gram for Sequence-to-Sequence Pre-training](https://arxiv.org/abs/2001.04063) by Yu Yan, Weizhen Qi, Yeyun Gong, Dayiheng Liu, Nan Duan, Jiusheng Chen, Ruofei Zhang and Ming Zhou. +1. **[XLM-RoBERTa](https://huggingface.co/docs/transformers/model_doc/xlm-roberta)** (from Facebook AI), released together with the paper [Unsupervised Cross-lingual Representation Learning at Scale](https://arxiv.org/abs/1911.02116) by Alexis Conneau*, Kartikay Khandelwal*, Naman Goyal, Vishrav Chaudhary, Guillaume Wenzek, Francisco Guzmán, Edouard Grave, Myle Ott, Luke Zettlemoyer and Veselin Stoyanov. +1. **[XLM-RoBERTa-XL](https://huggingface.co/docs/transformers/model_doc/xlm-roberta-xl)** (from Facebook AI), released together with the paper [Larger-Scale Transformers for Multilingual Masked Language Modeling](https://arxiv.org/abs/2105.00572) by Naman Goyal, Jingfei Du, Myle Ott, Giri Anantharaman, Alexis Conneau. +1. **[XLM-V](https://huggingface.co/docs/transformers/model_doc/xlm-v)** (from Meta AI) released with the paper [XLM-V: Overcoming the Vocabulary Bottleneck in Multilingual Masked Language Models](https://arxiv.org/abs/2301.10472) by Davis Liang, Hila Gonen, Yuning Mao, Rui Hou, Naman Goyal, Marjan Ghazvininejad, Luke Zettlemoyer, Madian Khabsa. +1. **[XLNet](https://huggingface.co/docs/transformers/model_doc/xlnet)** (from Google/CMU) released with the paper [​XLNet: Generalized Autoregressive Pretraining for Language Understanding](https://arxiv.org/abs/1906.08237) by Zhilin Yang*, Zihang Dai*, Yiming Yang, Jaime Carbonell, Ruslan Salakhutdinov, Quoc V. Le. +1. **[XLS-R](https://huggingface.co/docs/transformers/model_doc/xls_r)** (from Facebook AI) released with the paper [XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale](https://arxiv.org/abs/2111.09296) by Arun Babu, Changhan Wang, Andros Tjandra, Kushal Lakhotia, Qiantong Xu, Naman Goyal, Kritika Singh, Patrick von Platen, Yatharth Saraf, Juan Pino, Alexei Baevski, Alexis Conneau, Michael Auli. +1. **[XLSR-Wav2Vec2](https://huggingface.co/docs/transformers/model_doc/xlsr_wav2vec2)** (from Facebook AI) released with the paper [Unsupervised Cross-Lingual Representation Learning For Speech Recognition](https://arxiv.org/abs/2006.13979) by Alexis Conneau, Alexei Baevski, Ronan Collobert, Abdelrahman Mohamed, Michael Auli. +1. **[YOLOS](https://huggingface.co/docs/transformers/model_doc/yolos)** (from Huazhong University of Science & Technology) released with the paper [You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection](https://arxiv.org/abs/2106.00666) by Yuxin Fang, Bencheng Liao, Xinggang Wang, Jiemin Fang, Jiyang Qi, Rui Wu, Jianwei Niu, Wenyu Liu. +1. **[YOSO](https://huggingface.co/docs/transformers/model_doc/yoso)** (from the University of Wisconsin - Madison) released with the paper [You Only Sample (Almost) Once: Linear Cost Self-Attention Via Bernoulli Sampling](https://arxiv.org/abs/2111.09714) by Zhanpeng Zeng, Yunyang Xiong, Sathya N. Ravi, Shailesh Acharya, Glenn Fung, Vikas Singh. +1. Want to contribute a new model? We have added a **detailed guide and templates** to guide you in the process of adding a new model. You can find them in the [`templates`](./templates) folder of the repository. Be sure to check the [contributing guidelines](./CONTRIBUTING.md) and contact the maintainers or open an issue to collect feedbacks before starting your PR. + +To check if each model has an implementation in Flax, PyTorch or TensorFlow, or has an associated tokenizer backed by the 🤗 Tokenizers library, refer to [this table](https://huggingface.co/docs/transformers/index#supported-frameworks). + +These implementations have been tested on several datasets (see the example scripts) and should match the performance of the original implementations. You can find more details on performance in the Examples section of the [documentation](https://github.com/huggingface/transformers/tree/main/examples). + + +## Learn more + +| Section | Description | +|-|-| +| [Documentation](https://huggingface.co/docs/transformers/) | Full API documentation and tutorials | +| [Task summary](https://huggingface.co/docs/transformers/task_summary) | Tasks supported by 🤗 Transformers | +| [Preprocessing tutorial](https://huggingface.co/docs/transformers/preprocessing) | Using the `Tokenizer` class to prepare data for the models | +| [Training and fine-tuning](https://huggingface.co/docs/transformers/training) | Using the models provided by 🤗 Transformers in a PyTorch/TensorFlow training loop and the `Trainer` API | +| [Quick tour: Fine-tuning/usage scripts](https://github.com/huggingface/transformers/tree/main/examples) | Example scripts for fine-tuning models on a wide range of tasks | +| [Model sharing and uploading](https://huggingface.co/docs/transformers/model_sharing) | Upload and share your fine-tuned models with the community | +| [Migration](https://huggingface.co/docs/transformers/migration) | Migrate to 🤗 Transformers from `pytorch-transformers` or `pytorch-pretrained-bert` | + +## Citation + +We now have a [paper](https://www.aclweb.org/anthology/2020.emnlp-demos.6/) you can cite for the 🤗 Transformers library: +```bibtex +@inproceedings{wolf-etal-2020-transformers, + title = "Transformers: State-of-the-Art Natural Language Processing", + author = "Thomas Wolf and Lysandre Debut and Victor Sanh and Julien Chaumond and Clement Delangue and Anthony Moi and Pierric Cistac and Tim Rault and Rémi Louf and Morgan Funtowicz and Joe Davison and Sam Shleifer and Patrick von Platen and Clara Ma and Yacine Jernite and Julien Plu and Canwen Xu and Teven Le Scao and Sylvain Gugger and Mariama Drame and Quentin Lhoest and Alexander M. Rush", + booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations", + month = oct, + year = "2020", + address = "Online", + publisher = "Association for Computational Linguistics", + url = "https://www.aclweb.org/anthology/2020.emnlp-demos.6", + pages = "38--45" +} +``` + diff --git a/hf-dev-train/transformers-main/src/transformers.egg-info/SOURCES.txt b/hf-dev-train/transformers-main/src/transformers.egg-info/SOURCES.txt new file mode 100644 index 0000000000000000000000000000000000000000..2039c32fc4e1dbc8b67a9923babb399309b4b248 --- /dev/null +++ b/hf-dev-train/transformers-main/src/transformers.egg-info/SOURCES.txt @@ -0,0 +1,1291 @@ +LICENSE +MANIFEST.in +README.md +pyproject.toml +setup.cfg +setup.py +src/transformers/__init__.py +src/transformers/activations.py +src/transformers/activations_tf.py +src/transformers/audio_utils.py +src/transformers/configuration_utils.py +src/transformers/convert_graph_to_onnx.py +src/transformers/convert_pytorch_checkpoint_to_tf2.py +src/transformers/convert_slow_tokenizer.py +src/transformers/convert_slow_tokenizers_checkpoints_to_fast.py +src/transformers/convert_tf_hub_seq_to_seq_bert_to_pytorch.py +src/transformers/debug_utils.py +src/transformers/deepspeed.py +src/transformers/dependency_versions_check.py +src/transformers/dependency_versions_table.py +src/transformers/dynamic_module_utils.py +src/transformers/feature_extraction_sequence_utils.py +src/transformers/feature_extraction_utils.py +src/transformers/file_utils.py +src/transformers/generation_flax_utils.py +src/transformers/generation_tf_utils.py +src/transformers/generation_utils.py +src/transformers/hf_argparser.py +src/transformers/image_processing_utils.py +src/transformers/image_transforms.py +src/transformers/image_utils.py +src/transformers/integrations.py +src/transformers/keras_callbacks.py +src/transformers/modelcard.py +src/transformers/modeling_flax_outputs.py +src/transformers/modeling_flax_pytorch_utils.py +src/transformers/modeling_flax_utils.py +src/transformers/modeling_outputs.py +src/transformers/modeling_tf_outputs.py +src/transformers/modeling_tf_pytorch_utils.py +src/transformers/modeling_tf_utils.py +src/transformers/modeling_utils.py +src/transformers/optimization.py +src/transformers/optimization_tf.py +src/transformers/processing_utils.py +src/transformers/pytorch_utils.py +src/transformers/testing_utils.py +src/transformers/tf_utils.py +src/transformers/time_series_utils.py +src/transformers/tokenization_utils.py +src/transformers/tokenization_utils_base.py +src/transformers/tokenization_utils_fast.py +src/transformers/trainer.py +src/transformers/trainer_callback.py +src/transformers/trainer_pt_utils.py +src/transformers/trainer_pt_utils_back.py +src/transformers/trainer_seq2seq.py +src/transformers/trainer_tf.py +src/transformers/trainer_utils.py +src/transformers/training_args.py +src/transformers/training_args_seq2seq.py +src/transformers/training_args_tf.py +src/transformers.egg-info/PKG-INFO +src/transformers.egg-info/SOURCES.txt +src/transformers.egg-info/dependency_links.txt +src/transformers.egg-info/entry_points.txt +src/transformers.egg-info/not-zip-safe +src/transformers.egg-info/requires.txt +src/transformers.egg-info/top_level.txt +src/transformers/benchmark/__init__.py +src/transformers/benchmark/benchmark.py +src/transformers/benchmark/benchmark_args.py +src/transformers/benchmark/benchmark_args_tf.py +src/transformers/benchmark/benchmark_args_utils.py +src/transformers/benchmark/benchmark_tf.py +src/transformers/benchmark/benchmark_utils.py +src/transformers/commands/__init__.py +src/transformers/commands/add_new_model.py +src/transformers/commands/add_new_model_like.py +src/transformers/commands/convert.py +src/transformers/commands/download.py +src/transformers/commands/env.py +src/transformers/commands/lfs.py +src/transformers/commands/pt_to_tf.py +src/transformers/commands/run.py +src/transformers/commands/serving.py +src/transformers/commands/train.py +src/transformers/commands/transformers_cli.py +src/transformers/commands/user.py +src/transformers/data/__init__.py +src/transformers/data/data_collator.py +src/transformers/data/data_collator_back.py +src/transformers/data/data_collator_qformer.py +src/transformers/data/test_generation_utils.py +src/transformers/data/datasets/__init__.py +src/transformers/data/datasets/glue.py +src/transformers/data/datasets/language_modeling.py +src/transformers/data/datasets/squad.py +src/transformers/data/metrics/__init__.py +src/transformers/data/metrics/squad_metrics.py +src/transformers/data/processors/__init__.py +src/transformers/data/processors/glue.py +src/transformers/data/processors/squad.py +src/transformers/data/processors/utils.py +src/transformers/data/processors/xnli.py +src/transformers/generation/__init__.py +src/transformers/generation/beam_constraints.py +src/transformers/generation/beam_search.py +src/transformers/generation/configuration_utils.py +src/transformers/generation/flax_logits_process.py +src/transformers/generation/flax_utils.py +src/transformers/generation/logits_process.py +src/transformers/generation/stopping_criteria.py +src/transformers/generation/tf_logits_process.py +src/transformers/generation/tf_utils.py +src/transformers/generation/utils.py +src/transformers/models/__init__.py +src/transformers/models/albert/__init__.py +src/transformers/models/albert/configuration_albert.py +src/transformers/models/albert/convert_albert_original_tf_checkpoint_to_pytorch.py +src/transformers/models/albert/modeling_albert.py +src/transformers/models/albert/modeling_flax_albert.py +src/transformers/models/albert/modeling_tf_albert.py +src/transformers/models/albert/tokenization_albert.py +src/transformers/models/albert/tokenization_albert_fast.py +src/transformers/models/align/__init__.py +src/transformers/models/align/configuration_align.py +src/transformers/models/align/convert_align_tf_to_hf.py +src/transformers/models/align/modeling_align.py +src/transformers/models/align/processing_align.py +src/transformers/models/altclip/__init__.py +src/transformers/models/altclip/configuration_altclip.py +src/transformers/models/altclip/modeling_altclip.py +src/transformers/models/altclip/processing_altclip.py +src/transformers/models/audio_spectrogram_transformer/__init__.py +src/transformers/models/audio_spectrogram_transformer/configuration_audio_spectrogram_transformer.py +src/transformers/models/audio_spectrogram_transformer/convert_audio_spectrogram_transformer_original_to_pytorch.py +src/transformers/models/audio_spectrogram_transformer/feature_extraction_audio_spectrogram_transformer.py +src/transformers/models/audio_spectrogram_transformer/modeling_audio_spectrogram_transformer.py +src/transformers/models/auto/__init__.py +src/transformers/models/auto/auto_factory.py +src/transformers/models/auto/configuration_auto.py +src/transformers/models/auto/feature_extraction_auto.py +src/transformers/models/auto/image_processing_auto.py +src/transformers/models/auto/modeling_auto.py +src/transformers/models/auto/modeling_flax_auto.py +src/transformers/models/auto/modeling_tf_auto.py +src/transformers/models/auto/processing_auto.py +src/transformers/models/auto/tokenization_auto.py +src/transformers/models/bart/__init__.py +src/transformers/models/bart/configuration_bart.py +src/transformers/models/bart/convert_bart_original_pytorch_checkpoint_to_pytorch.py +src/transformers/models/bart/modeling_bart.py +src/transformers/models/bart/modeling_flax_bart.py +src/transformers/models/bart/modeling_tf_bart.py +src/transformers/models/bart/tokenization_bart.py +src/transformers/models/bart/tokenization_bart_fast.py +src/transformers/models/barthez/__init__.py +src/transformers/models/barthez/tokenization_barthez.py +src/transformers/models/barthez/tokenization_barthez_fast.py +src/transformers/models/bartpho/__init__.py +src/transformers/models/bartpho/tokenization_bartpho.py +src/transformers/models/beit/__init__.py +src/transformers/models/beit/configuration_beit.py +src/transformers/models/beit/convert_beit_unilm_to_pytorch.py +src/transformers/models/beit/feature_extraction_beit.py +src/transformers/models/beit/image_processing_beit.py +src/transformers/models/beit/modeling_beit.py +src/transformers/models/beit/modeling_flax_beit.py +src/transformers/models/bert/__init__.py +src/transformers/models/bert/configuration_bert.py +src/transformers/models/bert/convert_bert_original_tf2_checkpoint_to_pytorch.py +src/transformers/models/bert/convert_bert_original_tf_checkpoint_to_pytorch.py +src/transformers/models/bert/convert_bert_pytorch_checkpoint_to_original_tf.py +src/transformers/models/bert/convert_bert_token_dropping_original_tf2_checkpoint_to_pytorch.py +src/transformers/models/bert/modeling_bert.py +src/transformers/models/bert/modeling_flax_bert.py +src/transformers/models/bert/modeling_tf_bert.py +src/transformers/models/bert/tokenization_bert.py +src/transformers/models/bert/tokenization_bert_fast.py +src/transformers/models/bert/tokenization_bert_tf.py +src/transformers/models/bert_generation/__init__.py +src/transformers/models/bert_generation/configuration_bert_generation.py +src/transformers/models/bert_generation/modeling_bert_generation.py +src/transformers/models/bert_generation/tokenization_bert_generation.py +src/transformers/models/bert_japanese/__init__.py +src/transformers/models/bert_japanese/tokenization_bert_japanese.py +src/transformers/models/bertweet/__init__.py +src/transformers/models/bertweet/tokenization_bertweet.py +src/transformers/models/big_bird/__init__.py +src/transformers/models/big_bird/configuration_big_bird.py +src/transformers/models/big_bird/convert_bigbird_original_tf_checkpoint_to_pytorch.py +src/transformers/models/big_bird/modeling_big_bird.py +src/transformers/models/big_bird/modeling_flax_big_bird.py +src/transformers/models/big_bird/tokenization_big_bird.py +src/transformers/models/big_bird/tokenization_big_bird_fast.py +src/transformers/models/bigbird_pegasus/__init__.py +src/transformers/models/bigbird_pegasus/configuration_bigbird_pegasus.py +src/transformers/models/bigbird_pegasus/convert_bigbird_pegasus_tf_to_pytorch.py +src/transformers/models/bigbird_pegasus/modeling_bigbird_pegasus.py +src/transformers/models/biogpt/__init__.py +src/transformers/models/biogpt/configuration_biogpt.py +src/transformers/models/biogpt/convert_biogpt_original_pytorch_checkpoint_to_pytorch.py +src/transformers/models/biogpt/modeling_biogpt.py +src/transformers/models/biogpt/tokenization_biogpt.py +src/transformers/models/bit/__init__.py +src/transformers/models/bit/configuration_bit.py +src/transformers/models/bit/convert_bit_to_pytorch.py +src/transformers/models/bit/image_processing_bit.py +src/transformers/models/bit/modeling_bit.py +src/transformers/models/blenderbot/__init__.py +src/transformers/models/blenderbot/configuration_blenderbot.py +src/transformers/models/blenderbot/convert_blenderbot_original_pytorch_checkpoint_to_pytorch.py +src/transformers/models/blenderbot/modeling_blenderbot.py +src/transformers/models/blenderbot/modeling_flax_blenderbot.py +src/transformers/models/blenderbot/modeling_tf_blenderbot.py +src/transformers/models/blenderbot/tokenization_blenderbot.py +src/transformers/models/blenderbot/tokenization_blenderbot_fast.py +src/transformers/models/blenderbot_small/__init__.py +src/transformers/models/blenderbot_small/configuration_blenderbot_small.py +src/transformers/models/blenderbot_small/modeling_blenderbot_small.py +src/transformers/models/blenderbot_small/modeling_flax_blenderbot_small.py +src/transformers/models/blenderbot_small/modeling_tf_blenderbot_small.py +src/transformers/models/blenderbot_small/tokenization_blenderbot_small.py +src/transformers/models/blenderbot_small/tokenization_blenderbot_small_fast.py +src/transformers/models/blip/__init__.py +src/transformers/models/blip/configuration_blip.py +src/transformers/models/blip/convert_blip_original_pytorch_to_hf.py +src/transformers/models/blip/image_processing_blip.py +src/transformers/models/blip/modeling_blip.py +src/transformers/models/blip/modeling_blip_text.py +src/transformers/models/blip/processing_blip.py +src/transformers/models/blip_2/__init__.py +src/transformers/models/blip_2/configuration_blip_2.py +src/transformers/models/blip_2/convert_blip_2_original_to_pytorch.py +src/transformers/models/blip_2/modeling_blip_2.py +src/transformers/models/blip_2/processing_blip_2.py +src/transformers/models/bloom/__init__.py +src/transformers/models/bloom/configuration_bloom.py +src/transformers/models/bloom/convert_bloom_original_checkpoint_to_pytorch.py +src/transformers/models/bloom/modeling_bloom.py +src/transformers/models/bloom/tokenization_bloom_fast.py +src/transformers/models/bort/__init__.py +src/transformers/models/bort/convert_bort_original_gluonnlp_checkpoint_to_pytorch.py +src/transformers/models/bridgetower/__init__.py +src/transformers/models/bridgetower/configuration_bridgetower.py +src/transformers/models/bridgetower/image_processing_bridgetower.py +src/transformers/models/bridgetower/modeling_bridgetower.py +src/transformers/models/bridgetower/processing_bridgetower.py +src/transformers/models/byt5/__init__.py +src/transformers/models/byt5/convert_byt5_original_tf_checkpoint_to_pytorch.py +src/transformers/models/byt5/tokenization_byt5.py +src/transformers/models/camembert/__init__.py +src/transformers/models/camembert/configuration_camembert.py +src/transformers/models/camembert/modeling_camembert.py +src/transformers/models/camembert/modeling_tf_camembert.py +src/transformers/models/camembert/tokenization_camembert.py +src/transformers/models/camembert/tokenization_camembert_fast.py +src/transformers/models/canine/__init__.py +src/transformers/models/canine/configuration_canine.py +src/transformers/models/canine/convert_canine_original_tf_checkpoint_to_pytorch.py +src/transformers/models/canine/modeling_canine.py +src/transformers/models/canine/tokenization_canine.py +src/transformers/models/chinese_clip/__init__.py +src/transformers/models/chinese_clip/configuration_chinese_clip.py +src/transformers/models/chinese_clip/convert_chinese_clip_original_pytorch_to_hf.py +src/transformers/models/chinese_clip/feature_extraction_chinese_clip.py +src/transformers/models/chinese_clip/image_processing_chinese_clip.py +src/transformers/models/chinese_clip/modeling_chinese_clip.py +src/transformers/models/chinese_clip/processing_chinese_clip.py +src/transformers/models/clap/__init__.py +src/transformers/models/clap/configuration_clap.py +src/transformers/models/clap/convert_clap_original_pytorch_to_hf.py +src/transformers/models/clap/feature_extraction_clap.py +src/transformers/models/clap/modeling_clap.py +src/transformers/models/clap/processing_clap.py +src/transformers/models/clip/__init__.py +src/transformers/models/clip/configuration_clip.py +src/transformers/models/clip/convert_clip_original_pytorch_to_hf.py +src/transformers/models/clip/feature_extraction_clip.py +src/transformers/models/clip/image_processing_clip.py +src/transformers/models/clip/modeling_clip.py +src/transformers/models/clip/modeling_flax_clip.py +src/transformers/models/clip/modeling_tf_clip.py +src/transformers/models/clip/processing_clip.py +src/transformers/models/clip/tokenization_clip.py +src/transformers/models/clip/tokenization_clip_fast.py +src/transformers/models/clipseg/__init__.py +src/transformers/models/clipseg/configuration_clipseg.py +src/transformers/models/clipseg/convert_clipseg_original_pytorch_to_hf.py +src/transformers/models/clipseg/modeling_clipseg.py +src/transformers/models/clipseg/processing_clipseg.py +src/transformers/models/codegen/__init__.py +src/transformers/models/codegen/configuration_codegen.py +src/transformers/models/codegen/modeling_codegen.py +src/transformers/models/codegen/tokenization_codegen.py +src/transformers/models/codegen/tokenization_codegen_fast.py +src/transformers/models/conditional_detr/__init__.py +src/transformers/models/conditional_detr/configuration_conditional_detr.py +src/transformers/models/conditional_detr/convert_conditional_detr_original_pytorch_checkpoint_to_pytorch.py +src/transformers/models/conditional_detr/feature_extraction_conditional_detr.py +src/transformers/models/conditional_detr/image_processing_conditional_detr.py +src/transformers/models/conditional_detr/modeling_conditional_detr.py +src/transformers/models/convbert/__init__.py +src/transformers/models/convbert/configuration_convbert.py +src/transformers/models/convbert/convert_convbert_original_tf1_checkpoint_to_pytorch_and_tf2.py +src/transformers/models/convbert/modeling_convbert.py +src/transformers/models/convbert/modeling_tf_convbert.py +src/transformers/models/convbert/tokenization_convbert.py +src/transformers/models/convbert/tokenization_convbert_fast.py +src/transformers/models/convnext/__init__.py +src/transformers/models/convnext/configuration_convnext.py +src/transformers/models/convnext/convert_convnext_to_pytorch.py +src/transformers/models/convnext/feature_extraction_convnext.py +src/transformers/models/convnext/image_processing_convnext.py +src/transformers/models/convnext/modeling_convnext.py +src/transformers/models/convnext/modeling_tf_convnext.py +src/transformers/models/convnextv2/__init__.py +src/transformers/models/convnextv2/configuration_convnextv2.py +src/transformers/models/convnextv2/convert_convnextv2_to_pytorch.py +src/transformers/models/convnextv2/modeling_convnextv2.py +src/transformers/models/cpm/__init__.py +src/transformers/models/cpm/tokenization_cpm.py +src/transformers/models/cpm/tokenization_cpm_fast.py +src/transformers/models/ctrl/__init__.py +src/transformers/models/ctrl/configuration_ctrl.py +src/transformers/models/ctrl/modeling_ctrl.py +src/transformers/models/ctrl/modeling_tf_ctrl.py +src/transformers/models/ctrl/tokenization_ctrl.py +src/transformers/models/cvt/__init__.py +src/transformers/models/cvt/configuration_cvt.py +src/transformers/models/cvt/convert_cvt_original_pytorch_checkpoint_to_pytorch.py +src/transformers/models/cvt/modeling_cvt.py +src/transformers/models/cvt/modeling_tf_cvt.py +src/transformers/models/data2vec/__init__.py +src/transformers/models/data2vec/configuration_data2vec_audio.py +src/transformers/models/data2vec/configuration_data2vec_text.py +src/transformers/models/data2vec/configuration_data2vec_vision.py +src/transformers/models/data2vec/convert_data2vec_audio_original_pytorch_checkpoint_to_pytorch.py +src/transformers/models/data2vec/convert_data2vec_text_original_pytorch_checkpoint_to_pytorch.py +src/transformers/models/data2vec/convert_data2vec_vision_original_pytorch_checkpoint_to_pytorch.py +src/transformers/models/data2vec/modeling_data2vec_audio.py +src/transformers/models/data2vec/modeling_data2vec_text.py +src/transformers/models/data2vec/modeling_data2vec_vision.py +src/transformers/models/data2vec/modeling_tf_data2vec_vision.py +src/transformers/models/deberta/__init__.py +src/transformers/models/deberta/configuration_deberta.py +src/transformers/models/deberta/modeling_deberta.py +src/transformers/models/deberta/modeling_tf_deberta.py +src/transformers/models/deberta/tokenization_deberta.py +src/transformers/models/deberta/tokenization_deberta_fast.py +src/transformers/models/deberta_v2/__init__.py +src/transformers/models/deberta_v2/configuration_deberta_v2.py +src/transformers/models/deberta_v2/modeling_deberta_v2.py +src/transformers/models/deberta_v2/modeling_tf_deberta_v2.py +src/transformers/models/deberta_v2/tokenization_deberta_v2.py +src/transformers/models/deberta_v2/tokenization_deberta_v2_fast.py +src/transformers/models/decision_transformer/__init__.py +src/transformers/models/decision_transformer/configuration_decision_transformer.py +src/transformers/models/decision_transformer/modeling_decision_transformer.py +src/transformers/models/deformable_detr/__init__.py +src/transformers/models/deformable_detr/configuration_deformable_detr.py +src/transformers/models/deformable_detr/convert_deformable_detr_to_pytorch.py +src/transformers/models/deformable_detr/feature_extraction_deformable_detr.py +src/transformers/models/deformable_detr/image_processing_deformable_detr.py +src/transformers/models/deformable_detr/load_custom.py +src/transformers/models/deformable_detr/modeling_deformable_detr.py +src/transformers/models/deit/__init__.py +src/transformers/models/deit/configuration_deit.py +src/transformers/models/deit/convert_deit_timm_to_pytorch.py +src/transformers/models/deit/feature_extraction_deit.py +src/transformers/models/deit/image_processing_deit.py +src/transformers/models/deit/modeling_deit.py +src/transformers/models/deit/modeling_tf_deit.py +src/transformers/models/deta/__init__.py +src/transformers/models/deta/configuration_deta.py +src/transformers/models/deta/convert_deta_resnet_to_pytorch.py +src/transformers/models/deta/convert_deta_swin_to_pytorch.py +src/transformers/models/deta/image_processing_deta.py +src/transformers/models/deta/modeling_deta.py +src/transformers/models/detr/__init__.py +src/transformers/models/detr/configuration_detr.py +src/transformers/models/detr/convert_detr_original_pytorch_checkpoint_to_pytorch.py +src/transformers/models/detr/convert_detr_to_pytorch.py +src/transformers/models/detr/feature_extraction_detr.py +src/transformers/models/detr/image_processing_detr.py +src/transformers/models/detr/modeling_detr.py +src/transformers/models/dialogpt/__init__.py +src/transformers/models/dialogpt/convert_dialogpt_original_pytorch_checkpoint_to_pytorch.py +src/transformers/models/dinat/__init__.py +src/transformers/models/dinat/configuration_dinat.py +src/transformers/models/dinat/modeling_dinat.py +src/transformers/models/distilbert/__init__.py +src/transformers/models/distilbert/configuration_distilbert.py +src/transformers/models/distilbert/modeling_distilbert.py +src/transformers/models/distilbert/modeling_flax_distilbert.py +src/transformers/models/distilbert/modeling_tf_distilbert.py +src/transformers/models/distilbert/tokenization_distilbert.py +src/transformers/models/distilbert/tokenization_distilbert_fast.py +src/transformers/models/dit/__init__.py +src/transformers/models/dit/convert_dit_unilm_to_pytorch.py +src/transformers/models/donut/__init__.py +src/transformers/models/donut/configuration_donut_swin.py +src/transformers/models/donut/convert_donut_to_pytorch.py +src/transformers/models/donut/feature_extraction_donut.py +src/transformers/models/donut/image_processing_donut.py +src/transformers/models/donut/modeling_donut_swin.py +src/transformers/models/donut/processing_donut.py +src/transformers/models/dpr/__init__.py +src/transformers/models/dpr/configuration_dpr.py +src/transformers/models/dpr/convert_dpr_original_checkpoint_to_pytorch.py +src/transformers/models/dpr/modeling_dpr.py +src/transformers/models/dpr/modeling_tf_dpr.py +src/transformers/models/dpr/tokenization_dpr.py +src/transformers/models/dpr/tokenization_dpr_fast.py +src/transformers/models/dpt/__init__.py +src/transformers/models/dpt/configuration_dpt.py +src/transformers/models/dpt/convert_dpt_hybrid_to_pytorch.py +src/transformers/models/dpt/convert_dpt_to_pytorch.py +src/transformers/models/dpt/feature_extraction_dpt.py +src/transformers/models/dpt/image_processing_dpt.py +src/transformers/models/dpt/modeling_dpt.py +src/transformers/models/efficientformer/__init__.py +src/transformers/models/efficientformer/configuration_efficientformer.py +src/transformers/models/efficientformer/convert_efficientformer_original_pytorch_checkpoint_to_pytorch.py +src/transformers/models/efficientformer/image_processing_efficientformer.py +src/transformers/models/efficientformer/modeling_efficientformer.py +src/transformers/models/efficientnet/__init__.py +src/transformers/models/efficientnet/configuration_efficientnet.py +src/transformers/models/efficientnet/convert_efficientnet_to_pytorch.py +src/transformers/models/efficientnet/image_processing_efficientnet.py +src/transformers/models/efficientnet/modeling_efficientnet.py +src/transformers/models/electra/__init__.py +src/transformers/models/electra/configuration_electra.py +src/transformers/models/electra/convert_electra_original_tf_checkpoint_to_pytorch.py +src/transformers/models/electra/modeling_electra.py +src/transformers/models/electra/modeling_flax_electra.py +src/transformers/models/electra/modeling_tf_electra.py +src/transformers/models/electra/tokenization_electra.py +src/transformers/models/electra/tokenization_electra_fast.py +src/transformers/models/encoder_decoder/__init__.py +src/transformers/models/encoder_decoder/configuration_encoder_decoder.py +src/transformers/models/encoder_decoder/modeling_encoder_decoder.py +src/transformers/models/encoder_decoder/modeling_flax_encoder_decoder.py +src/transformers/models/encoder_decoder/modeling_tf_encoder_decoder.py +src/transformers/models/ernie/__init__.py +src/transformers/models/ernie/configuration_ernie.py +src/transformers/models/ernie/modeling_ernie.py +src/transformers/models/ernie_m/__init__.py +src/transformers/models/ernie_m/configuration_ernie_m.py +src/transformers/models/ernie_m/modeling_ernie_m.py +src/transformers/models/ernie_m/tokenization_ernie_m.py +src/transformers/models/esm/__init__.py +src/transformers/models/esm/configuration_esm.py +src/transformers/models/esm/convert_esm.py +src/transformers/models/esm/modeling_esm.py +src/transformers/models/esm/modeling_esmfold.py +src/transformers/models/esm/modeling_tf_esm.py +src/transformers/models/esm/tokenization_esm.py +src/transformers/models/esm/openfold_utils/__init__.py +src/transformers/models/esm/openfold_utils/chunk_utils.py +src/transformers/models/esm/openfold_utils/data_transforms.py +src/transformers/models/esm/openfold_utils/feats.py +src/transformers/models/esm/openfold_utils/loss.py +src/transformers/models/esm/openfold_utils/protein.py +src/transformers/models/esm/openfold_utils/residue_constants.py +src/transformers/models/esm/openfold_utils/rigid_utils.py +src/transformers/models/esm/openfold_utils/tensor_utils.py +src/transformers/models/flaubert/__init__.py +src/transformers/models/flaubert/configuration_flaubert.py +src/transformers/models/flaubert/modeling_flaubert.py +src/transformers/models/flaubert/modeling_tf_flaubert.py +src/transformers/models/flaubert/tokenization_flaubert.py +src/transformers/models/flava/__init__.py +src/transformers/models/flava/configuration_flava.py +src/transformers/models/flava/convert_dalle_to_flava_codebook.py +src/transformers/models/flava/convert_flava_original_pytorch_to_hf.py +src/transformers/models/flava/feature_extraction_flava.py +src/transformers/models/flava/image_processing_flava.py +src/transformers/models/flava/modeling_flava.py +src/transformers/models/flava/processing_flava.py +src/transformers/models/fnet/__init__.py +src/transformers/models/fnet/configuration_fnet.py +src/transformers/models/fnet/convert_fnet_original_flax_checkpoint_to_pytorch.py +src/transformers/models/fnet/modeling_fnet.py +src/transformers/models/fnet/tokenization_fnet.py +src/transformers/models/fnet/tokenization_fnet_fast.py +src/transformers/models/fsmt/__init__.py +src/transformers/models/fsmt/configuration_fsmt.py +src/transformers/models/fsmt/convert_fsmt_original_pytorch_checkpoint_to_pytorch.py +src/transformers/models/fsmt/modeling_fsmt.py +src/transformers/models/fsmt/tokenization_fsmt.py +src/transformers/models/funnel/__init__.py +src/transformers/models/funnel/configuration_funnel.py +src/transformers/models/funnel/convert_funnel_original_tf_checkpoint_to_pytorch.py +src/transformers/models/funnel/modeling_funnel.py +src/transformers/models/funnel/modeling_tf_funnel.py +src/transformers/models/funnel/tokenization_funnel.py +src/transformers/models/funnel/tokenization_funnel_fast.py +src/transformers/models/git/__init__.py +src/transformers/models/git/configuration_git.py +src/transformers/models/git/convert_git_to_pytorch.py +src/transformers/models/git/modeling_git.py +src/transformers/models/git/processing_git.py +src/transformers/models/glpn/__init__.py +src/transformers/models/glpn/configuration_glpn.py +src/transformers/models/glpn/convert_glpn_to_pytorch.py +src/transformers/models/glpn/feature_extraction_glpn.py +src/transformers/models/glpn/image_processing_glpn.py +src/transformers/models/glpn/modeling_glpn.py +src/transformers/models/gpt2/__init__.py +src/transformers/models/gpt2/configuration_gpt2.py +src/transformers/models/gpt2/convert_gpt2_original_tf_checkpoint_to_pytorch.py +src/transformers/models/gpt2/modeling_flax_gpt2.py +src/transformers/models/gpt2/modeling_gpt2.py +src/transformers/models/gpt2/modeling_tf_gpt2.py +src/transformers/models/gpt2/tokenization_gpt2.py +src/transformers/models/gpt2/tokenization_gpt2_fast.py +src/transformers/models/gpt2/tokenization_gpt2_tf.py +src/transformers/models/gpt_neo/__init__.py +src/transformers/models/gpt_neo/configuration_gpt_neo.py +src/transformers/models/gpt_neo/convert_gpt_neo_mesh_tf_to_pytorch.py +src/transformers/models/gpt_neo/modeling_flax_gpt_neo.py +src/transformers/models/gpt_neo/modeling_gpt_neo.py +src/transformers/models/gpt_neox/__init__.py +src/transformers/models/gpt_neox/configuration_gpt_neox.py +src/transformers/models/gpt_neox/modeling_gpt_neox.py +src/transformers/models/gpt_neox/tokenization_gpt_neox_fast.py +src/transformers/models/gpt_neox_japanese/__init__.py +src/transformers/models/gpt_neox_japanese/configuration_gpt_neox_japanese.py +src/transformers/models/gpt_neox_japanese/modeling_gpt_neox_japanese.py +src/transformers/models/gpt_neox_japanese/tokenization_gpt_neox_japanese.py +src/transformers/models/gpt_sw3/__init__.py +src/transformers/models/gpt_sw3/convert_megatron_to_pytorch.py +src/transformers/models/gpt_sw3/tokenization_gpt_sw3.py +src/transformers/models/gptj/__init__.py +src/transformers/models/gptj/configuration_gptj.py +src/transformers/models/gptj/modeling_flax_gptj.py +src/transformers/models/gptj/modeling_gptj.py +src/transformers/models/gptj/modeling_tf_gptj.py +src/transformers/models/gptsan_japanese/__init__.py +src/transformers/models/gptsan_japanese/configuration_gptsan_japanese.py +src/transformers/models/gptsan_japanese/convert_gptsan_tf_checkpoint_to_pytorch.py +src/transformers/models/gptsan_japanese/modeling_gptsan_japanese.py +src/transformers/models/gptsan_japanese/tokenization_gptsan_japanese.py +src/transformers/models/graphormer/__init__.py +src/transformers/models/graphormer/collating_graphormer.py +src/transformers/models/graphormer/configuration_graphormer.py +src/transformers/models/graphormer/modeling_graphormer.py +src/transformers/models/groupvit/__init__.py +src/transformers/models/groupvit/configuration_groupvit.py +src/transformers/models/groupvit/convert_groupvit_nvlab_to_hf.py +src/transformers/models/groupvit/modeling_groupvit.py +src/transformers/models/groupvit/modeling_tf_groupvit.py +src/transformers/models/herbert/__init__.py +src/transformers/models/herbert/tokenization_herbert.py +src/transformers/models/herbert/tokenization_herbert_fast.py +src/transformers/models/hubert/__init__.py +src/transformers/models/hubert/configuration_hubert.py +src/transformers/models/hubert/convert_distilhubert_original_s3prl_checkpoint_to_pytorch.py +src/transformers/models/hubert/convert_hubert_original_pytorch_checkpoint_to_pytorch.py +src/transformers/models/hubert/convert_hubert_original_s3prl_checkpoint_to_pytorch.py +src/transformers/models/hubert/modeling_hubert.py +src/transformers/models/hubert/modeling_tf_hubert.py +src/transformers/models/ibert/__init__.py +src/transformers/models/ibert/configuration_ibert.py +src/transformers/models/ibert/modeling_ibert.py +src/transformers/models/ibert/quant_modules.py +src/transformers/models/imagegpt/__init__.py +src/transformers/models/imagegpt/configuration_imagegpt.py +src/transformers/models/imagegpt/convert_imagegpt_original_tf2_to_pytorch.py +src/transformers/models/imagegpt/feature_extraction_imagegpt.py +src/transformers/models/imagegpt/image_processing_imagegpt.py +src/transformers/models/imagegpt/modeling_imagegpt.py +src/transformers/models/informer/__init__.py +src/transformers/models/informer/configuration_informer.py +src/transformers/models/informer/modeling_informer.py +src/transformers/models/jukebox/__init__.py +src/transformers/models/jukebox/configuration_jukebox.py +src/transformers/models/jukebox/convert_jukebox.py +src/transformers/models/jukebox/modeling_jukebox.py +src/transformers/models/jukebox/tokenization_jukebox.py +src/transformers/models/layoutlm/__init__.py +src/transformers/models/layoutlm/configuration_layoutlm.py +src/transformers/models/layoutlm/modeling_layoutlm.py +src/transformers/models/layoutlm/modeling_tf_layoutlm.py +src/transformers/models/layoutlm/tokenization_layoutlm.py +src/transformers/models/layoutlm/tokenization_layoutlm_fast.py +src/transformers/models/layoutlmv2/__init__.py +src/transformers/models/layoutlmv2/configuration_layoutlmv2.py +src/transformers/models/layoutlmv2/feature_extraction_layoutlmv2.py +src/transformers/models/layoutlmv2/image_processing_layoutlmv2.py +src/transformers/models/layoutlmv2/modeling_layoutlmv2.py +src/transformers/models/layoutlmv2/processing_layoutlmv2.py +src/transformers/models/layoutlmv2/tokenization_layoutlmv2.py +src/transformers/models/layoutlmv2/tokenization_layoutlmv2_fast.py +src/transformers/models/layoutlmv3/__init__.py +src/transformers/models/layoutlmv3/configuration_layoutlmv3.py +src/transformers/models/layoutlmv3/feature_extraction_layoutlmv3.py +src/transformers/models/layoutlmv3/image_processing_layoutlmv3.py +src/transformers/models/layoutlmv3/modeling_layoutlmv3.py +src/transformers/models/layoutlmv3/modeling_tf_layoutlmv3.py +src/transformers/models/layoutlmv3/processing_layoutlmv3.py +src/transformers/models/layoutlmv3/tokenization_layoutlmv3.py +src/transformers/models/layoutlmv3/tokenization_layoutlmv3_fast.py +src/transformers/models/layoutxlm/__init__.py +src/transformers/models/layoutxlm/processing_layoutxlm.py +src/transformers/models/layoutxlm/tokenization_layoutxlm.py +src/transformers/models/layoutxlm/tokenization_layoutxlm_fast.py +src/transformers/models/led/__init__.py +src/transformers/models/led/configuration_led.py +src/transformers/models/led/modeling_led.py +src/transformers/models/led/modeling_tf_led.py +src/transformers/models/led/tokenization_led.py +src/transformers/models/led/tokenization_led_fast.py +src/transformers/models/levit/__init__.py +src/transformers/models/levit/configuration_levit.py +src/transformers/models/levit/convert_levit_timm_to_pytorch.py +src/transformers/models/levit/feature_extraction_levit.py +src/transformers/models/levit/image_processing_levit.py +src/transformers/models/levit/modeling_levit.py +src/transformers/models/lilt/__init__.py +src/transformers/models/lilt/configuration_lilt.py +src/transformers/models/lilt/modeling_lilt.py +src/transformers/models/llama/Qformer.py +src/transformers/models/llama/Qformer_lion.py +src/transformers/models/llama/__init__.py +src/transformers/models/llama/cavmae.py +src/transformers/models/llama/cavmae_back.py +src/transformers/models/llama/configuration_llama.py +src/transformers/models/llama/convert_llama_weights_to_hf.py +src/transformers/models/llama/feature_fusion.py +src/transformers/models/llama/htsat.py +src/transformers/models/llama/modeling_llama.py +src/transformers/models/llama/pos_embed.py +src/transformers/models/llama/tokenization_llama.py +src/transformers/models/llama_old/__init__.py +src/transformers/models/llama_old/configuration_llama.py +src/transformers/models/llama_old/convert_llama_weights_to_hf.py +src/transformers/models/llama_old/modeling_llama.py +src/transformers/models/llama_old/tokenization_llama.py +src/transformers/models/longformer/__init__.py +src/transformers/models/longformer/configuration_longformer.py +src/transformers/models/longformer/convert_longformer_original_pytorch_lightning_to_pytorch.py +src/transformers/models/longformer/modeling_longformer.py +src/transformers/models/longformer/modeling_tf_longformer.py +src/transformers/models/longformer/tokenization_longformer.py +src/transformers/models/longformer/tokenization_longformer_fast.py +src/transformers/models/longt5/__init__.py +src/transformers/models/longt5/configuration_longt5.py +src/transformers/models/longt5/convert_longt5x_checkpoint_to_flax.py +src/transformers/models/longt5/modeling_flax_longt5.py +src/transformers/models/longt5/modeling_longt5.py +src/transformers/models/luke/__init__.py +src/transformers/models/luke/configuration_luke.py +src/transformers/models/luke/convert_luke_original_pytorch_checkpoint_to_pytorch.py +src/transformers/models/luke/modeling_luke.py +src/transformers/models/luke/tokenization_luke.py +src/transformers/models/lxmert/__init__.py +src/transformers/models/lxmert/configuration_lxmert.py +src/transformers/models/lxmert/convert_lxmert_original_tf_checkpoint_to_pytorch.py +src/transformers/models/lxmert/modeling_lxmert.py +src/transformers/models/lxmert/modeling_tf_lxmert.py +src/transformers/models/lxmert/tokenization_lxmert.py +src/transformers/models/lxmert/tokenization_lxmert_fast.py +src/transformers/models/m2m_100/__init__.py +src/transformers/models/m2m_100/configuration_m2m_100.py +src/transformers/models/m2m_100/convert_m2m100_original_checkpoint_to_pytorch.py +src/transformers/models/m2m_100/modeling_m2m_100.py +src/transformers/models/m2m_100/tokenization_m2m_100.py +src/transformers/models/marian/__init__.py +src/transformers/models/marian/configuration_marian.py +src/transformers/models/marian/convert_marian_tatoeba_to_pytorch.py +src/transformers/models/marian/convert_marian_to_pytorch.py +src/transformers/models/marian/modeling_flax_marian.py +src/transformers/models/marian/modeling_marian.py +src/transformers/models/marian/modeling_tf_marian.py +src/transformers/models/marian/tokenization_marian.py +src/transformers/models/markuplm/__init__.py +src/transformers/models/markuplm/configuration_markuplm.py +src/transformers/models/markuplm/feature_extraction_markuplm.py +src/transformers/models/markuplm/modeling_markuplm.py +src/transformers/models/markuplm/processing_markuplm.py +src/transformers/models/markuplm/tokenization_markuplm.py +src/transformers/models/markuplm/tokenization_markuplm_fast.py +src/transformers/models/mask2former/__init__.py +src/transformers/models/mask2former/configuration_mask2former.py +src/transformers/models/mask2former/convert_mask2former_original_pytorch_checkpoint_to_pytorch.py +src/transformers/models/mask2former/image_processing_mask2former.py +src/transformers/models/mask2former/modeling_mask2former.py +src/transformers/models/maskformer/__init__.py +src/transformers/models/maskformer/configuration_maskformer.py +src/transformers/models/maskformer/configuration_maskformer_swin.py +src/transformers/models/maskformer/convert_maskformer_original_pytorch_checkpoint_to_pytorch.py +src/transformers/models/maskformer/convert_maskformer_resnet_to_pytorch.py +src/transformers/models/maskformer/convert_maskformer_swin_to_pytorch.py +src/transformers/models/maskformer/feature_extraction_maskformer.py +src/transformers/models/maskformer/image_processing_maskformer.py +src/transformers/models/maskformer/modeling_maskformer.py +src/transformers/models/maskformer/modeling_maskformer_swin.py +src/transformers/models/mbart/__init__.py +src/transformers/models/mbart/configuration_mbart.py +src/transformers/models/mbart/convert_mbart_original_checkpoint_to_pytorch.py +src/transformers/models/mbart/modeling_flax_mbart.py +src/transformers/models/mbart/modeling_mbart.py +src/transformers/models/mbart/modeling_tf_mbart.py +src/transformers/models/mbart/tokenization_mbart.py +src/transformers/models/mbart/tokenization_mbart_fast.py +src/transformers/models/mbart50/__init__.py +src/transformers/models/mbart50/tokenization_mbart50.py +src/transformers/models/mbart50/tokenization_mbart50_fast.py +src/transformers/models/mctct/__init__.py +src/transformers/models/mctct/configuration_mctct.py +src/transformers/models/mctct/feature_extraction_mctct.py +src/transformers/models/mctct/modeling_mctct.py +src/transformers/models/mctct/processing_mctct.py +src/transformers/models/mega/__init__.py +src/transformers/models/mega/configuration_mega.py +src/transformers/models/mega/convert_mega_original_pytorch_checkpoint_to_pytorch.py +src/transformers/models/mega/modeling_mega.py +src/transformers/models/megatron_bert/__init__.py +src/transformers/models/megatron_bert/configuration_megatron_bert.py +src/transformers/models/megatron_bert/convert_megatron_bert_checkpoint.py +src/transformers/models/megatron_bert/modeling_megatron_bert.py +src/transformers/models/megatron_gpt2/__init__.py +src/transformers/models/megatron_gpt2/checkpoint_reshaping_and_interoperability.py +src/transformers/models/megatron_gpt2/convert_megatron_gpt2_checkpoint.py +src/transformers/models/mgp_str/__init__.py +src/transformers/models/mgp_str/configuration_mgp_str.py +src/transformers/models/mgp_str/modeling_mgp_str.py +src/transformers/models/mgp_str/processing_mgp_str.py +src/transformers/models/mgp_str/tokenization_mgp_str.py +src/transformers/models/mluke/__init__.py +src/transformers/models/mluke/convert_mluke_original_pytorch_checkpoint_to_pytorch.py +src/transformers/models/mluke/tokenization_mluke.py +src/transformers/models/mmbt/__init__.py +src/transformers/models/mmbt/configuration_mmbt.py +src/transformers/models/mmbt/modeling_mmbt.py +src/transformers/models/mobilebert/__init__.py +src/transformers/models/mobilebert/configuration_mobilebert.py +src/transformers/models/mobilebert/convert_mobilebert_original_tf_checkpoint_to_pytorch.py +src/transformers/models/mobilebert/modeling_mobilebert.py +src/transformers/models/mobilebert/modeling_tf_mobilebert.py +src/transformers/models/mobilebert/tokenization_mobilebert.py +src/transformers/models/mobilebert/tokenization_mobilebert_fast.py +src/transformers/models/mobilenet_v1/__init__.py +src/transformers/models/mobilenet_v1/configuration_mobilenet_v1.py +src/transformers/models/mobilenet_v1/convert_original_tf_checkpoint_to_pytorch.py +src/transformers/models/mobilenet_v1/feature_extraction_mobilenet_v1.py +src/transformers/models/mobilenet_v1/image_processing_mobilenet_v1.py +src/transformers/models/mobilenet_v1/modeling_mobilenet_v1.py +src/transformers/models/mobilenet_v2/__init__.py +src/transformers/models/mobilenet_v2/configuration_mobilenet_v2.py +src/transformers/models/mobilenet_v2/convert_original_tf_checkpoint_to_pytorch.py +src/transformers/models/mobilenet_v2/feature_extraction_mobilenet_v2.py +src/transformers/models/mobilenet_v2/image_processing_mobilenet_v2.py +src/transformers/models/mobilenet_v2/modeling_mobilenet_v2.py +src/transformers/models/mobilevit/__init__.py +src/transformers/models/mobilevit/configuration_mobilevit.py +src/transformers/models/mobilevit/convert_mlcvnets_to_pytorch.py +src/transformers/models/mobilevit/feature_extraction_mobilevit.py +src/transformers/models/mobilevit/image_processing_mobilevit.py +src/transformers/models/mobilevit/modeling_mobilevit.py +src/transformers/models/mobilevit/modeling_tf_mobilevit.py +src/transformers/models/mpnet/__init__.py +src/transformers/models/mpnet/configuration_mpnet.py +src/transformers/models/mpnet/modeling_mpnet.py +src/transformers/models/mpnet/modeling_tf_mpnet.py +src/transformers/models/mpnet/tokenization_mpnet.py +src/transformers/models/mpnet/tokenization_mpnet_fast.py +src/transformers/models/mt5/__init__.py +src/transformers/models/mt5/configuration_mt5.py +src/transformers/models/mt5/modeling_flax_mt5.py +src/transformers/models/mt5/modeling_mt5.py +src/transformers/models/mt5/modeling_tf_mt5.py +src/transformers/models/mvp/__init__.py +src/transformers/models/mvp/configuration_mvp.py +src/transformers/models/mvp/modeling_mvp.py +src/transformers/models/mvp/tokenization_mvp.py +src/transformers/models/mvp/tokenization_mvp_fast.py +src/transformers/models/nat/__init__.py +src/transformers/models/nat/configuration_nat.py +src/transformers/models/nat/modeling_nat.py +src/transformers/models/nezha/__init__.py +src/transformers/models/nezha/configuration_nezha.py +src/transformers/models/nezha/modeling_nezha.py +src/transformers/models/nllb/__init__.py +src/transformers/models/nllb/tokenization_nllb.py +src/transformers/models/nllb/tokenization_nllb_fast.py +src/transformers/models/nllb_moe/__init__.py +src/transformers/models/nllb_moe/configuration_nllb_moe.py +src/transformers/models/nllb_moe/convert_nllb_moe_sharded_original_checkpoint_to_pytorch.py +src/transformers/models/nllb_moe/modeling_nllb_moe.py +src/transformers/models/nystromformer/__init__.py +src/transformers/models/nystromformer/configuration_nystromformer.py +src/transformers/models/nystromformer/convert_nystromformer_original_pytorch_checkpoint_to_pytorch.py +src/transformers/models/nystromformer/modeling_nystromformer.py +src/transformers/models/oneformer/__init__.py +src/transformers/models/oneformer/configuration_oneformer.py +src/transformers/models/oneformer/convert_to_hf_oneformer.py +src/transformers/models/oneformer/image_processing_oneformer.py +src/transformers/models/oneformer/modeling_oneformer.py +src/transformers/models/oneformer/processing_oneformer.py +src/transformers/models/openai/__init__.py +src/transformers/models/openai/configuration_openai.py +src/transformers/models/openai/convert_openai_original_tf_checkpoint_to_pytorch.py +src/transformers/models/openai/modeling_openai.py +src/transformers/models/openai/modeling_tf_openai.py +src/transformers/models/openai/tokenization_openai.py +src/transformers/models/openai/tokenization_openai_fast.py +src/transformers/models/opt/__init__.py +src/transformers/models/opt/configuration_opt.py +src/transformers/models/opt/convert_opt_original_pytorch_checkpoint_to_pytorch.py +src/transformers/models/opt/modeling_flax_opt.py +src/transformers/models/opt/modeling_opt.py +src/transformers/models/opt/modeling_tf_opt.py +src/transformers/models/owlvit/__init__.py +src/transformers/models/owlvit/configuration_owlvit.py +src/transformers/models/owlvit/convert_owlvit_original_flax_to_hf.py +src/transformers/models/owlvit/feature_extraction_owlvit.py +src/transformers/models/owlvit/image_processing_owlvit.py +src/transformers/models/owlvit/modeling_owlvit.py +src/transformers/models/owlvit/processing_owlvit.py +src/transformers/models/pegasus/__init__.py +src/transformers/models/pegasus/configuration_pegasus.py +src/transformers/models/pegasus/convert_pegasus_tf_to_pytorch.py +src/transformers/models/pegasus/modeling_flax_pegasus.py +src/transformers/models/pegasus/modeling_pegasus.py +src/transformers/models/pegasus/modeling_tf_pegasus.py +src/transformers/models/pegasus/tokenization_pegasus.py +src/transformers/models/pegasus/tokenization_pegasus_fast.py +src/transformers/models/pegasus_x/__init__.py +src/transformers/models/pegasus_x/configuration_pegasus_x.py +src/transformers/models/pegasus_x/modeling_pegasus_x.py +src/transformers/models/perceiver/__init__.py +src/transformers/models/perceiver/configuration_perceiver.py +src/transformers/models/perceiver/convert_perceiver_haiku_to_pytorch.py +src/transformers/models/perceiver/feature_extraction_perceiver.py +src/transformers/models/perceiver/image_processing_perceiver.py +src/transformers/models/perceiver/modeling_perceiver.py +src/transformers/models/perceiver/tokenization_perceiver.py +src/transformers/models/phobert/__init__.py +src/transformers/models/phobert/tokenization_phobert.py +src/transformers/models/pix2struct/__init__.py +src/transformers/models/pix2struct/configuration_pix2struct.py +src/transformers/models/pix2struct/convert_pix2struct_original_pytorch_to_hf.py +src/transformers/models/pix2struct/image_processing_pix2struct.py +src/transformers/models/pix2struct/modeling_pix2struct.py +src/transformers/models/pix2struct/processing_pix2struct.py +src/transformers/models/plbart/__init__.py +src/transformers/models/plbart/configuration_plbart.py +src/transformers/models/plbart/convert_plbart_original_checkpoint_to_torch.py +src/transformers/models/plbart/modeling_plbart.py +src/transformers/models/plbart/tokenization_plbart.py +src/transformers/models/poolformer/__init__.py +src/transformers/models/poolformer/configuration_poolformer.py +src/transformers/models/poolformer/convert_poolformer_original_to_pytorch.py +src/transformers/models/poolformer/feature_extraction_poolformer.py +src/transformers/models/poolformer/image_processing_poolformer.py +src/transformers/models/poolformer/modeling_poolformer.py +src/transformers/models/prophetnet/__init__.py +src/transformers/models/prophetnet/configuration_prophetnet.py +src/transformers/models/prophetnet/convert_prophetnet_original_pytorch_checkpoint_to_pytorch.py +src/transformers/models/prophetnet/modeling_prophetnet.py +src/transformers/models/prophetnet/tokenization_prophetnet.py +src/transformers/models/qdqbert/__init__.py +src/transformers/models/qdqbert/configuration_qdqbert.py +src/transformers/models/qdqbert/modeling_qdqbert.py +src/transformers/models/rag/__init__.py +src/transformers/models/rag/configuration_rag.py +src/transformers/models/rag/modeling_rag.py +src/transformers/models/rag/modeling_tf_rag.py +src/transformers/models/rag/retrieval_rag.py +src/transformers/models/rag/tokenization_rag.py +src/transformers/models/realm/__init__.py +src/transformers/models/realm/configuration_realm.py +src/transformers/models/realm/modeling_realm.py +src/transformers/models/realm/retrieval_realm.py +src/transformers/models/realm/tokenization_realm.py +src/transformers/models/realm/tokenization_realm_fast.py +src/transformers/models/reformer/__init__.py +src/transformers/models/reformer/configuration_reformer.py +src/transformers/models/reformer/convert_reformer_trax_checkpoint_to_pytorch.py +src/transformers/models/reformer/modeling_reformer.py +src/transformers/models/reformer/tokenization_reformer.py +src/transformers/models/reformer/tokenization_reformer_fast.py +src/transformers/models/regnet/__init__.py +src/transformers/models/regnet/configuration_regnet.py +src/transformers/models/regnet/convert_regnet_seer_10b_to_pytorch.py +src/transformers/models/regnet/convert_regnet_to_pytorch.py +src/transformers/models/regnet/modeling_regnet.py +src/transformers/models/regnet/modeling_tf_regnet.py +src/transformers/models/rembert/__init__.py +src/transformers/models/rembert/configuration_rembert.py +src/transformers/models/rembert/convert_rembert_tf_checkpoint_to_pytorch.py +src/transformers/models/rembert/modeling_rembert.py +src/transformers/models/rembert/modeling_tf_rembert.py +src/transformers/models/rembert/tokenization_rembert.py +src/transformers/models/rembert/tokenization_rembert_fast.py +src/transformers/models/resnet/__init__.py +src/transformers/models/resnet/configuration_resnet.py +src/transformers/models/resnet/convert_resnet_to_pytorch.py +src/transformers/models/resnet/modeling_flax_resnet.py +src/transformers/models/resnet/modeling_resnet.py +src/transformers/models/resnet/modeling_tf_resnet.py +src/transformers/models/retribert/__init__.py +src/transformers/models/retribert/configuration_retribert.py +src/transformers/models/retribert/modeling_retribert.py +src/transformers/models/retribert/tokenization_retribert.py +src/transformers/models/retribert/tokenization_retribert_fast.py +src/transformers/models/roberta/__init__.py +src/transformers/models/roberta/configuration_roberta.py +src/transformers/models/roberta/convert_roberta_original_pytorch_checkpoint_to_pytorch.py +src/transformers/models/roberta/modeling_flax_roberta.py +src/transformers/models/roberta/modeling_roberta.py +src/transformers/models/roberta/modeling_tf_roberta.py +src/transformers/models/roberta/tokenization_roberta.py +src/transformers/models/roberta/tokenization_roberta_fast.py +src/transformers/models/roberta_prelayernorm/__init__.py +src/transformers/models/roberta_prelayernorm/configuration_roberta_prelayernorm.py +src/transformers/models/roberta_prelayernorm/convert_roberta_prelayernorm_original_pytorch_checkpoint_to_pytorch.py +src/transformers/models/roberta_prelayernorm/modeling_flax_roberta_prelayernorm.py +src/transformers/models/roberta_prelayernorm/modeling_roberta_prelayernorm.py +src/transformers/models/roberta_prelayernorm/modeling_tf_roberta_prelayernorm.py +src/transformers/models/roc_bert/__init__.py +src/transformers/models/roc_bert/configuration_roc_bert.py +src/transformers/models/roc_bert/modeling_roc_bert.py +src/transformers/models/roc_bert/tokenization_roc_bert.py +src/transformers/models/roformer/__init__.py +src/transformers/models/roformer/configuration_roformer.py +src/transformers/models/roformer/convert_roformer_original_tf_checkpoint_to_pytorch.py +src/transformers/models/roformer/modeling_flax_roformer.py +src/transformers/models/roformer/modeling_roformer.py +src/transformers/models/roformer/modeling_tf_roformer.py +src/transformers/models/roformer/tokenization_roformer.py +src/transformers/models/roformer/tokenization_roformer_fast.py +src/transformers/models/roformer/tokenization_utils.py +src/transformers/models/segformer/__init__.py +src/transformers/models/segformer/configuration_segformer.py +src/transformers/models/segformer/convert_segformer_original_to_pytorch.py +src/transformers/models/segformer/feature_extraction_segformer.py +src/transformers/models/segformer/image_processing_segformer.py +src/transformers/models/segformer/modeling_segformer.py +src/transformers/models/segformer/modeling_tf_segformer.py +src/transformers/models/sew/__init__.py +src/transformers/models/sew/configuration_sew.py +src/transformers/models/sew/convert_sew_original_pytorch_checkpoint_to_pytorch.py +src/transformers/models/sew/modeling_sew.py +src/transformers/models/sew_d/__init__.py +src/transformers/models/sew_d/configuration_sew_d.py +src/transformers/models/sew_d/convert_sew_d_original_pytorch_checkpoint_to_pytorch.py +src/transformers/models/sew_d/modeling_sew_d.py +src/transformers/models/speech_encoder_decoder/__init__.py +src/transformers/models/speech_encoder_decoder/configuration_speech_encoder_decoder.py +src/transformers/models/speech_encoder_decoder/convert_mbart_wav2vec2_seq2seq_original_to_pytorch.py +src/transformers/models/speech_encoder_decoder/convert_speech_to_text_wav2vec2_seq2seq_original_to_pytorch.py +src/transformers/models/speech_encoder_decoder/modeling_flax_speech_encoder_decoder.py +src/transformers/models/speech_encoder_decoder/modeling_speech_encoder_decoder.py +src/transformers/models/speech_to_text/__init__.py +src/transformers/models/speech_to_text/configuration_speech_to_text.py +src/transformers/models/speech_to_text/convert_s2t_fairseq_to_tfms.py +src/transformers/models/speech_to_text/feature_extraction_speech_to_text.py +src/transformers/models/speech_to_text/modeling_speech_to_text.py +src/transformers/models/speech_to_text/modeling_tf_speech_to_text.py +src/transformers/models/speech_to_text/processing_speech_to_text.py +src/transformers/models/speech_to_text/tokenization_speech_to_text.py +src/transformers/models/speech_to_text_2/__init__.py +src/transformers/models/speech_to_text_2/configuration_speech_to_text_2.py +src/transformers/models/speech_to_text_2/modeling_speech_to_text_2.py +src/transformers/models/speech_to_text_2/processing_speech_to_text_2.py +src/transformers/models/speech_to_text_2/tokenization_speech_to_text_2.py +src/transformers/models/speecht5/__init__.py +src/transformers/models/speecht5/configuration_speecht5.py +src/transformers/models/speecht5/convert_hifigan.py +src/transformers/models/speecht5/convert_speecht5_original_pytorch_checkpoint_to_pytorch.py +src/transformers/models/speecht5/feature_extraction_speecht5.py +src/transformers/models/speecht5/modeling_speecht5.py +src/transformers/models/speecht5/processing_speecht5.py +src/transformers/models/speecht5/tokenization_speecht5.py +src/transformers/models/splinter/__init__.py +src/transformers/models/splinter/configuration_splinter.py +src/transformers/models/splinter/modeling_splinter.py +src/transformers/models/splinter/tokenization_splinter.py +src/transformers/models/splinter/tokenization_splinter_fast.py +src/transformers/models/squeezebert/__init__.py +src/transformers/models/squeezebert/configuration_squeezebert.py +src/transformers/models/squeezebert/modeling_squeezebert.py +src/transformers/models/squeezebert/tokenization_squeezebert.py +src/transformers/models/squeezebert/tokenization_squeezebert_fast.py +src/transformers/models/swin/__init__.py +src/transformers/models/swin/configuration_swin.py +src/transformers/models/swin/convert_swin_simmim_to_pytorch.py +src/transformers/models/swin/convert_swin_timm_to_pytorch.py +src/transformers/models/swin/modeling_swin.py +src/transformers/models/swin/modeling_tf_swin.py +src/transformers/models/swin2sr/__init__.py +src/transformers/models/swin2sr/configuration_swin2sr.py +src/transformers/models/swin2sr/convert_swin2sr_original_to_pytorch.py +src/transformers/models/swin2sr/image_processing_swin2sr.py +src/transformers/models/swin2sr/modeling_swin2sr.py +src/transformers/models/swinv2/__init__.py +src/transformers/models/swinv2/configuration_swinv2.py +src/transformers/models/swinv2/convert_swinv2_timm_to_pytorch.py +src/transformers/models/swinv2/modeling_swinv2.py +src/transformers/models/switch_transformers/__init__.py +src/transformers/models/switch_transformers/configuration_switch_transformers.py +src/transformers/models/switch_transformers/convert_big_switch.py +src/transformers/models/switch_transformers/convert_switch_transformers_original_flax_checkpoint_to_pytorch.py +src/transformers/models/switch_transformers/modeling_switch_transformers.py +src/transformers/models/t5/__init__.py +src/transformers/models/t5/configuration_t5.py +src/transformers/models/t5/convert_t5_original_tf_checkpoint_to_pytorch.py +src/transformers/models/t5/convert_t5x_checkpoint_to_flax.py +src/transformers/models/t5/convert_t5x_checkpoint_to_pytorch.py +src/transformers/models/t5/modeling_flax_t5.py +src/transformers/models/t5/modeling_t5.py +src/transformers/models/t5/modeling_tf_t5.py +src/transformers/models/t5/tokenization_t5.py +src/transformers/models/t5/tokenization_t5_fast.py +src/transformers/models/table_transformer/__init__.py +src/transformers/models/table_transformer/configuration_table_transformer.py +src/transformers/models/table_transformer/convert_table_transformer_original_pytorch_checkpoint_to_pytorch.py +src/transformers/models/table_transformer/modeling_table_transformer.py +src/transformers/models/tapas/__init__.py +src/transformers/models/tapas/configuration_tapas.py +src/transformers/models/tapas/convert_tapas_original_tf_checkpoint_to_pytorch.py +src/transformers/models/tapas/modeling_tapas.py +src/transformers/models/tapas/modeling_tf_tapas.py +src/transformers/models/tapas/tokenization_tapas.py +src/transformers/models/tapex/__init__.py +src/transformers/models/tapex/tokenization_tapex.py +src/transformers/models/time_series_transformer/__init__.py +src/transformers/models/time_series_transformer/configuration_time_series_transformer.py +src/transformers/models/time_series_transformer/modeling_time_series_transformer.py +src/transformers/models/timesformer/__init__.py +src/transformers/models/timesformer/configuration_timesformer.py +src/transformers/models/timesformer/convert_timesformer_to_pytorch.py +src/transformers/models/timesformer/modeling_timesformer.py +src/transformers/models/trajectory_transformer/__init__.py +src/transformers/models/trajectory_transformer/configuration_trajectory_transformer.py +src/transformers/models/trajectory_transformer/convert_trajectory_transformer_original_pytorch_checkpoint_to_pytorch.py +src/transformers/models/trajectory_transformer/modeling_trajectory_transformer.py +src/transformers/models/transfo_xl/__init__.py +src/transformers/models/transfo_xl/configuration_transfo_xl.py +src/transformers/models/transfo_xl/convert_transfo_xl_original_tf_checkpoint_to_pytorch.py +src/transformers/models/transfo_xl/modeling_tf_transfo_xl.py +src/transformers/models/transfo_xl/modeling_tf_transfo_xl_utilities.py +src/transformers/models/transfo_xl/modeling_transfo_xl.py +src/transformers/models/transfo_xl/modeling_transfo_xl_utilities.py +src/transformers/models/transfo_xl/tokenization_transfo_xl.py +src/transformers/models/trocr/__init__.py +src/transformers/models/trocr/configuration_trocr.py +src/transformers/models/trocr/convert_trocr_unilm_to_pytorch.py +src/transformers/models/trocr/modeling_trocr.py +src/transformers/models/trocr/processing_trocr.py +src/transformers/models/tvlt/__init__.py +src/transformers/models/tvlt/configuration_tvlt.py +src/transformers/models/tvlt/feature_extraction_tvlt.py +src/transformers/models/tvlt/image_processing_tvlt.py +src/transformers/models/tvlt/modeling_tvlt.py +src/transformers/models/tvlt/processing_tvlt.py +src/transformers/models/unispeech/__init__.py +src/transformers/models/unispeech/configuration_unispeech.py +src/transformers/models/unispeech/convert_unispeech_original_pytorch_checkpoint_to_pytorch.py +src/transformers/models/unispeech/modeling_unispeech.py +src/transformers/models/unispeech_sat/__init__.py +src/transformers/models/unispeech_sat/configuration_unispeech_sat.py +src/transformers/models/unispeech_sat/convert_unispeech_original_s3prl_checkpoint_to_pytorch.py +src/transformers/models/unispeech_sat/convert_unispeech_sat_original_pytorch_checkpoint_to_pytorch.py +src/transformers/models/unispeech_sat/modeling_unispeech_sat.py +src/transformers/models/upernet/__init__.py +src/transformers/models/upernet/configuration_upernet.py +src/transformers/models/upernet/convert_convnext_upernet_to_pytorch.py +src/transformers/models/upernet/convert_swin_upernet_to_pytorch.py +src/transformers/models/upernet/modeling_upernet.py +src/transformers/models/van/__init__.py +src/transformers/models/van/configuration_van.py +src/transformers/models/van/convert_van_to_pytorch.py +src/transformers/models/van/modeling_van.py +src/transformers/models/videomae/__init__.py +src/transformers/models/videomae/configuration_videomae.py +src/transformers/models/videomae/convert_videomae_to_pytorch.py +src/transformers/models/videomae/feature_extraction_videomae.py +src/transformers/models/videomae/image_processing_videomae.py +src/transformers/models/videomae/modeling_videomae.py +src/transformers/models/vilt/__init__.py +src/transformers/models/vilt/configuration_vilt.py +src/transformers/models/vilt/convert_vilt_original_to_pytorch.py +src/transformers/models/vilt/feature_extraction_vilt.py +src/transformers/models/vilt/image_processing_vilt.py +src/transformers/models/vilt/modeling_vilt.py +src/transformers/models/vilt/processing_vilt.py +src/transformers/models/vision_encoder_decoder/__init__.py +src/transformers/models/vision_encoder_decoder/configuration_vision_encoder_decoder.py +src/transformers/models/vision_encoder_decoder/modeling_flax_vision_encoder_decoder.py +src/transformers/models/vision_encoder_decoder/modeling_tf_vision_encoder_decoder.py +src/transformers/models/vision_encoder_decoder/modeling_vision_encoder_decoder.py +src/transformers/models/vision_text_dual_encoder/__init__.py +src/transformers/models/vision_text_dual_encoder/configuration_vision_text_dual_encoder.py +src/transformers/models/vision_text_dual_encoder/modeling_flax_vision_text_dual_encoder.py +src/transformers/models/vision_text_dual_encoder/modeling_tf_vision_text_dual_encoder.py +src/transformers/models/vision_text_dual_encoder/modeling_vision_text_dual_encoder.py +src/transformers/models/vision_text_dual_encoder/processing_vision_text_dual_encoder.py +src/transformers/models/visual_bert/__init__.py +src/transformers/models/visual_bert/configuration_visual_bert.py +src/transformers/models/visual_bert/convert_visual_bert_original_pytorch_checkpoint_to_pytorch.py +src/transformers/models/visual_bert/modeling_visual_bert.py +src/transformers/models/vit/__init__.py +src/transformers/models/vit/configuration_vit.py +src/transformers/models/vit/convert_dino_to_pytorch.py +src/transformers/models/vit/convert_vit_timm_to_pytorch.py +src/transformers/models/vit/feature_extraction_vit.py +src/transformers/models/vit/image_processing_vit.py +src/transformers/models/vit/modeling_flax_vit.py +src/transformers/models/vit/modeling_tf_vit.py +src/transformers/models/vit/modeling_vit.py +src/transformers/models/vit_hybrid/__init__.py +src/transformers/models/vit_hybrid/configuration_vit_hybrid.py +src/transformers/models/vit_hybrid/convert_vit_hybrid_timm_to_pytorch.py +src/transformers/models/vit_hybrid/image_processing_vit_hybrid.py +src/transformers/models/vit_hybrid/modeling_vit_hybrid.py +src/transformers/models/vit_mae/__init__.py +src/transformers/models/vit_mae/configuration_vit_mae.py +src/transformers/models/vit_mae/convert_vit_mae_to_pytorch.py +src/transformers/models/vit_mae/modeling_tf_vit_mae.py +src/transformers/models/vit_mae/modeling_vit_mae.py +src/transformers/models/vit_msn/__init__.py +src/transformers/models/vit_msn/configuration_vit_msn.py +src/transformers/models/vit_msn/convert_msn_to_pytorch.py +src/transformers/models/vit_msn/modeling_vit_msn.py +src/transformers/models/wav2vec2/__init__.py +src/transformers/models/wav2vec2/configuration_wav2vec2.py +src/transformers/models/wav2vec2/convert_wav2vec2_original_pytorch_checkpoint_to_pytorch.py +src/transformers/models/wav2vec2/convert_wav2vec2_original_s3prl_checkpoint_to_pytorch.py +src/transformers/models/wav2vec2/feature_extraction_wav2vec2.py +src/transformers/models/wav2vec2/modeling_flax_wav2vec2.py +src/transformers/models/wav2vec2/modeling_tf_wav2vec2.py +src/transformers/models/wav2vec2/modeling_wav2vec2.py +src/transformers/models/wav2vec2/processing_wav2vec2.py +src/transformers/models/wav2vec2/tokenization_wav2vec2.py +src/transformers/models/wav2vec2_conformer/__init__.py +src/transformers/models/wav2vec2_conformer/configuration_wav2vec2_conformer.py +src/transformers/models/wav2vec2_conformer/convert_wav2vec2_conformer_original_pytorch_checkpoint_to_pytorch.py +src/transformers/models/wav2vec2_conformer/modeling_wav2vec2_conformer.py +src/transformers/models/wav2vec2_phoneme/__init__.py +src/transformers/models/wav2vec2_phoneme/tokenization_wav2vec2_phoneme.py +src/transformers/models/wav2vec2_with_lm/__init__.py +src/transformers/models/wav2vec2_with_lm/processing_wav2vec2_with_lm.py +src/transformers/models/wavlm/__init__.py +src/transformers/models/wavlm/configuration_wavlm.py +src/transformers/models/wavlm/convert_wavlm_original_pytorch_checkpoint_to_pytorch.py +src/transformers/models/wavlm/convert_wavlm_original_s3prl_checkpoint_to_pytorch.py +src/transformers/models/wavlm/modeling_wavlm.py +src/transformers/models/whisper/__init__.py +src/transformers/models/whisper/configuration_whisper.py +src/transformers/models/whisper/convert_openai_to_hf.py +src/transformers/models/whisper/english_normalizer.py +src/transformers/models/whisper/feature_extraction_whisper.py +src/transformers/models/whisper/modeling_flax_whisper.py +src/transformers/models/whisper/modeling_tf_whisper.py +src/transformers/models/whisper/modeling_whisper.py +src/transformers/models/whisper/processing_whisper.py +src/transformers/models/whisper/tokenization_whisper.py +src/transformers/models/whisper/tokenization_whisper_fast.py +src/transformers/models/x_clip/__init__.py +src/transformers/models/x_clip/configuration_x_clip.py +src/transformers/models/x_clip/convert_x_clip_original_pytorch_to_hf.py +src/transformers/models/x_clip/modeling_x_clip.py +src/transformers/models/x_clip/processing_x_clip.py +src/transformers/models/xglm/__init__.py +src/transformers/models/xglm/configuration_xglm.py +src/transformers/models/xglm/convert_xglm_original_ckpt_to_trfms.py +src/transformers/models/xglm/modeling_flax_xglm.py +src/transformers/models/xglm/modeling_tf_xglm.py +src/transformers/models/xglm/modeling_xglm.py +src/transformers/models/xglm/tokenization_xglm.py +src/transformers/models/xglm/tokenization_xglm_fast.py +src/transformers/models/xlm/__init__.py +src/transformers/models/xlm/configuration_xlm.py +src/transformers/models/xlm/convert_xlm_original_pytorch_checkpoint_to_pytorch.py +src/transformers/models/xlm/modeling_tf_xlm.py +src/transformers/models/xlm/modeling_xlm.py +src/transformers/models/xlm/tokenization_xlm.py +src/transformers/models/xlm_prophetnet/__init__.py +src/transformers/models/xlm_prophetnet/configuration_xlm_prophetnet.py +src/transformers/models/xlm_prophetnet/modeling_xlm_prophetnet.py +src/transformers/models/xlm_prophetnet/tokenization_xlm_prophetnet.py +src/transformers/models/xlm_roberta/__init__.py +src/transformers/models/xlm_roberta/configuration_xlm_roberta.py +src/transformers/models/xlm_roberta/modeling_flax_xlm_roberta.py +src/transformers/models/xlm_roberta/modeling_tf_xlm_roberta.py +src/transformers/models/xlm_roberta/modeling_xlm_roberta.py +src/transformers/models/xlm_roberta/tokenization_xlm_roberta.py +src/transformers/models/xlm_roberta/tokenization_xlm_roberta_fast.py +src/transformers/models/xlm_roberta_xl/__init__.py +src/transformers/models/xlm_roberta_xl/configuration_xlm_roberta_xl.py +src/transformers/models/xlm_roberta_xl/convert_xlm_roberta_xl_original_pytorch_checkpoint_to_pytorch.py +src/transformers/models/xlm_roberta_xl/modeling_xlm_roberta_xl.py +src/transformers/models/xlnet/__init__.py +src/transformers/models/xlnet/configuration_xlnet.py +src/transformers/models/xlnet/convert_xlnet_original_tf_checkpoint_to_pytorch.py +src/transformers/models/xlnet/modeling_tf_xlnet.py +src/transformers/models/xlnet/modeling_xlnet.py +src/transformers/models/xlnet/tokenization_xlnet.py +src/transformers/models/xlnet/tokenization_xlnet_fast.py +src/transformers/models/xmod/__init__.py +src/transformers/models/xmod/configuration_xmod.py +src/transformers/models/xmod/convert_xmod_original_pytorch_checkpoint_to_pytorch.py +src/transformers/models/xmod/modeling_xmod.py +src/transformers/models/yolos/__init__.py +src/transformers/models/yolos/configuration_yolos.py +src/transformers/models/yolos/convert_yolos_to_pytorch.py +src/transformers/models/yolos/feature_extraction_yolos.py +src/transformers/models/yolos/image_processing_yolos.py +src/transformers/models/yolos/modeling_yolos.py +src/transformers/models/yoso/__init__.py +src/transformers/models/yoso/configuration_yoso.py +src/transformers/models/yoso/convert_yoso_pytorch_to_pytorch.py +src/transformers/models/yoso/modeling_yoso.py +src/transformers/onnx/__init__.py +src/transformers/onnx/__main__.py +src/transformers/onnx/config.py +src/transformers/onnx/convert.py +src/transformers/onnx/features.py +src/transformers/onnx/utils.py +src/transformers/pipelines/__init__.py +src/transformers/pipelines/audio_classification.py +src/transformers/pipelines/audio_utils.py +src/transformers/pipelines/automatic_speech_recognition.py +src/transformers/pipelines/base.py +src/transformers/pipelines/conversational.py +src/transformers/pipelines/depth_estimation.py +src/transformers/pipelines/document_question_answering.py +src/transformers/pipelines/feature_extraction.py +src/transformers/pipelines/fill_mask.py +src/transformers/pipelines/image_classification.py +src/transformers/pipelines/image_segmentation.py +src/transformers/pipelines/image_to_text.py +src/transformers/pipelines/object_detection.py +src/transformers/pipelines/pt_utils.py +src/transformers/pipelines/question_answering.py +src/transformers/pipelines/table_question_answering.py +src/transformers/pipelines/text2text_generation.py +src/transformers/pipelines/text_classification.py +src/transformers/pipelines/text_generation.py +src/transformers/pipelines/token_classification.py +src/transformers/pipelines/video_classification.py +src/transformers/pipelines/visual_question_answering.py +src/transformers/pipelines/zero_shot_audio_classification.py +src/transformers/pipelines/zero_shot_classification.py +src/transformers/pipelines/zero_shot_image_classification.py +src/transformers/pipelines/zero_shot_object_detection.py +src/transformers/sagemaker/__init__.py +src/transformers/sagemaker/trainer_sm.py +src/transformers/sagemaker/training_args_sm.py +src/transformers/utils/__init__.py +src/transformers/utils/bitsandbytes.py +src/transformers/utils/constants.py +src/transformers/utils/doc.py +src/transformers/utils/dummy_detectron2_objects.py +src/transformers/utils/dummy_flax_objects.py +src/transformers/utils/dummy_keras_nlp_objects.py +src/transformers/utils/dummy_pt_objects.py +src/transformers/utils/dummy_sentencepiece_and_tokenizers_objects.py +src/transformers/utils/dummy_sentencepiece_objects.py +src/transformers/utils/dummy_speech_objects.py +src/transformers/utils/dummy_tensorflow_text_objects.py +src/transformers/utils/dummy_tf_objects.py +src/transformers/utils/dummy_tokenizers_objects.py +src/transformers/utils/dummy_vision_objects.py +src/transformers/utils/fx.py +src/transformers/utils/generic.py +src/transformers/utils/hp_naming.py +src/transformers/utils/hub.py +src/transformers/utils/import_utils.py +src/transformers/utils/logging.py +src/transformers/utils/model_parallel_utils.py +src/transformers/utils/notebook.py +src/transformers/utils/quantization_config.py +src/transformers/utils/sentencepiece_model_pb2.py +src/transformers/utils/versions.py +tests/test_configuration_common.py +tests/test_feature_extraction_common.py +tests/test_image_processing_common.py +tests/test_image_transforms.py +tests/test_modeling_common.py +tests/test_modeling_flax_common.py +tests/test_modeling_tf_common.py +tests/test_pipeline_mixin.py +tests/test_sequence_feature_extraction_common.py +tests/test_tokenization_common.py \ No newline at end of file diff --git a/hf-dev-train/transformers-main/src/transformers.egg-info/dependency_links.txt b/hf-dev-train/transformers-main/src/transformers.egg-info/dependency_links.txt new file mode 100644 index 0000000000000000000000000000000000000000..8b137891791fe96927ad78e64b0aad7bded08bdc --- /dev/null +++ b/hf-dev-train/transformers-main/src/transformers.egg-info/dependency_links.txt @@ -0,0 +1 @@ + diff --git a/hf-dev-train/transformers-main/src/transformers.egg-info/entry_points.txt b/hf-dev-train/transformers-main/src/transformers.egg-info/entry_points.txt new file mode 100644 index 0000000000000000000000000000000000000000..8a7995ed6f21261a78509c57d57daba51ecf1a7d --- /dev/null +++ b/hf-dev-train/transformers-main/src/transformers.egg-info/entry_points.txt @@ -0,0 +1,2 @@ +[console_scripts] +transformers-cli = transformers.commands.transformers_cli:main diff --git a/hf-dev-train/transformers-main/src/transformers.egg-info/not-zip-safe b/hf-dev-train/transformers-main/src/transformers.egg-info/not-zip-safe new file mode 100644 index 0000000000000000000000000000000000000000..8b137891791fe96927ad78e64b0aad7bded08bdc --- /dev/null +++ b/hf-dev-train/transformers-main/src/transformers.egg-info/not-zip-safe @@ -0,0 +1 @@ + diff --git a/hf-dev-train/transformers-main/src/transformers.egg-info/requires.txt b/hf-dev-train/transformers-main/src/transformers.egg-info/requires.txt new file mode 100644 index 0000000000000000000000000000000000000000..0de7a231309a1e88c09cacda88abcafb64cf489c --- /dev/null +++ b/hf-dev-train/transformers-main/src/transformers.egg-info/requires.txt @@ -0,0 +1,453 @@ +filelock +huggingface-hub<1.0,>=0.11.0 +numpy>=1.17 +packaging>=20.0 +pyyaml>=5.1 +regex!=2019.12.17 +requests +tokenizers!=0.11.3,<0.14,>=0.11.1 +tqdm>=4.27 + +[:python_version < "3.8"] +importlib_metadata + +[accelerate] +accelerate>=0.10.0 + +[all] +tensorflow<2.13,>=2.4 +onnxconverter-common +tf2onnx +tensorflow-text<2.13 +keras-nlp>=0.3.1 +torch!=1.12.0,>=1.9 +jax!=0.3.2,<=0.3.6,>=0.2.8 +jaxlib<=0.3.6,>=0.1.65 +flax>=0.4.1 +optax>=0.0.8 +sentencepiece!=0.1.92,>=0.1.91 +protobuf<=3.20.2 +tokenizers!=0.11.3,<0.14,>=0.11.1 +torchaudio +librosa +pyctcdecode>=0.4.0 +phonemizer +kenlm +Pillow +optuna +ray[tune] +sigopt +timm +torchvision +codecarbon==1.2.0 +accelerate>=0.10.0 +decord==0.6.0 +av==9.2.0 + +[audio] +librosa +pyctcdecode>=0.4.0 +phonemizer +kenlm + +[codecarbon] +codecarbon==1.2.0 + +[deepspeed] +deepspeed>=0.8.3 +accelerate>=0.10.0 + +[deepspeed-testing] +deepspeed>=0.8.3 +accelerate>=0.10.0 +pytest +pytest-xdist +timeout-decorator +parameterized +psutil +datasets!=2.5.0 +dill<0.3.5 +evaluate>=0.2.0 +pytest-timeout +black~=23.1 +sacrebleu<2.0.0,>=1.4.12 +rouge-score!=0.0.7,!=0.0.8,!=0.1,!=0.1.1 +nltk +GitPython<3.1.19 +hf-doc-builder>=0.3.0 +protobuf<=3.20.2 +sacremoses +rjieba +safetensors>=0.2.1 +beautifulsoup4 +faiss-cpu +cookiecutter==1.7.3 +optuna +sentencepiece!=0.1.92,>=0.1.91 + +[dev] +tensorflow<2.13,>=2.4 +onnxconverter-common +tf2onnx +tensorflow-text<2.13 +keras-nlp>=0.3.1 +torch!=1.12.0,>=1.9 +jax!=0.3.2,<=0.3.6,>=0.2.8 +jaxlib<=0.3.6,>=0.1.65 +flax>=0.4.1 +optax>=0.0.8 +sentencepiece!=0.1.92,>=0.1.91 +protobuf<=3.20.2 +tokenizers!=0.11.3,<0.14,>=0.11.1 +torchaudio +librosa +pyctcdecode>=0.4.0 +phonemizer +kenlm +Pillow +optuna +ray[tune] +sigopt +timm +torchvision +codecarbon==1.2.0 +accelerate>=0.10.0 +decord==0.6.0 +av==9.2.0 +pytest +pytest-xdist +timeout-decorator +parameterized +psutil +datasets!=2.5.0 +dill<0.3.5 +evaluate>=0.2.0 +pytest-timeout +black~=23.1 +sacrebleu<2.0.0,>=1.4.12 +rouge-score!=0.0.7,!=0.0.8,!=0.1,!=0.1.1 +nltk +GitPython<3.1.19 +hf-doc-builder>=0.3.0 +sacremoses +rjieba +safetensors>=0.2.1 +beautifulsoup4 +faiss-cpu +cookiecutter==1.7.3 +isort>=5.5.4 +ruff<=0.0.259,>=0.0.241 +fugashi>=1.0 +ipadic<2.0,>=1.0.0 +unidic_lite>=1.0.7 +unidic>=1.0.2 +sudachipy>=0.6.6 +sudachidict_core>=20220729 +rhoknp>=1.1.0 +hf-doc-builder +scikit-learn + +[dev-tensorflow] +pytest +pytest-xdist +timeout-decorator +parameterized +psutil +datasets!=2.5.0 +dill<0.3.5 +evaluate>=0.2.0 +pytest-timeout +black~=23.1 +sacrebleu<2.0.0,>=1.4.12 +rouge-score!=0.0.7,!=0.0.8,!=0.1,!=0.1.1 +nltk +GitPython<3.1.19 +hf-doc-builder>=0.3.0 +protobuf<=3.20.2 +sacremoses +rjieba +safetensors>=0.2.1 +beautifulsoup4 +faiss-cpu +cookiecutter==1.7.3 +tensorflow<2.13,>=2.4 +onnxconverter-common +tf2onnx +tensorflow-text<2.13 +keras-nlp>=0.3.1 +sentencepiece!=0.1.92,>=0.1.91 +tokenizers!=0.11.3,<0.14,>=0.11.1 +Pillow +isort>=5.5.4 +ruff<=0.0.259,>=0.0.241 +hf-doc-builder +scikit-learn +onnxruntime>=1.4.0 +onnxruntime-tools>=1.4.2 +librosa +pyctcdecode>=0.4.0 +phonemizer +kenlm + +[dev-torch] +pytest +pytest-xdist +timeout-decorator +parameterized +psutil +datasets!=2.5.0 +dill<0.3.5 +evaluate>=0.2.0 +pytest-timeout +black~=23.1 +sacrebleu<2.0.0,>=1.4.12 +rouge-score!=0.0.7,!=0.0.8,!=0.1,!=0.1.1 +nltk +GitPython<3.1.19 +hf-doc-builder>=0.3.0 +protobuf<=3.20.2 +sacremoses +rjieba +safetensors>=0.2.1 +beautifulsoup4 +faiss-cpu +cookiecutter==1.7.3 +torch!=1.12.0,>=1.9 +sentencepiece!=0.1.92,>=0.1.91 +tokenizers!=0.11.3,<0.14,>=0.11.1 +torchaudio +librosa +pyctcdecode>=0.4.0 +phonemizer +kenlm +Pillow +optuna +ray[tune] +sigopt +timm +torchvision +codecarbon==1.2.0 +isort>=5.5.4 +ruff<=0.0.259,>=0.0.241 +fugashi>=1.0 +ipadic<2.0,>=1.0.0 +unidic_lite>=1.0.7 +unidic>=1.0.2 +sudachipy>=0.6.6 +sudachidict_core>=20220729 +rhoknp>=1.1.0 +hf-doc-builder +scikit-learn +onnxruntime>=1.4.0 +onnxruntime-tools>=1.4.2 + +[docs] +tensorflow<2.13,>=2.4 +onnxconverter-common +tf2onnx +tensorflow-text<2.13 +keras-nlp>=0.3.1 +torch!=1.12.0,>=1.9 +jax!=0.3.2,<=0.3.6,>=0.2.8 +jaxlib<=0.3.6,>=0.1.65 +flax>=0.4.1 +optax>=0.0.8 +sentencepiece!=0.1.92,>=0.1.91 +protobuf<=3.20.2 +tokenizers!=0.11.3,<0.14,>=0.11.1 +torchaudio +librosa +pyctcdecode>=0.4.0 +phonemizer +kenlm +Pillow +optuna +ray[tune] +sigopt +timm +torchvision +codecarbon==1.2.0 +accelerate>=0.10.0 +decord==0.6.0 +av==9.2.0 +hf-doc-builder + +[docs_specific] +hf-doc-builder + +[fairscale] +fairscale>0.3 + +[flax] +jax!=0.3.2,<=0.3.6,>=0.2.8 +jaxlib<=0.3.6,>=0.1.65 +flax>=0.4.1 +optax>=0.0.8 + +[flax-speech] +librosa +pyctcdecode>=0.4.0 +phonemizer +kenlm + +[ftfy] +ftfy + +[integrations] +optuna +ray[tune] +sigopt + +[ja] +fugashi>=1.0 +ipadic<2.0,>=1.0.0 +unidic_lite>=1.0.7 +unidic>=1.0.2 +sudachipy>=0.6.6 +sudachidict_core>=20220729 +rhoknp>=1.1.0 + +[modelcreation] +cookiecutter==1.7.3 + +[natten] +natten>=0.14.6 + +[onnx] +onnxconverter-common +tf2onnx +onnxruntime>=1.4.0 +onnxruntime-tools>=1.4.2 + +[onnxruntime] +onnxruntime>=1.4.0 +onnxruntime-tools>=1.4.2 + +[optuna] +optuna + +[quality] +black~=23.1 +datasets!=2.5.0 +isort>=5.5.4 +ruff<=0.0.259,>=0.0.241 +GitPython<3.1.19 +hf-doc-builder>=0.3.0 + +[ray] +ray[tune] + +[retrieval] +faiss-cpu +datasets!=2.5.0 + +[sagemaker] +sagemaker>=2.31.0 + +[sentencepiece] +sentencepiece!=0.1.92,>=0.1.91 +protobuf<=3.20.2 + +[serving] +pydantic +uvicorn +fastapi +starlette + +[sigopt] +sigopt + +[sklearn] +scikit-learn + +[speech] +torchaudio +librosa +pyctcdecode>=0.4.0 +phonemizer +kenlm + +[testing] +pytest +pytest-xdist +timeout-decorator +parameterized +psutil +datasets!=2.5.0 +dill<0.3.5 +evaluate>=0.2.0 +pytest-timeout +black~=23.1 +sacrebleu<2.0.0,>=1.4.12 +rouge-score!=0.0.7,!=0.0.8,!=0.1,!=0.1.1 +nltk +GitPython<3.1.19 +hf-doc-builder>=0.3.0 +protobuf<=3.20.2 +sacremoses +rjieba +safetensors>=0.2.1 +beautifulsoup4 +faiss-cpu +cookiecutter==1.7.3 + +[tf] +tensorflow<2.13,>=2.4 +onnxconverter-common +tf2onnx +tensorflow-text<2.13 +keras-nlp>=0.3.1 + +[tf-cpu] +tensorflow-cpu<2.13,>=2.4 +onnxconverter-common +tf2onnx +tensorflow-text<2.13 +keras-nlp>=0.3.1 + +[tf-speech] +librosa +pyctcdecode>=0.4.0 +phonemizer +kenlm + +[timm] +timm + +[tokenizers] +tokenizers!=0.11.3,<0.14,>=0.11.1 + +[torch] +torch!=1.12.0,>=1.9 + +[torch-speech] +torchaudio +librosa +pyctcdecode>=0.4.0 +phonemizer +kenlm + +[torch-vision] +torchvision +Pillow + +[torchhub] +filelock +huggingface-hub<1.0,>=0.11.0 +importlib_metadata +numpy>=1.17 +packaging>=20.0 +protobuf<=3.20.2 +regex!=2019.12.17 +requests +sentencepiece!=0.1.92,>=0.1.91 +torch!=1.12.0,>=1.9 +tokenizers!=0.11.3,<0.14,>=0.11.1 +tqdm>=4.27 + +[video] +decord==0.6.0 +av==9.2.0 + +[vision] +Pillow diff --git a/hf-dev-train/transformers-main/src/transformers.egg-info/top_level.txt b/hf-dev-train/transformers-main/src/transformers.egg-info/top_level.txt new file mode 100644 index 0000000000000000000000000000000000000000..976a2b1f3998279c10c413279a095be86bf69167 --- /dev/null +++ b/hf-dev-train/transformers-main/src/transformers.egg-info/top_level.txt @@ -0,0 +1 @@ +transformers diff --git a/hf-dev-train/transformers-main/src/transformers/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..47996911283fe3f5cab3f47730072b89743757e2 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/__pycache__/activations.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/__pycache__/activations.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..30a32ec5cc502f9c9274b0002cff447a39278baa Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/__pycache__/activations.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/__pycache__/configuration_utils.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/__pycache__/configuration_utils.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..f9d7ce890348432eb816db101c404391e04b55aa Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/__pycache__/configuration_utils.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/__pycache__/convert_slow_tokenizer.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/__pycache__/convert_slow_tokenizer.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..65ec31b454f2fd08ac9b45acecb32186b4bec932 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/__pycache__/convert_slow_tokenizer.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/__pycache__/debug_utils.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/__pycache__/debug_utils.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..1dccbed090d834bb89786cc23a5dacd9b087088e Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/__pycache__/debug_utils.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/__pycache__/deepspeed.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/__pycache__/deepspeed.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..c66c4671088b0c49223f941daa8ad1cee3ff54b1 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/__pycache__/deepspeed.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/__pycache__/dependency_versions_check.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/__pycache__/dependency_versions_check.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..2ffff4d4d981f022fea5ac6647ab78ed965fc6e9 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/__pycache__/dependency_versions_check.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/__pycache__/dependency_versions_table.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/__pycache__/dependency_versions_table.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..51a79ccd8cecdf58d76b2a397bef832dc328f7c5 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/__pycache__/dependency_versions_table.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/__pycache__/dynamic_module_utils.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/__pycache__/dynamic_module_utils.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..487315100840f59e5ce7043430e4d5867fc9bd32 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/__pycache__/dynamic_module_utils.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/__pycache__/feature_extraction_utils.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/__pycache__/feature_extraction_utils.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..10814ebecf91ffce22a26c81b84db85af9c014d9 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/__pycache__/feature_extraction_utils.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/__pycache__/file_utils.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/__pycache__/file_utils.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..eba315962188538241145858f3f4b27312301dcc Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/__pycache__/file_utils.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/__pycache__/image_processing_utils.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/__pycache__/image_processing_utils.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..77f2831ad06b17176b6e233121ac51110dd88fa0 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/__pycache__/image_processing_utils.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/__pycache__/image_transforms.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/__pycache__/image_transforms.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..fd7d1a8100d586474b23aefda1f704db0cafc7b7 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/__pycache__/image_transforms.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/__pycache__/image_utils.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/__pycache__/image_utils.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..6ed5ad1d827517d88888e0518fdbb14f376391e5 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/__pycache__/image_utils.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/__pycache__/integrations.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/__pycache__/integrations.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..8e48a120d29b92f5204d120db22129f60f9f0055 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/__pycache__/integrations.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/__pycache__/modelcard.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/__pycache__/modelcard.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..d335fcd3110be1deae0fb40aef76e42b893d51d8 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/__pycache__/modelcard.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/__pycache__/modeling_outputs.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/__pycache__/modeling_outputs.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..25739dd72b20118a044fe09e858c136c208a4521 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/__pycache__/modeling_outputs.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/__pycache__/modeling_utils.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/__pycache__/modeling_utils.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..dc2c9baa988c2f2c9e873fc617260c41f7aa88b5 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/__pycache__/modeling_utils.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/__pycache__/optimization.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/__pycache__/optimization.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..9db277ef3c0fc3428ba0e312b61c54c94152b6d7 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/__pycache__/optimization.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/__pycache__/pytorch_utils.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/__pycache__/pytorch_utils.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..a8c81322fce47cc0628915be2a47b8d95ce37620 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/__pycache__/pytorch_utils.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/__pycache__/tokenization_utils.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/__pycache__/tokenization_utils.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..242edc885ddc667d37a6fd1d42812dc53538e538 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/__pycache__/tokenization_utils.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/__pycache__/tokenization_utils_base.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/__pycache__/tokenization_utils_base.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..82dacdd41f615c3482306f5b40aeda00348761b2 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/__pycache__/tokenization_utils_base.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/__pycache__/tokenization_utils_fast.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/__pycache__/tokenization_utils_fast.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..33c368f2c376017d3617f649f76c6e88cedcf0de Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/__pycache__/tokenization_utils_fast.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/__pycache__/trainer.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/__pycache__/trainer.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..9cc0fda79e61a3fb9b948a6b07328dd1888a0c04 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/__pycache__/trainer.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/__pycache__/trainer_callback.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/__pycache__/trainer_callback.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..3cef366e648fbcaeb69e9b28fbda207484968613 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/__pycache__/trainer_callback.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/__pycache__/trainer_pt_utils.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/__pycache__/trainer_pt_utils.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..b081fb2be53830cb5f7202b5af00ab19a5a6ebb9 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/__pycache__/trainer_pt_utils.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/__pycache__/trainer_utils.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/__pycache__/trainer_utils.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..f1c313b3ffeca49e4c0797e5f97c7acf31b5facf Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/__pycache__/trainer_utils.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/__pycache__/training_args.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/__pycache__/training_args.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..b73d73a0f4ef08e251ad5aa127defc7ae8187def Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/__pycache__/training_args.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/data/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/data/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..5fa3228101af9dde15e30e7993edfc6c94363513 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/data/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/data/__pycache__/data_collator.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/data/__pycache__/data_collator.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..7e73e81e34250e9815d41de3bebc81a79cc80f9f Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/data/__pycache__/data_collator.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/data/metrics/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/data/metrics/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..44d2ae74f1174f50161f9df8f3d16ef4c06d2d7d Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/data/metrics/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/data/processors/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/data/processors/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..8bf8dbec19533cdaf22beac4a28cda6180463176 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/data/processors/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/data/processors/__pycache__/glue.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/data/processors/__pycache__/glue.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..4abe3b6c8de18acea93a02e9da2b3f9f06fd93da Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/data/processors/__pycache__/glue.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/data/processors/__pycache__/squad.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/data/processors/__pycache__/squad.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..60b31d6bcc39e91ee01b9230d09a4b4ee4c6037d Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/data/processors/__pycache__/squad.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/data/processors/__pycache__/utils.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/data/processors/__pycache__/utils.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..74e5c7f70a3fdb67a0b85763660c93a21aab13f3 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/data/processors/__pycache__/utils.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/data/processors/__pycache__/xnli.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/data/processors/__pycache__/xnli.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..c7dc0a69495002c6eb3494414a5b4efd2cff2463 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/data/processors/__pycache__/xnli.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/generation/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/generation/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..07f61aa1b13977c5ce9e0e65389a71dd0baad0f9 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/generation/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/generation/__pycache__/beam_constraints.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/generation/__pycache__/beam_constraints.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..a773a3a9177634b0ec3f68a3827cead6f1472e5c Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/generation/__pycache__/beam_constraints.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/generation/__pycache__/beam_search.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/generation/__pycache__/beam_search.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..f2963efdb7a551f553ca8a2ed7b92cfce4857959 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/generation/__pycache__/beam_search.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/generation/__pycache__/configuration_utils.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/generation/__pycache__/configuration_utils.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..49876a125081885fe93c983479235b785442a4b0 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/generation/__pycache__/configuration_utils.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/generation/__pycache__/logits_process.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/generation/__pycache__/logits_process.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..8acbb7d9decc8247ec72181daf94389a8acac51d Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/generation/__pycache__/logits_process.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/generation/__pycache__/stopping_criteria.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/generation/__pycache__/stopping_criteria.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..21a543e18563509afa2698a978ef4f37e6849eb8 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/generation/__pycache__/stopping_criteria.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/generation/__pycache__/utils.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/generation/__pycache__/utils.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..7268d583517481c90238ef10d9eb1ffb5b7ab0e4 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/generation/__pycache__/utils.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..ab75e870cd40ee425129eeeccf2c77fdf1c79c44 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/albert/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/albert/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..a41723c2e970405712496dd786bb767fae42ba6c Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/albert/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/albert/__pycache__/configuration_albert.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/albert/__pycache__/configuration_albert.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..b5ad207336a2395cca5d91e0badc05b63572f106 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/albert/__pycache__/configuration_albert.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/align/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/align/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..ddfc4c901da9b485bde7bd4b504f33b64b604d8a Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/align/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/align/__pycache__/configuration_align.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/align/__pycache__/configuration_align.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..45abeb7394abd1a1386fa0a1e14446926de9b114 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/align/__pycache__/configuration_align.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/altclip/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/altclip/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..b8a15eb1ab692b1b3ead9a4a2be44996ef7f4be5 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/altclip/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/altclip/__pycache__/configuration_altclip.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/altclip/__pycache__/configuration_altclip.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..9ae324748d5d6e1fb9a6a32ca6cc0c87b528a584 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/altclip/__pycache__/configuration_altclip.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/audio_spectrogram_transformer/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/audio_spectrogram_transformer/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..9cc2e68cf075a587261c5059286707b4142dc6c6 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/audio_spectrogram_transformer/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/audio_spectrogram_transformer/__pycache__/configuration_audio_spectrogram_transformer.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/audio_spectrogram_transformer/__pycache__/configuration_audio_spectrogram_transformer.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..794df95a2409bb8ba64a60ad2446cc5622eb570a Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/audio_spectrogram_transformer/__pycache__/configuration_audio_spectrogram_transformer.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/auto/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/auto/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..8ef207d331859b6b6f80af01e97104e94c892073 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/auto/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/auto/__pycache__/auto_factory.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/auto/__pycache__/auto_factory.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..b2a93e69d34145389d3e0a158059321e9a140265 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/auto/__pycache__/auto_factory.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/auto/__pycache__/configuration_auto.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/auto/__pycache__/configuration_auto.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..c54f1843b8c31d6eb0511c4c292b6ea99e742043 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/auto/__pycache__/configuration_auto.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/auto/__pycache__/modeling_auto.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/auto/__pycache__/modeling_auto.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..9fd8c228ef2c066c106881ad4ee493184edbf9e8 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/auto/__pycache__/modeling_auto.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/auto/__pycache__/tokenization_auto.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/auto/__pycache__/tokenization_auto.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..5556f1e2df10af64930fb7ee33d8ee2e5506a04f Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/auto/__pycache__/tokenization_auto.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/bart/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/bart/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..029d14967db8d181d052f7444f7027df63e2cedd Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/bart/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/bart/__pycache__/configuration_bart.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/bart/__pycache__/configuration_bart.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..c42e0b973a160329affc1c91f396723e4fc392a7 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/bart/__pycache__/configuration_bart.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/barthez/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/barthez/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..4d4c11b47208b5bfe3633e09523003a878f1c43f Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/barthez/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/bartpho/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/bartpho/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..822f98f1ead85a514e4271faae9ebca4eb56f456 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/bartpho/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/beit/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/beit/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..21e9fd6b5f796795b8ccb9de963aa88d25b20108 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/beit/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/beit/__pycache__/configuration_beit.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/beit/__pycache__/configuration_beit.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..3a5d1dc4013c072482b588418b699eac4ca4b7b1 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/beit/__pycache__/configuration_beit.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/bert/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/bert/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..8a3332c451ce91d98dc939bf2f2e41271be2fe67 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/bert/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/bert/__pycache__/configuration_bert.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/bert/__pycache__/configuration_bert.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..af4292d3d4fe4693cd567996ecfc60c3c799bba6 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/bert/__pycache__/configuration_bert.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/bert/__pycache__/modeling_bert.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/bert/__pycache__/modeling_bert.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..3451ecb84eb521e6da0107b1d3b0235d56d7a7c3 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/bert/__pycache__/modeling_bert.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/bert/__pycache__/tokenization_bert.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/bert/__pycache__/tokenization_bert.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..0ae2128e48aa4e3cf7ff7e68da41fe27d126f116 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/bert/__pycache__/tokenization_bert.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/bert/__pycache__/tokenization_bert_fast.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/bert/__pycache__/tokenization_bert_fast.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..b838d5c0417d56d9a1edaeb1427f3c4682d70d1b Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/bert/__pycache__/tokenization_bert_fast.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/bert_generation/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/bert_generation/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..44748413a3b1925fac95f0fe2b9397cbe3ce2bd7 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/bert_generation/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/bert_generation/__pycache__/configuration_bert_generation.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/bert_generation/__pycache__/configuration_bert_generation.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..a401cf8c2bd622f419ad1515be97653e255ebd38 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/bert_generation/__pycache__/configuration_bert_generation.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/bert_japanese/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/bert_japanese/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..e565ffae1e86ad4080d86fe6586438d0ca378b34 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/bert_japanese/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/bertweet/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/bertweet/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..1b21de3c562da860e8658425a1dfadc35c11c089 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/bertweet/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/big_bird/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/big_bird/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..c07d7e9ab58b24a9bed8a50e3865f8803e3d1d49 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/big_bird/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/big_bird/__pycache__/configuration_big_bird.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/big_bird/__pycache__/configuration_big_bird.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..4e9e01ce79144835b6b96005bebe9dba583069ac Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/big_bird/__pycache__/configuration_big_bird.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/bigbird_pegasus/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/bigbird_pegasus/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..92e5b8952c5e0ba8313449f5c9b5d107c7654319 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/bigbird_pegasus/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/bigbird_pegasus/__pycache__/configuration_bigbird_pegasus.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/bigbird_pegasus/__pycache__/configuration_bigbird_pegasus.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..45f6021666f95c937ed48519e52350c43ea7b284 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/bigbird_pegasus/__pycache__/configuration_bigbird_pegasus.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/biogpt/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/biogpt/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..c48e268b084251abad54dea5a948fec2af67d8ce Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/biogpt/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/biogpt/__pycache__/configuration_biogpt.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/biogpt/__pycache__/configuration_biogpt.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..f3ed6a92d1bf81581a9d9bfd8a0265a6ae677b3c Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/biogpt/__pycache__/configuration_biogpt.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/bit/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/bit/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..1796628f331e274e6e71b51e4c0d92a7d94c5010 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/bit/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/bit/__pycache__/configuration_bit.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/bit/__pycache__/configuration_bit.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..cb14a4c0d23c16e0b4f12e47ddcecbac584f413f Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/bit/__pycache__/configuration_bit.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/blenderbot/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/blenderbot/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..02fc3d723ee609e061c7581d0b471f8fcd34d751 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/blenderbot/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/blenderbot/__pycache__/configuration_blenderbot.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/blenderbot/__pycache__/configuration_blenderbot.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..f59e4d9f8ae106114b5666f73861c3149467035b Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/blenderbot/__pycache__/configuration_blenderbot.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/blenderbot_small/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/blenderbot_small/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..f4c231985482e35de245116a8f4543096f05aca2 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/blenderbot_small/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/blenderbot_small/__pycache__/configuration_blenderbot_small.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/blenderbot_small/__pycache__/configuration_blenderbot_small.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..ff7b2fd18d6dd0172225cbfffd600781f3a0bf2d Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/blenderbot_small/__pycache__/configuration_blenderbot_small.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/blip/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/blip/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..5069f808e9087b2c56aa7b907fdd9f65338ab0b3 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/blip/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/blip/__pycache__/configuration_blip.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/blip/__pycache__/configuration_blip.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..5abeecdea480b9361999d8c588bfa9f8ec12bd98 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/blip/__pycache__/configuration_blip.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/blip_2/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/blip_2/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..e999f14925ea2439855aeaae735f96104f6455fa Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/blip_2/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/blip_2/__pycache__/configuration_blip_2.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/blip_2/__pycache__/configuration_blip_2.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..2cd8a399782275f7506781c8708e8312fef34f58 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/blip_2/__pycache__/configuration_blip_2.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/bloom/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/bloom/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..8df41f18869bc1ed1683eee6648ea99f95a901e2 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/bloom/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/bloom/__pycache__/configuration_bloom.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/bloom/__pycache__/configuration_bloom.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..b8d9692fb9f7fefdd82c99e1bfb796854f73f9dc Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/bloom/__pycache__/configuration_bloom.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/bort/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/bort/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..de3dcd3b28f4aed1f8a11252bf4f3b1ad503f316 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/bort/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/bridgetower/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/bridgetower/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..8fc083fd1d774a0bb00f2275d9e99b3f34049167 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/bridgetower/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/bridgetower/__pycache__/configuration_bridgetower.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/bridgetower/__pycache__/configuration_bridgetower.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..e638dacfc916178afd2cabd95d8c679a4b074a45 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/bridgetower/__pycache__/configuration_bridgetower.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/byt5/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/byt5/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..e82f5762ba649a7c12fc98319e116c7fb4a9e9f8 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/byt5/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/camembert/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/camembert/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..0ff5f21deefca4c38951b9d1d948c85706ae23b0 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/camembert/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/camembert/__pycache__/configuration_camembert.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/camembert/__pycache__/configuration_camembert.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..47a545134946fa45f74ad446fe2c5226f72dea07 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/camembert/__pycache__/configuration_camembert.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/canine/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/canine/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..36e9b2859aa52c5df22593c5461f541a61fa117c Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/canine/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/canine/__pycache__/configuration_canine.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/canine/__pycache__/configuration_canine.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..bd703fadef31c89ceda594bd60af073d54f98cb7 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/canine/__pycache__/configuration_canine.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/chinese_clip/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/chinese_clip/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..c839bab6511ce8a3fc2f0f438f8e2bf3e1ee8749 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/chinese_clip/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/chinese_clip/__pycache__/configuration_chinese_clip.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/chinese_clip/__pycache__/configuration_chinese_clip.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..115f982e0b56ecfbd97f8441062f76825dd5a9f4 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/chinese_clip/__pycache__/configuration_chinese_clip.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/clap/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/clap/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..79d581b661799e8ab3f929c93c8b98d9e20b82fa Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/clap/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/clap/__pycache__/configuration_clap.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/clap/__pycache__/configuration_clap.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..d8d4cb6c85f066c3456c7d6369ff64a16a9aed10 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/clap/__pycache__/configuration_clap.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/clip/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/clip/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..f7387d0385744a63f932fb6ad65f6b3661b44465 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/clip/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/clip/__pycache__/configuration_clip.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/clip/__pycache__/configuration_clip.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..babafe6e3feab7ba1bbd78aa35223b45e28368a3 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/clip/__pycache__/configuration_clip.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/clip/__pycache__/image_processing_clip.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/clip/__pycache__/image_processing_clip.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..8af3780740134a7f0f886aa7276192eee7ce9013 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/clip/__pycache__/image_processing_clip.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/clip/__pycache__/modeling_clip.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/clip/__pycache__/modeling_clip.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..2b8a331a95ae9249fab994719e271d46edf5f6f8 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/clip/__pycache__/modeling_clip.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/clipseg/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/clipseg/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..06d85a5e2389a3b9c18d962c72b1279d5077d5ab Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/clipseg/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/clipseg/__pycache__/configuration_clipseg.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/clipseg/__pycache__/configuration_clipseg.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..48a42779a0ec77b27f7c59a5867eef95212b4f20 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/clipseg/__pycache__/configuration_clipseg.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/codegen/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/codegen/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..32348f23572a32e36da3f995ae9955cfbb34b144 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/codegen/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/codegen/__pycache__/configuration_codegen.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/codegen/__pycache__/configuration_codegen.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..6977b0074dd79c3c2da59d71ebc770b62954570a Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/codegen/__pycache__/configuration_codegen.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/conditional_detr/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/conditional_detr/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..4cc6313488654561946d0e95b1ab1802d0375fb9 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/conditional_detr/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/conditional_detr/__pycache__/configuration_conditional_detr.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/conditional_detr/__pycache__/configuration_conditional_detr.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..8068111965433d0d04a44f47206cb5677787f8a8 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/conditional_detr/__pycache__/configuration_conditional_detr.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/convbert/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/convbert/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..d288229a352c00ffe081f9c484a8178efba19a04 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/convbert/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/convbert/__pycache__/configuration_convbert.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/convbert/__pycache__/configuration_convbert.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..58c50d6301df33fa56328a3475ec75f04d55b066 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/convbert/__pycache__/configuration_convbert.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/convnext/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/convnext/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..6af245f8e7c46c801d283ad0cef67fb6f1c6ddf9 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/convnext/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/convnext/__pycache__/configuration_convnext.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/convnext/__pycache__/configuration_convnext.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..051f54e11520e35f5197c7a09ddabedea7dd87b6 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/convnext/__pycache__/configuration_convnext.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/convnextv2/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/convnextv2/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..1e790cdb467079daf27ef35a44c9b4f7af7d95c4 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/convnextv2/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/convnextv2/__pycache__/configuration_convnextv2.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/convnextv2/__pycache__/configuration_convnextv2.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..256b16b39b1cb6c3144893eb41927ff00690015e Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/convnextv2/__pycache__/configuration_convnextv2.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/cpm/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/cpm/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..392bd5671d2565ff009eaf9d1a6787457a8bd8f4 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/cpm/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/ctrl/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/ctrl/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..ecf6ade3b0ff4b7ad39de68538b1a3435903689b Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/ctrl/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/ctrl/__pycache__/configuration_ctrl.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/ctrl/__pycache__/configuration_ctrl.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..7d25553e8e04c621d282e244a97ccc0777106915 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/ctrl/__pycache__/configuration_ctrl.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/cvt/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/cvt/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..f95a9209876d36a924fa6f4e16ea01a41b933249 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/cvt/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/cvt/__pycache__/configuration_cvt.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/cvt/__pycache__/configuration_cvt.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..cde6da745f12d64bf45f3ec729486ea81d69176b Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/cvt/__pycache__/configuration_cvt.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/data2vec/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/data2vec/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..45ceaa7bf25b646493fbde3c7846c0330cc734b3 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/data2vec/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/data2vec/__pycache__/configuration_data2vec_audio.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/data2vec/__pycache__/configuration_data2vec_audio.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..6cf5f1e4ab4993d61fa04875c646a1aaa49fb321 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/data2vec/__pycache__/configuration_data2vec_audio.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/data2vec/__pycache__/configuration_data2vec_text.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/data2vec/__pycache__/configuration_data2vec_text.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..e5018e3f9b56fd9cebd7ae20842dac604b01bc92 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/data2vec/__pycache__/configuration_data2vec_text.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/data2vec/__pycache__/configuration_data2vec_vision.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/data2vec/__pycache__/configuration_data2vec_vision.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..b5bb4067d903424603fca98ed2d0ae00c451c0bf Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/data2vec/__pycache__/configuration_data2vec_vision.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/deberta/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/deberta/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..1b2e29a29b4bdc261b89ec2f18117c50d5da1b12 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/deberta/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/deberta/__pycache__/configuration_deberta.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/deberta/__pycache__/configuration_deberta.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..4e0685b17faa11c926c0975683cfb1aa3bd0b03a Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/deberta/__pycache__/configuration_deberta.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/deberta_v2/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/deberta_v2/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..1024b2ce5e5ad138b434f7c77873480a72ee17c6 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/deberta_v2/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/deberta_v2/__pycache__/configuration_deberta_v2.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/deberta_v2/__pycache__/configuration_deberta_v2.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..6b93caa991523703be42dce775a656b42cec0773 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/deberta_v2/__pycache__/configuration_deberta_v2.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/decision_transformer/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/decision_transformer/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..cff5bef727e9659ff110b6c66ad02ff06a440f74 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/decision_transformer/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/decision_transformer/__pycache__/configuration_decision_transformer.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/decision_transformer/__pycache__/configuration_decision_transformer.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..738735ddbed400a846e7e431aa2ef93e2d78cc78 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/decision_transformer/__pycache__/configuration_decision_transformer.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/deformable_detr/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/deformable_detr/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..c4bd7ac46cdcec2da0ff05a0ee700285cb3e80bb Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/deformable_detr/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/deformable_detr/__pycache__/configuration_deformable_detr.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/deformable_detr/__pycache__/configuration_deformable_detr.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..e0313f1dfa5861c06543c24057addacc65137914 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/deformable_detr/__pycache__/configuration_deformable_detr.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/deit/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/deit/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..9579ff5fb1da703970081f67c6f4eded18810b0f Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/deit/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/deit/__pycache__/configuration_deit.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/deit/__pycache__/configuration_deit.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..6942b35fa7dbc8c1ad1c972066fb9f781e6ed208 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/deit/__pycache__/configuration_deit.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/deta/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/deta/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..8807f26733786d504b750afdbf527153a4df7206 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/deta/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/deta/__pycache__/configuration_deta.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/deta/__pycache__/configuration_deta.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..81790774e7faf600ceeb4f34b763d1ba2afff550 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/deta/__pycache__/configuration_deta.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/detr/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/detr/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..5cfb46bcd00425d95d9dd3f805c10e262ad84ac8 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/detr/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/detr/__pycache__/configuration_detr.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/detr/__pycache__/configuration_detr.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..929099bc9c2643a38db2eafa3c77c5220a545689 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/detr/__pycache__/configuration_detr.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/dialogpt/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/dialogpt/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..d1c6df6788593b0bfd62f9212e370b60a716568a Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/dialogpt/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/dinat/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/dinat/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..c66e0010639e13a44c3ce75b5b21853d78965f2a Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/dinat/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/dinat/__pycache__/configuration_dinat.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/dinat/__pycache__/configuration_dinat.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..48d3f29c8a361f5ab570d55229223f0fc264226a Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/dinat/__pycache__/configuration_dinat.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/distilbert/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/distilbert/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..ec434c11d0d7b298020c5c37d247ed98ea861efc Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/distilbert/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/distilbert/__pycache__/configuration_distilbert.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/distilbert/__pycache__/configuration_distilbert.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..207b2bc5256267498b4b158c1034cd78d48f5270 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/distilbert/__pycache__/configuration_distilbert.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/dit/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/dit/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..4f1ea6a6e45b54b23eb67756bf493f29eeb568e6 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/dit/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/donut/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/donut/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..669dbcbe1cdce09440c74c1250efef75324cb2c4 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/donut/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/donut/__pycache__/configuration_donut_swin.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/donut/__pycache__/configuration_donut_swin.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..1af952aba6f0c046410883062778d1f9833c1e1c Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/donut/__pycache__/configuration_donut_swin.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/dpr/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/dpr/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..8a2a9e90a983d88c41ef92e1265a460cfce460ff Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/dpr/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/dpr/__pycache__/configuration_dpr.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/dpr/__pycache__/configuration_dpr.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..382408bfe65efdf8ef3d97e2167fed185c378579 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/dpr/__pycache__/configuration_dpr.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/dpt/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/dpt/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..c04ef113de1d42499eb1ca1754770e3cade5f957 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/dpt/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/dpt/__pycache__/configuration_dpt.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/dpt/__pycache__/configuration_dpt.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..acace1881a3f42f7335309b7a697d32d2719a99b Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/dpt/__pycache__/configuration_dpt.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/efficientformer/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/efficientformer/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..ff02b2ca2348101ff3f3cc94d00931bcc1d873d4 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/efficientformer/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/efficientformer/__pycache__/configuration_efficientformer.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/efficientformer/__pycache__/configuration_efficientformer.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..8fa7859c298c3548508a3e10b6e4c4f64c6593f0 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/efficientformer/__pycache__/configuration_efficientformer.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/efficientnet/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/efficientnet/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..083dba36db986835adfa89dbe35b9194a170076f Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/efficientnet/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/efficientnet/__pycache__/configuration_efficientnet.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/efficientnet/__pycache__/configuration_efficientnet.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..fd87a86d1a15c26b6d23f6d9879597cb92e5b359 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/efficientnet/__pycache__/configuration_efficientnet.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/electra/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/electra/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..9e6477d6349c5e7dfbea5ca8637d4530576a4b37 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/electra/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/electra/__pycache__/configuration_electra.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/electra/__pycache__/configuration_electra.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..60947f9b66b3d4317c0d9ebe867b42e6666b4ce2 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/electra/__pycache__/configuration_electra.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/encoder_decoder/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/encoder_decoder/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..1534c0cfa74dadfdeb09e8206df86ad352658b31 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/encoder_decoder/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/encoder_decoder/__pycache__/configuration_encoder_decoder.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/encoder_decoder/__pycache__/configuration_encoder_decoder.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..3d37b20c296cba2d1046c368fc5a8c1e1d2f12d6 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/encoder_decoder/__pycache__/configuration_encoder_decoder.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/ernie/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/ernie/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..98daa910c87b3ab0ebc554c45c69325acec181f5 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/ernie/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/ernie/__pycache__/configuration_ernie.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/ernie/__pycache__/configuration_ernie.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..e5070dcde0af2dd0a1f97243e0e3432db7d75c5c Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/ernie/__pycache__/configuration_ernie.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/ernie_m/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/ernie_m/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..9554cc526c61b5f114e5dd58b7b3cb9871cd092a Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/ernie_m/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/ernie_m/__pycache__/configuration_ernie_m.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/ernie_m/__pycache__/configuration_ernie_m.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..33b419f865958d92b1fdf201e99d346a7d5fbb85 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/ernie_m/__pycache__/configuration_ernie_m.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/esm/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/esm/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..aa88642b1446e1cf7a4b51132936f9ef600892bc Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/esm/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/esm/__pycache__/configuration_esm.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/esm/__pycache__/configuration_esm.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..5cf8308f305afda210b1b0a8972942bddbeaaeab Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/esm/__pycache__/configuration_esm.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/flaubert/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/flaubert/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..cf828af34fa8fcc5a0e14b11f12220629cdc149d Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/flaubert/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/flaubert/__pycache__/configuration_flaubert.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/flaubert/__pycache__/configuration_flaubert.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..6f46f84c7ac244efee7c844faf3cbb7b63c0c700 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/flaubert/__pycache__/configuration_flaubert.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/flava/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/flava/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..861646d4033b0e4caa2e91771a7a202cd853d18a Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/flava/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/flava/__pycache__/configuration_flava.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/flava/__pycache__/configuration_flava.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..61767e36260433c64df269f611257a4bc981c264 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/flava/__pycache__/configuration_flava.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/fnet/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/fnet/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..b6c9cd86068216481b8e2c37d67a54d96493c3d9 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/fnet/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/fnet/__pycache__/configuration_fnet.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/fnet/__pycache__/configuration_fnet.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..3e9d313572c175bd1aec8491f060c3b4c820b6be Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/fnet/__pycache__/configuration_fnet.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/fsmt/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/fsmt/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..7b13e53651dd9719c9dcbb3903760e3e813cab3d Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/fsmt/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/fsmt/__pycache__/configuration_fsmt.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/fsmt/__pycache__/configuration_fsmt.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..f5d6f065830177fdf5fc822473f56a96ff87d3e7 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/fsmt/__pycache__/configuration_fsmt.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/funnel/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/funnel/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..40ce20b760a77c4b803a70dd399e8be2b2460051 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/funnel/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/funnel/__pycache__/configuration_funnel.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/funnel/__pycache__/configuration_funnel.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..fa47efb0003559ceedaa16614119b35e873381c0 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/funnel/__pycache__/configuration_funnel.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/git/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/git/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..19d6745badd3db60bf485d8aee48da3b0757eace Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/git/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/git/__pycache__/configuration_git.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/git/__pycache__/configuration_git.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..c777c1cd4bd6321c3202db9996746753a33aba37 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/git/__pycache__/configuration_git.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/glpn/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/glpn/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..3eed69e548a7ba2fb9e2ab35503472771662f142 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/glpn/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/glpn/__pycache__/configuration_glpn.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/glpn/__pycache__/configuration_glpn.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..a92b70c0a9a3aa6c9e493c6018d0998b9d0c3942 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/glpn/__pycache__/configuration_glpn.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/gpt2/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/gpt2/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..008bb4c3c4896fcb74482e8f190ca4141e2f09dd Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/gpt2/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/gpt2/__pycache__/configuration_gpt2.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/gpt2/__pycache__/configuration_gpt2.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..589cb721499394dcdcdfb8cc46acedf9a8b1ea9e Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/gpt2/__pycache__/configuration_gpt2.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/gpt2/__pycache__/modeling_gpt2.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/gpt2/__pycache__/modeling_gpt2.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..1539080fa800afec0561fee644e3badd9e98af73 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/gpt2/__pycache__/modeling_gpt2.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/gpt2/__pycache__/tokenization_gpt2.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/gpt2/__pycache__/tokenization_gpt2.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..c66ac6a1c8eab8e72a5fbc42d6d37eef7950e611 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/gpt2/__pycache__/tokenization_gpt2.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/gpt2/__pycache__/tokenization_gpt2_fast.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/gpt2/__pycache__/tokenization_gpt2_fast.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..1478293c99516521d010f91ad7dacada06217a1d Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/gpt2/__pycache__/tokenization_gpt2_fast.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/gpt_neo/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/gpt_neo/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..30befd95540fc231a495eda9070480f0d243180d Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/gpt_neo/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/gpt_neo/__pycache__/configuration_gpt_neo.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/gpt_neo/__pycache__/configuration_gpt_neo.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..722253a93c2a9e9b3eb80df687a5d9126149e149 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/gpt_neo/__pycache__/configuration_gpt_neo.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/gpt_neox/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/gpt_neox/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..91db444c3e3375afa2e29c1192c7512462b92a00 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/gpt_neox/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/gpt_neox/__pycache__/configuration_gpt_neox.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/gpt_neox/__pycache__/configuration_gpt_neox.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..1822804ff8088f1111586f156512e22f32bd558d Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/gpt_neox/__pycache__/configuration_gpt_neox.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/gpt_neox_japanese/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/gpt_neox_japanese/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..a5c8d4c4a1d6ab5885f09d67b82041c7c388cd79 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/gpt_neox_japanese/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/gpt_neox_japanese/__pycache__/configuration_gpt_neox_japanese.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/gpt_neox_japanese/__pycache__/configuration_gpt_neox_japanese.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..5e4934fa97afda680bda46dd3640d4be86779b1e Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/gpt_neox_japanese/__pycache__/configuration_gpt_neox_japanese.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/gpt_sw3/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/gpt_sw3/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..caf5f333da1e0ed73916864517c93bb3f7901819 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/gpt_sw3/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/gptj/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/gptj/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..92596731ae615d30452931bb49c1f0d981b47697 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/gptj/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/gptj/__pycache__/configuration_gptj.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/gptj/__pycache__/configuration_gptj.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..9476cb8acb92a26e577172d55f0bd7e98e13ccfd Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/gptj/__pycache__/configuration_gptj.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/gptsan_japanese/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/gptsan_japanese/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..231bf0329717555b178ad04cfc0a84d7ff7f8253 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/gptsan_japanese/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/gptsan_japanese/__pycache__/configuration_gptsan_japanese.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/gptsan_japanese/__pycache__/configuration_gptsan_japanese.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..a59a8795418887070b029631d0526b5000934fbb Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/gptsan_japanese/__pycache__/configuration_gptsan_japanese.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/graphormer/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/graphormer/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..1b4ad49b6aaea889d95cb6501b7760e192e438d2 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/graphormer/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/graphormer/__pycache__/configuration_graphormer.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/graphormer/__pycache__/configuration_graphormer.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..5060ef648352af851bf16b3c587ac8ae44ab132b Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/graphormer/__pycache__/configuration_graphormer.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/groupvit/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/groupvit/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..37b5f1908f8b6ba5a8da3ab9fd4c5c6fef973cf0 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/groupvit/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/groupvit/__pycache__/configuration_groupvit.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/groupvit/__pycache__/configuration_groupvit.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..9fb027482209248d85f8e0e7ec2503c92ae22f82 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/groupvit/__pycache__/configuration_groupvit.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/herbert/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/herbert/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..4f6d83eacfb6995fc1138fd0d1671666fb6241ff Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/herbert/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/hubert/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/hubert/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..af1ae7e7201f1d255fa44e1811515d83bcb36314 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/hubert/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/hubert/__pycache__/configuration_hubert.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/hubert/__pycache__/configuration_hubert.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..5087536389773300f7a43eba77cd2ff26e8fd386 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/hubert/__pycache__/configuration_hubert.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/ibert/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/ibert/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..7c1b57723849378fe38c05376ec2d70001a46ecc Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/ibert/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/ibert/__pycache__/configuration_ibert.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/ibert/__pycache__/configuration_ibert.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..aa20f44d41b878549b747c88a353ec6d58d0e0b0 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/ibert/__pycache__/configuration_ibert.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/imagegpt/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/imagegpt/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..80b5eea606e5e24bab0435b2c4f7081919e51a6c Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/imagegpt/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/imagegpt/__pycache__/configuration_imagegpt.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/imagegpt/__pycache__/configuration_imagegpt.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..a3f7c03b5e305ad66dcb927d456497be4af4818f Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/imagegpt/__pycache__/configuration_imagegpt.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/informer/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/informer/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..247f64ec3be9ad8b1eee86298a15f52915a810e8 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/informer/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/informer/__pycache__/configuration_informer.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/informer/__pycache__/configuration_informer.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..77d226722cafcec70c32e3647ec50f179aaa3406 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/informer/__pycache__/configuration_informer.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/jukebox/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/jukebox/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..03705c805c3d8f5fe9f95df31740d6ca4e0b55a0 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/jukebox/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/jukebox/__pycache__/configuration_jukebox.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/jukebox/__pycache__/configuration_jukebox.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..94b12c261654567e97f114a444168b206ea0ad57 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/jukebox/__pycache__/configuration_jukebox.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/layoutlm/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/layoutlm/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..20a10e092dbc5c7cecb46199a2b5452dc9dd849f Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/layoutlm/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/layoutlm/__pycache__/configuration_layoutlm.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/layoutlm/__pycache__/configuration_layoutlm.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..fd81bc1700ac399e9d0388d3e201a098c1dd19e0 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/layoutlm/__pycache__/configuration_layoutlm.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/layoutlmv2/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/layoutlmv2/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..eab5ff29a8754d5aac9e2a5ef56868f76ed361a9 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/layoutlmv2/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/layoutlmv2/__pycache__/configuration_layoutlmv2.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/layoutlmv2/__pycache__/configuration_layoutlmv2.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..028a3599b49349b2edcc0746c01775cf9749d7c9 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/layoutlmv2/__pycache__/configuration_layoutlmv2.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/layoutlmv3/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/layoutlmv3/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..25dfff7b0a2d2c59bf81e5d81ad3f29155079443 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/layoutlmv3/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/layoutlmv3/__pycache__/configuration_layoutlmv3.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/layoutlmv3/__pycache__/configuration_layoutlmv3.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..180b0d228d47a7e17cafb9597a42730847f16cc8 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/layoutlmv3/__pycache__/configuration_layoutlmv3.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/layoutxlm/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/layoutxlm/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..684f49af9485789155411ef3580a0f5b72a48885 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/layoutxlm/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/led/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/led/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..b65054b975a8637f4221f1bdf95411549d07604a Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/led/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/led/__pycache__/configuration_led.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/led/__pycache__/configuration_led.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..9623ff87520f01b8b041d76b4042524897ee3ba4 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/led/__pycache__/configuration_led.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/levit/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/levit/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..ff11b0d7537806ce748c8b8ad0e0daf99670952f Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/levit/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/levit/__pycache__/configuration_levit.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/levit/__pycache__/configuration_levit.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..e53ea65b2f94e854f0e47e75a5827ea9025fba27 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/levit/__pycache__/configuration_levit.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/lilt/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/lilt/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..841ddd5debd8d1ed644bcf8a145f399cc7387662 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/lilt/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/lilt/__pycache__/configuration_lilt.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/lilt/__pycache__/configuration_lilt.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..38bb7adea3606ca2d53a1ff2724581a410ad83b4 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/lilt/__pycache__/configuration_lilt.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/llama/__pycache__/Qformer.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/llama/__pycache__/Qformer.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..95de1814d91f30fe53e3aec1eae13fc110d6569a Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/llama/__pycache__/Qformer.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/llama/__pycache__/Qformer_lion.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/llama/__pycache__/Qformer_lion.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..72a3b08c7ef1c45a65bb0dda7b82ef1807a9abb2 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/llama/__pycache__/Qformer_lion.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/llama/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/llama/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..d278af0253e9b4edac4d6f4a1c126e997a6a2162 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/llama/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/llama/__pycache__/cavmae.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/llama/__pycache__/cavmae.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..312570cf4c39592eb011cb3d6c854ca899c4d3d9 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/llama/__pycache__/cavmae.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/llama/__pycache__/configuration_llama.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/llama/__pycache__/configuration_llama.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..68a5be72081876d0d33525e876452fca95879e81 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/llama/__pycache__/configuration_llama.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/llama/__pycache__/feature_fusion.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/llama/__pycache__/feature_fusion.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..4107c660084b00a13f2c015a69d8fb2dc5319aaf Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/llama/__pycache__/feature_fusion.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/llama/__pycache__/htsat.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/llama/__pycache__/htsat.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..e7ea81af2cab41c9831c1deb9f5536278cb5578a Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/llama/__pycache__/htsat.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/llama/__pycache__/modeling_llama.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/llama/__pycache__/modeling_llama.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..76d0bbe2abab3b51c5b75726afd886601f7f4b00 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/llama/__pycache__/modeling_llama.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/llama/__pycache__/pos_embed.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/llama/__pycache__/pos_embed.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..f88ba0500fd6c64043032bc3771713a30d01e7cb Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/llama/__pycache__/pos_embed.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/llama/__pycache__/tokenization_llama.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/llama/__pycache__/tokenization_llama.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..39f12a0195247decf2ece00daa59653558618645 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/llama/__pycache__/tokenization_llama.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/longformer/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/longformer/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..30500065025b02aed4426dd0d7feb108a530922e Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/longformer/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/longformer/__pycache__/configuration_longformer.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/longformer/__pycache__/configuration_longformer.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..07bd45749f9982ef95a59406a52883a3d9d04700 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/longformer/__pycache__/configuration_longformer.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/longt5/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/longt5/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..fbab658cb6f2386d7cb95f4f9c7b6e2fa61db6c5 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/longt5/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/longt5/__pycache__/configuration_longt5.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/longt5/__pycache__/configuration_longt5.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..1364fff79e0bd743496c807555a294765b66dda1 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/longt5/__pycache__/configuration_longt5.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/luke/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/luke/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..c1f67a87f04904c7291e7e061f423941185038b3 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/luke/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/luke/__pycache__/configuration_luke.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/luke/__pycache__/configuration_luke.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..600b119823190bb43cbda4ced36b2cde6e596565 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/luke/__pycache__/configuration_luke.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/lxmert/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/lxmert/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..3338071fc2312e7e032c743c53e830559386bee6 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/lxmert/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/lxmert/__pycache__/configuration_lxmert.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/lxmert/__pycache__/configuration_lxmert.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..3a63bd6f4364a2a8386d2b649113839b108c929c Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/lxmert/__pycache__/configuration_lxmert.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/m2m_100/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/m2m_100/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..e4fc787fea62fa1cf3ff2508debb76842b96edc2 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/m2m_100/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/m2m_100/__pycache__/configuration_m2m_100.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/m2m_100/__pycache__/configuration_m2m_100.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..6771c962434e8395391e9743e629192072676a5c Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/m2m_100/__pycache__/configuration_m2m_100.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/marian/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/marian/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..43b4c1276ddc3a03d8a4331b6d6b431e19e2561c Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/marian/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/marian/__pycache__/configuration_marian.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/marian/__pycache__/configuration_marian.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..09e0a0cd50cabeb8705246817b08a295be64277c Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/marian/__pycache__/configuration_marian.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/markuplm/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/markuplm/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..cb1466e24631c3ae284ac71a0d840546614d2f24 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/markuplm/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/markuplm/__pycache__/configuration_markuplm.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/markuplm/__pycache__/configuration_markuplm.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..dd5109d00afc466827a89aa81ad6f48ab3d2243c Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/markuplm/__pycache__/configuration_markuplm.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/mask2former/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/mask2former/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..c103bf3d10106656f0730169c82022a94dc6b1ab Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/mask2former/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/mask2former/__pycache__/configuration_mask2former.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/mask2former/__pycache__/configuration_mask2former.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..cd0694f99ed8fecb3591e96f62a70de30748fbfd Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/mask2former/__pycache__/configuration_mask2former.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/maskformer/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/maskformer/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..35f87d0c8a10fb6fc48d7e8340090daf44b82424 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/maskformer/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/maskformer/__pycache__/configuration_maskformer.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/maskformer/__pycache__/configuration_maskformer.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..bc3e5ac55121fa04292c367195ca400534fb853a Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/maskformer/__pycache__/configuration_maskformer.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/maskformer/__pycache__/configuration_maskformer_swin.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/maskformer/__pycache__/configuration_maskformer_swin.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..f13b5ac10b086eee144d3854a6e24e047cb9b067 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/maskformer/__pycache__/configuration_maskformer_swin.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/mbart/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/mbart/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..bb58b3ce5caeb1fd49782e212f912e11c31528e7 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/mbart/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/mbart/__pycache__/configuration_mbart.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/mbart/__pycache__/configuration_mbart.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..4b9bdcd89557a87d478bc1db0d26caf946bb42d6 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/mbart/__pycache__/configuration_mbart.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/mbart50/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/mbart50/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..fddf1913b9ccf4f139deaa7e3734eea603595105 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/mbart50/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/mctct/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/mctct/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..74637c8ed4765f060be79cb2191e994a2af32e2a Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/mctct/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/mctct/__pycache__/configuration_mctct.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/mctct/__pycache__/configuration_mctct.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..67caf8aaf15243419d7cd67a7e844be071a4ab4c Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/mctct/__pycache__/configuration_mctct.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/mega/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/mega/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..c960c1f4274711aec560462d5e26b7a7dfd407d0 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/mega/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/mega/__pycache__/configuration_mega.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/mega/__pycache__/configuration_mega.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..b15ca19fa4954bc9bfa27b82b84ca34aa9cd5853 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/mega/__pycache__/configuration_mega.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/megatron_bert/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/megatron_bert/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..1f1ab5ed33af9986724589f3996f548c0f0102bb Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/megatron_bert/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/megatron_bert/__pycache__/configuration_megatron_bert.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/megatron_bert/__pycache__/configuration_megatron_bert.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..3a16d445603f1f7a27a1ecf73b2cd6aecace83da Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/megatron_bert/__pycache__/configuration_megatron_bert.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/megatron_gpt2/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/megatron_gpt2/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..ecdbaaa6e00e48092a50b2bb70dda685727cd263 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/megatron_gpt2/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/mgp_str/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/mgp_str/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..c36defa639059a3479a78772944b2c3ec9e57652 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/mgp_str/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/mgp_str/__pycache__/configuration_mgp_str.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/mgp_str/__pycache__/configuration_mgp_str.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..16cb92e14c87ffcf7e0130b3c846f81ff8988899 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/mgp_str/__pycache__/configuration_mgp_str.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/mluke/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/mluke/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..d90ee1a2b34f392ed23f6c8f1ef8e6defdc33179 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/mluke/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/mmbt/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/mmbt/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..2a8dd6cc467042f9367d061d6d6108354359bbd0 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/mmbt/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/mobilebert/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/mobilebert/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..c5dc5da5c7812e9191a406cf4a2a0b3d968f6562 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/mobilebert/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/mobilebert/__pycache__/configuration_mobilebert.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/mobilebert/__pycache__/configuration_mobilebert.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..967c04fa42bfac89b243401c027acd26534b5b09 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/mobilebert/__pycache__/configuration_mobilebert.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/mobilenet_v1/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/mobilenet_v1/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..f7bc74122503d93da0e6f5d2b63d1e3c6e723714 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/mobilenet_v1/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/mobilenet_v1/__pycache__/configuration_mobilenet_v1.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/mobilenet_v1/__pycache__/configuration_mobilenet_v1.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..555789947df8ed15e2d188912ead0b6174170db4 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/mobilenet_v1/__pycache__/configuration_mobilenet_v1.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/mobilenet_v2/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/mobilenet_v2/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..917518ff5c20cae118ce60e714204b5acbd5ff54 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/mobilenet_v2/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/mobilenet_v2/__pycache__/configuration_mobilenet_v2.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/mobilenet_v2/__pycache__/configuration_mobilenet_v2.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..c9ed6fdc3bf4e81f9027e38c44118e56a44b915a Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/mobilenet_v2/__pycache__/configuration_mobilenet_v2.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/mobilevit/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/mobilevit/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..c0bde0786a6d715365661d845cb7ee2d0a50bb01 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/mobilevit/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/mobilevit/__pycache__/configuration_mobilevit.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/mobilevit/__pycache__/configuration_mobilevit.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..e24a6458084839ef031e584670ef385f901f8c69 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/mobilevit/__pycache__/configuration_mobilevit.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/mpnet/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/mpnet/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..3d3eab0d0e83d86b9b39ca4e24e0930594e90a2c Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/mpnet/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/mpnet/__pycache__/configuration_mpnet.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/mpnet/__pycache__/configuration_mpnet.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..b3f8481802af1e2769fe36fc223730af540ab27e Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/mpnet/__pycache__/configuration_mpnet.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/mt5/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/mt5/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..3beb6f48c9cdd09974db2f5b6065e9ab7fe712e2 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/mt5/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/mt5/__pycache__/configuration_mt5.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/mt5/__pycache__/configuration_mt5.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..f35301f455bf734b34a70906541ec334c77b1aaa Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/mt5/__pycache__/configuration_mt5.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/mvp/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/mvp/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..91b864ef155b12bacd301422ad0629e85e3897a5 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/mvp/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/mvp/__pycache__/configuration_mvp.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/mvp/__pycache__/configuration_mvp.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..e64eca63afebd45693786d1108acb63a7c4569bd Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/mvp/__pycache__/configuration_mvp.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/nat/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/nat/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..4036558aa8127cecae5a12ed3a860013504e91cb Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/nat/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/nat/__pycache__/configuration_nat.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/nat/__pycache__/configuration_nat.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..f9a580d633d48ea926f3cbe06e4df6d83bcccf7c Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/nat/__pycache__/configuration_nat.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/nezha/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/nezha/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..29b9c4295589a507afbb6af706d99bf36b4859c2 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/nezha/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/nezha/__pycache__/configuration_nezha.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/nezha/__pycache__/configuration_nezha.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..f3c46578d51d1afd163ca50cd798a2ca2d31c235 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/nezha/__pycache__/configuration_nezha.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/nllb/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/nllb/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..ac3145dee452d69b3a6d7a242897b710d48e7c48 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/nllb/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/nllb_moe/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/nllb_moe/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..907a34fa0990b9545b659f872066fc14fde288e6 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/nllb_moe/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/nllb_moe/__pycache__/configuration_nllb_moe.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/nllb_moe/__pycache__/configuration_nllb_moe.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..fc0579a1e081fc15ff4a84c3931c97db331316bd Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/nllb_moe/__pycache__/configuration_nllb_moe.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/nystromformer/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/nystromformer/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..b50071ee32c165a030fbe9fc261f92385a48b006 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/nystromformer/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/nystromformer/__pycache__/configuration_nystromformer.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/nystromformer/__pycache__/configuration_nystromformer.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..90664b7ff8ab611e92226275afea759f1a9bb8ec Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/nystromformer/__pycache__/configuration_nystromformer.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/oneformer/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/oneformer/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..e3163ac2711f0bc5c4a14df74d617e464a16a8e3 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/oneformer/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/oneformer/__pycache__/configuration_oneformer.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/oneformer/__pycache__/configuration_oneformer.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..894ad096c400c4b189d992264a54bfa8274db8ab Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/oneformer/__pycache__/configuration_oneformer.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/openai/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/openai/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..62cbe7dd85deed608a895bb98d016cbd7f542a4d Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/openai/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/openai/__pycache__/configuration_openai.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/openai/__pycache__/configuration_openai.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..aff2a51728b0ffb945d9d60a0c5458ca64aa0c3b Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/openai/__pycache__/configuration_openai.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/opt/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/opt/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..393961ac7ec4202fd052cc2e2e3f8573d3aba86b Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/opt/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/opt/__pycache__/configuration_opt.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/opt/__pycache__/configuration_opt.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..51f3dbb50605a0887179b0ffb4f0682069573b89 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/opt/__pycache__/configuration_opt.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/owlvit/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/owlvit/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..3b1d327e4c2bd99942f5ab18fed78e51b70ceeb7 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/owlvit/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/owlvit/__pycache__/configuration_owlvit.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/owlvit/__pycache__/configuration_owlvit.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..ad946bdbc65507b09489f430293094585fde0dff Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/owlvit/__pycache__/configuration_owlvit.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/pegasus/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/pegasus/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..1784e14ab0d709b0f7dfa05b4fa898dfbccfd190 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/pegasus/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/pegasus/__pycache__/configuration_pegasus.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/pegasus/__pycache__/configuration_pegasus.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..60eb8e7d2f03e58df11d37f53572000a1cc789f7 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/pegasus/__pycache__/configuration_pegasus.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/pegasus_x/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/pegasus_x/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..67cabee05904200fafa5c350962323725c8acc4e Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/pegasus_x/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/pegasus_x/__pycache__/configuration_pegasus_x.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/pegasus_x/__pycache__/configuration_pegasus_x.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..71c92d79501c475c5d5b8bc0ce04711b26fe5d12 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/pegasus_x/__pycache__/configuration_pegasus_x.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/perceiver/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/perceiver/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..e1f9bd0f5581b20e6f7b61c992e7e77759e690f9 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/perceiver/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/perceiver/__pycache__/configuration_perceiver.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/perceiver/__pycache__/configuration_perceiver.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..0a039e71bd47b96b02d1ccc0228a10a13d92e739 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/perceiver/__pycache__/configuration_perceiver.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/phobert/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/phobert/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..18620a4bf860b3c413eb70b10b98783a78ead3f1 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/phobert/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/pix2struct/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/pix2struct/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..fd9f18fae3c7c74029c920b08d8c90f5d89239dd Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/pix2struct/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/plbart/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/plbart/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..124570afa489be7d31b7bcf8182e0905e33625bb Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/plbart/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/plbart/__pycache__/configuration_plbart.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/plbart/__pycache__/configuration_plbart.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..45325d25944aab7a64de59f9f13d94106fa00cea Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/plbart/__pycache__/configuration_plbart.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/poolformer/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/poolformer/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..3b712a987aeec95b39d6ba55f1dd68ca18ffa6c5 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/poolformer/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/poolformer/__pycache__/configuration_poolformer.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/poolformer/__pycache__/configuration_poolformer.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..cf00b16faccf146f3a7f34fcfb9b1fb5c024aabf Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/poolformer/__pycache__/configuration_poolformer.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/prophetnet/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/prophetnet/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..881c19ce766e669946d1730c7e2ad13688f0c1aa Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/prophetnet/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/prophetnet/__pycache__/configuration_prophetnet.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/prophetnet/__pycache__/configuration_prophetnet.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..f2c1a95a724639fac5511751562a2b01c821c078 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/prophetnet/__pycache__/configuration_prophetnet.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/qdqbert/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/qdqbert/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..dfc7f12e1fae987ff4237f390cc312ba2aa0473e Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/qdqbert/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/qdqbert/__pycache__/configuration_qdqbert.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/qdqbert/__pycache__/configuration_qdqbert.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..c8e2b1d18528c5b23e5f39206f5afc091b80df63 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/qdqbert/__pycache__/configuration_qdqbert.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/rag/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/rag/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..260d52d7ab5544437ac35c047452938f0134c9c0 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/rag/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/realm/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/realm/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..72ae93fd2c939e85648c10cf8d642e3788e79389 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/realm/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/reformer/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/reformer/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..32ec4667db23854a6b41f5b9927cf8b2e97bd459 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/reformer/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/reformer/__pycache__/configuration_reformer.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/reformer/__pycache__/configuration_reformer.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..ed4e2fc1c6047290e4d9e9ab1ea67957af85b52e Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/reformer/__pycache__/configuration_reformer.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/regnet/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/regnet/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..ee712122701da4ccfae4f809af87b6d6c391a89e Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/regnet/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/regnet/__pycache__/configuration_regnet.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/regnet/__pycache__/configuration_regnet.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..e9c93730b6ee59ecc1340196cad9e6b1fcbe4af1 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/regnet/__pycache__/configuration_regnet.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/rembert/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/rembert/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..d6206531830d5f5bca4dc1b469fc3bc6b2d86ff4 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/rembert/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/rembert/__pycache__/configuration_rembert.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/rembert/__pycache__/configuration_rembert.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..9e27c61067d5402bdc8027758f1f30c6f9cae6a7 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/rembert/__pycache__/configuration_rembert.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/resnet/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/resnet/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..7035924d4d0809c2c4fd7728960a4ef70b722db9 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/resnet/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/resnet/__pycache__/configuration_resnet.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/resnet/__pycache__/configuration_resnet.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..740252034dc15472653f638769ffd946fcecbdb4 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/resnet/__pycache__/configuration_resnet.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/retribert/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/retribert/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..6b0a52ff1f47c47685a472bfea6bdc1f35017fab Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/retribert/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/retribert/__pycache__/configuration_retribert.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/retribert/__pycache__/configuration_retribert.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..637033b179a5277a1698a762c0db6a937d530f57 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/retribert/__pycache__/configuration_retribert.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/roberta/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/roberta/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..2fce160b6780dff031632908dbf6201493fde1f5 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/roberta/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/roberta/__pycache__/configuration_roberta.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/roberta/__pycache__/configuration_roberta.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..a2dea3ea93f42889511f4e6ad4092083e50c8426 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/roberta/__pycache__/configuration_roberta.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/roberta_prelayernorm/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/roberta_prelayernorm/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..641bcede1d25db0a92db060701af8047b2336800 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/roberta_prelayernorm/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/roberta_prelayernorm/__pycache__/configuration_roberta_prelayernorm.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/roberta_prelayernorm/__pycache__/configuration_roberta_prelayernorm.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..582e99c3396fb0652def9a89d0386f905d8f3cb6 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/roberta_prelayernorm/__pycache__/configuration_roberta_prelayernorm.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/roc_bert/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/roc_bert/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..5bbce12b45441f2d0f2caf77e274b64c62b48981 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/roc_bert/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/roc_bert/__pycache__/configuration_roc_bert.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/roc_bert/__pycache__/configuration_roc_bert.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..345248e5d60a6e6b756a0469f7ae5517e112c626 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/roc_bert/__pycache__/configuration_roc_bert.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/roformer/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/roformer/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..f1018ac40cd257c7351cc33f86fc55c5c7a124d9 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/roformer/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/roformer/__pycache__/configuration_roformer.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/roformer/__pycache__/configuration_roformer.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..28fc55879208270439c61e95bbdd14e487bac2f1 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/roformer/__pycache__/configuration_roformer.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/segformer/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/segformer/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..c6f85337362105ff2fd1eb8c41621fa5035a04a3 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/segformer/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/segformer/__pycache__/configuration_segformer.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/segformer/__pycache__/configuration_segformer.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..c8b906eba874bca4e7bcc5d968cb918f17b42d65 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/segformer/__pycache__/configuration_segformer.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/sew/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/sew/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..7b21faf6f1d7f8d68f396134db61e8c464476c98 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/sew/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/sew/__pycache__/configuration_sew.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/sew/__pycache__/configuration_sew.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..f2070bc4de22eed3053e9f911008ccf0a8b3f069 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/sew/__pycache__/configuration_sew.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/sew_d/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/sew_d/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..470388db671b04ab2a7baa94e7f54ac552d40d15 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/sew_d/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/sew_d/__pycache__/configuration_sew_d.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/sew_d/__pycache__/configuration_sew_d.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..3107b3d9d998355f93080920579c6fb521be8654 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/sew_d/__pycache__/configuration_sew_d.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/speech_encoder_decoder/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/speech_encoder_decoder/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..0fb9eee822e23d9a5ac402bdd176d51bb4307a3d Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/speech_encoder_decoder/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/speech_to_text/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/speech_to_text/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..5b21838b191de8b59f615077883c283c500ab2e7 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/speech_to_text/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/speech_to_text/__pycache__/configuration_speech_to_text.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/speech_to_text/__pycache__/configuration_speech_to_text.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..3291cbbd8453e596c37ad44b366c6c40bc5aedb4 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/speech_to_text/__pycache__/configuration_speech_to_text.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/speech_to_text_2/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/speech_to_text_2/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..fc415c0160c604b58522a08b9318e65e80995e8a Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/speech_to_text_2/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/speech_to_text_2/__pycache__/configuration_speech_to_text_2.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/speech_to_text_2/__pycache__/configuration_speech_to_text_2.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..bc60b4672844aec320b590599e37163cb02b6ffb Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/speech_to_text_2/__pycache__/configuration_speech_to_text_2.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/speecht5/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/speecht5/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..cad297e921ae4eef0ed9c3a70d8d273633f6c5f5 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/speecht5/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/speecht5/__pycache__/configuration_speecht5.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/speecht5/__pycache__/configuration_speecht5.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..01dae9fb40f723a487179daf472f2ec02e3f9c7c Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/speecht5/__pycache__/configuration_speecht5.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/splinter/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/splinter/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..e91003306d978cd1b5af0025c1d0de1f7798612d Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/splinter/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/splinter/__pycache__/configuration_splinter.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/splinter/__pycache__/configuration_splinter.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..4c31f6dcf1315aa1dd74d2634f4bb00bbcaeb4c8 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/splinter/__pycache__/configuration_splinter.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/squeezebert/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/squeezebert/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..20c09b013feba0ec86382994d22e528ab1cd18a7 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/squeezebert/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/squeezebert/__pycache__/configuration_squeezebert.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/squeezebert/__pycache__/configuration_squeezebert.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..621450c302a5b29b2f298ef39d23ace9195af5e5 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/squeezebert/__pycache__/configuration_squeezebert.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/swin/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/swin/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..b6103cb55ce663fc7a5943e30d8fc7eecb27f7ac Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/swin/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/swin/__pycache__/configuration_swin.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/swin/__pycache__/configuration_swin.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..ea1091dc67da416fb74dabc4a35ff7ac79033da6 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/swin/__pycache__/configuration_swin.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/swin2sr/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/swin2sr/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..fbd962ec3add316bd73574c256a484a5e826a53e Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/swin2sr/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/swin2sr/__pycache__/configuration_swin2sr.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/swin2sr/__pycache__/configuration_swin2sr.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..274b86b83ac8c17c20dc3362cff3b94e9ff27668 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/swin2sr/__pycache__/configuration_swin2sr.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/swinv2/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/swinv2/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..bababf2a1bae586302dd932b4082fa87a6edcb87 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/swinv2/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/swinv2/__pycache__/configuration_swinv2.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/swinv2/__pycache__/configuration_swinv2.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..20ab6490230667971fa4103dcd13f77599de0053 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/swinv2/__pycache__/configuration_swinv2.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/switch_transformers/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/switch_transformers/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..4994cf0dbcc3942db150c450b9cfc536e3bc6cdd Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/switch_transformers/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/switch_transformers/__pycache__/configuration_switch_transformers.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/switch_transformers/__pycache__/configuration_switch_transformers.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..237b45c80acbb735df43c630f11e5d279aaa579e Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/switch_transformers/__pycache__/configuration_switch_transformers.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/t5/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/t5/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..fcc3993835c3aa8029abd4f7b4c7be228c9902f0 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/t5/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/t5/__pycache__/configuration_t5.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/t5/__pycache__/configuration_t5.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..76949aab2d85ba1d5c5ceedea4286c5dafc0b708 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/t5/__pycache__/configuration_t5.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/t5/__pycache__/tokenization_t5.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/t5/__pycache__/tokenization_t5.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..c29e0aa9215544625f539b68bda02aac7c299d0c Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/t5/__pycache__/tokenization_t5.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/t5/__pycache__/tokenization_t5_fast.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/t5/__pycache__/tokenization_t5_fast.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..2f5e2a4bfae0ae997ff261689f2252c6c04a4a4f Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/t5/__pycache__/tokenization_t5_fast.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/table_transformer/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/table_transformer/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..40d552b239a06223f745f428b9889dd2166a242a Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/table_transformer/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/table_transformer/__pycache__/configuration_table_transformer.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/table_transformer/__pycache__/configuration_table_transformer.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..b01eed10e1b74719d23ac6bd2ab4eb48e92059ec Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/table_transformer/__pycache__/configuration_table_transformer.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/tapas/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/tapas/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..cc2e0b431b6c85d761c33d686641d9c72951f10e Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/tapas/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/tapas/__pycache__/configuration_tapas.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/tapas/__pycache__/configuration_tapas.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..9b49b6924d18da0f52487063a97727e90588e8c4 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/tapas/__pycache__/configuration_tapas.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/tapex/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/tapex/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..0ba08cb76fb0d3deba7a476d2c9af2a5d9cd9009 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/tapex/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/time_series_transformer/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/time_series_transformer/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..06391c580ad62844db161929287691c7124564f8 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/time_series_transformer/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/time_series_transformer/__pycache__/configuration_time_series_transformer.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/time_series_transformer/__pycache__/configuration_time_series_transformer.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..fc8f2554195ed94684cf10304051000ef5ffea35 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/time_series_transformer/__pycache__/configuration_time_series_transformer.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/timesformer/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/timesformer/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..794462213822341a4cdaef7ff49fb9f8701f4cc4 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/timesformer/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/timesformer/__pycache__/configuration_timesformer.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/timesformer/__pycache__/configuration_timesformer.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..ddcc56785cfa19938da560b7a16200ea9e9224fd Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/timesformer/__pycache__/configuration_timesformer.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/trajectory_transformer/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/trajectory_transformer/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..f51f16966b6a983fe24c186abaec1589a0c1a25a Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/trajectory_transformer/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/trajectory_transformer/__pycache__/configuration_trajectory_transformer.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/trajectory_transformer/__pycache__/configuration_trajectory_transformer.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..40eb262aa4244dbb32bf60acb16712b715b46487 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/trajectory_transformer/__pycache__/configuration_trajectory_transformer.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/transfo_xl/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/transfo_xl/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..4a2cb92bafc7eed68f5626ee9761c954d7e69387 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/transfo_xl/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/transfo_xl/__pycache__/configuration_transfo_xl.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/transfo_xl/__pycache__/configuration_transfo_xl.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..3fb31757e30110d9f1d50a4557ed228d36a2bdab Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/transfo_xl/__pycache__/configuration_transfo_xl.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/trocr/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/trocr/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..e7d1f65064336778732ddef4319b8cbc8ef4c0ed Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/trocr/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/trocr/__pycache__/configuration_trocr.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/trocr/__pycache__/configuration_trocr.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..caceb8db77fd69f4a836e2b846b861452ad5a483 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/trocr/__pycache__/configuration_trocr.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/tvlt/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/tvlt/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..9b5ce74a0a60c7e15bedd8dc6b86c9cc92153120 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/tvlt/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/tvlt/__pycache__/configuration_tvlt.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/tvlt/__pycache__/configuration_tvlt.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..0c37524dab0646215a263b9f95a8710b7e81eedf Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/tvlt/__pycache__/configuration_tvlt.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/unispeech/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/unispeech/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..290ab714be73830a189eff01e43892fd3f64cc2f Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/unispeech/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/unispeech/__pycache__/configuration_unispeech.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/unispeech/__pycache__/configuration_unispeech.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..ec80e7c5d3580df8eaa098002fdbd13944565036 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/unispeech/__pycache__/configuration_unispeech.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/unispeech_sat/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/unispeech_sat/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..0a9c9ed7ffcecc0a842e5b7e9dfc8d5628ee07c0 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/unispeech_sat/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/unispeech_sat/__pycache__/configuration_unispeech_sat.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/unispeech_sat/__pycache__/configuration_unispeech_sat.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..4cab00c8f4026c2d776ced68c39e98737e4449b6 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/unispeech_sat/__pycache__/configuration_unispeech_sat.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/upernet/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/upernet/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..d2500a6a0bbc058eba26eae26e192aa21efc40d0 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/upernet/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/van/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/van/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..80acda5c8e7bda5af222ff51925170664d3fea65 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/van/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/van/__pycache__/configuration_van.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/van/__pycache__/configuration_van.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..813b6b18d7b741e6e8bcad22fc4c680c3e97e092 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/van/__pycache__/configuration_van.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/videomae/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/videomae/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..40f7e0c23970115113d50853896ab78e0c4c2aaf Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/videomae/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/videomae/__pycache__/configuration_videomae.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/videomae/__pycache__/configuration_videomae.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..d966b8de8c2fe6d7c7a683a21783a08af903e7c7 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/videomae/__pycache__/configuration_videomae.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/vilt/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/vilt/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..a3ad14911fba805bfd87398bc82426ca80911479 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/vilt/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/vilt/__pycache__/configuration_vilt.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/vilt/__pycache__/configuration_vilt.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..9c0cb8422b4f6f842cd0633154b8276bd82907ec Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/vilt/__pycache__/configuration_vilt.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/vision_encoder_decoder/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/vision_encoder_decoder/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..d47411f9cafe3d870ba565b6f2426ccff2ea4037 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/vision_encoder_decoder/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/vision_text_dual_encoder/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/vision_text_dual_encoder/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..d1db5d53f881883898c9ce2610d17a2327b87fd1 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/vision_text_dual_encoder/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/vision_text_dual_encoder/__pycache__/configuration_vision_text_dual_encoder.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/vision_text_dual_encoder/__pycache__/configuration_vision_text_dual_encoder.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..ad5200554938d7c3d1e6f2037b76d62356dd49f2 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/vision_text_dual_encoder/__pycache__/configuration_vision_text_dual_encoder.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/visual_bert/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/visual_bert/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..281f070369e4a44c9d10dcd94b2ba0fcc820a221 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/visual_bert/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/visual_bert/__pycache__/configuration_visual_bert.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/visual_bert/__pycache__/configuration_visual_bert.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..b73c3a3d540c92b453eb7d08713dd0e99ad1f227 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/visual_bert/__pycache__/configuration_visual_bert.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/vit/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/vit/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..72be7bbc6b38b22016a0e1a2c4b9194aa3eef301 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/vit/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/vit/__pycache__/configuration_vit.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/vit/__pycache__/configuration_vit.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..a280ac7bb85de70a33ed3a4c3c2eef4b5daf352d Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/vit/__pycache__/configuration_vit.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/vit_hybrid/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/vit_hybrid/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..f67b16dc36a5547fd21409626a2db46799f74077 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/vit_hybrid/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/vit_hybrid/__pycache__/configuration_vit_hybrid.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/vit_hybrid/__pycache__/configuration_vit_hybrid.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..6f588dbf15d961e52712b48c5252eef9bebe9341 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/vit_hybrid/__pycache__/configuration_vit_hybrid.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/vit_mae/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/vit_mae/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..88ff0a44effbca597664de8b1a3083349774dd1e Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/vit_mae/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/vit_mae/__pycache__/configuration_vit_mae.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/vit_mae/__pycache__/configuration_vit_mae.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..1b205ebc3963930c8571c40fddebafc5e61e0ffe Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/vit_mae/__pycache__/configuration_vit_mae.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/vit_msn/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/vit_msn/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..778e360a67194ec2572207f53041bf9f556135db Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/vit_msn/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/vit_msn/__pycache__/configuration_vit_msn.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/vit_msn/__pycache__/configuration_vit_msn.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..408ab3e341ad534de50ca37e0cff388f96a23dea Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/vit_msn/__pycache__/configuration_vit_msn.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/wav2vec2/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/wav2vec2/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..87ff70676cfe798c06aa77542053948e8408d19d Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/wav2vec2/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/wav2vec2/__pycache__/configuration_wav2vec2.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/wav2vec2/__pycache__/configuration_wav2vec2.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..0624bd44edf3a82a91b09898867604476725db50 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/wav2vec2/__pycache__/configuration_wav2vec2.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/wav2vec2_conformer/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/wav2vec2_conformer/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..4e65d3b8e7b73416509fecaf311774061299fb60 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/wav2vec2_conformer/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/wav2vec2_conformer/__pycache__/configuration_wav2vec2_conformer.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/wav2vec2_conformer/__pycache__/configuration_wav2vec2_conformer.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..ce7c4cc5ac1e448b2ae59ad937ef813f56ca2671 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/wav2vec2_conformer/__pycache__/configuration_wav2vec2_conformer.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/wav2vec2_phoneme/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/wav2vec2_phoneme/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..3da8f36ea04846938e4216f0c14b85b920c5447a Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/wav2vec2_phoneme/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/wav2vec2_with_lm/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/wav2vec2_with_lm/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..bc93b31e8e87ffc2fa328b0120d1cb9386492a9d Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/wav2vec2_with_lm/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/wavlm/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/wavlm/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..23c8c95aa5520d953f7d1cbeb2ba54abdb489558 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/wavlm/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/wavlm/__pycache__/configuration_wavlm.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/wavlm/__pycache__/configuration_wavlm.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..865465aa20148c6a12f326477f60eac7ad941449 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/wavlm/__pycache__/configuration_wavlm.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/whisper/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/whisper/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..70c7faa40edef7030c431639b162dc52ff782e95 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/whisper/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/whisper/__pycache__/configuration_whisper.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/whisper/__pycache__/configuration_whisper.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..dba27b14e60f19260e2db5208362e42d4909924a Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/whisper/__pycache__/configuration_whisper.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/x_clip/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/x_clip/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..826c95d37212063127ad39a65514c688490f54ad Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/x_clip/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/x_clip/__pycache__/configuration_x_clip.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/x_clip/__pycache__/configuration_x_clip.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..c79d089fb8b692d01bc6aa926ff0e46b27ce9677 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/x_clip/__pycache__/configuration_x_clip.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/xglm/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/xglm/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..3ea3202308ea452682dd886b37f9280bd19e5d1e Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/xglm/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/xglm/__pycache__/configuration_xglm.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/xglm/__pycache__/configuration_xglm.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..9460ea027db0def4bc37da2120c02e78176bf277 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/xglm/__pycache__/configuration_xglm.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/xlm/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/xlm/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..25199a8d0216598d426d76ea8c835488457d82fa Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/xlm/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/xlm/__pycache__/configuration_xlm.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/xlm/__pycache__/configuration_xlm.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..db0bff5436f340ecbda17ff6010607555014223d Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/xlm/__pycache__/configuration_xlm.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/xlm_prophetnet/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/xlm_prophetnet/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..5f14efe2b9574b14b944e0cf69a30aaa94c00c95 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/xlm_prophetnet/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/xlm_prophetnet/__pycache__/configuration_xlm_prophetnet.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/xlm_prophetnet/__pycache__/configuration_xlm_prophetnet.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..c64cba1c52ad16da5eace6211ba70a832244b369 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/xlm_prophetnet/__pycache__/configuration_xlm_prophetnet.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/xlm_roberta/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/xlm_roberta/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..19dce75b6060868e75c4905459b92e314dfa6c2a Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/xlm_roberta/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/xlm_roberta/__pycache__/configuration_xlm_roberta.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/xlm_roberta/__pycache__/configuration_xlm_roberta.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..d8da30850ca86653aa353d19d8d3485e2deb1351 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/xlm_roberta/__pycache__/configuration_xlm_roberta.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/xlm_roberta_xl/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/xlm_roberta_xl/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..6a25b32276c7ad62f1b7cd49246a9b3a721f3119 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/xlm_roberta_xl/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/xlm_roberta_xl/__pycache__/configuration_xlm_roberta_xl.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/xlm_roberta_xl/__pycache__/configuration_xlm_roberta_xl.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..02ea6ad435726112fd16f4f9fb7c6879bfacfba2 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/xlm_roberta_xl/__pycache__/configuration_xlm_roberta_xl.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/xlnet/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/xlnet/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..95ff472be679371d7d4fed51b57faea9cfaa4976 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/xlnet/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/xlnet/__pycache__/configuration_xlnet.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/xlnet/__pycache__/configuration_xlnet.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..5d04b5d9f5f57c023e4db3651c41cca51f719f13 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/xlnet/__pycache__/configuration_xlnet.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/xmod/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/xmod/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..1cd01158f0029f5f811a262b97da5ddbd40001eb Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/xmod/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/xmod/__pycache__/configuration_xmod.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/xmod/__pycache__/configuration_xmod.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..3055a2646e1c79334ec29176d5fb31c48dcd3ac8 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/xmod/__pycache__/configuration_xmod.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/yolos/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/yolos/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..51649913fe0d9015ea60fbbc5ef87d5832f52cd4 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/yolos/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/yolos/__pycache__/configuration_yolos.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/yolos/__pycache__/configuration_yolos.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..42a7050c06199c618a6389fa487b31e2e22e316e Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/yolos/__pycache__/configuration_yolos.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/yoso/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/yoso/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..24a0d75453a9f6df2c49917793fd6fe15eb8d089 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/yoso/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/models/yoso/__pycache__/configuration_yoso.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/models/yoso/__pycache__/configuration_yoso.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..d829f07fab6e047fdef62d044e24c35f7106a65b Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/models/yoso/__pycache__/configuration_yoso.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/onnx/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/onnx/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..7616a8f45cb22315716078cda48554d601b2d507 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/onnx/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/onnx/__pycache__/config.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/onnx/__pycache__/config.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..ce782f8cac04c176bf40d1b46e46b5aa0635566d Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/onnx/__pycache__/config.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/onnx/__pycache__/utils.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/onnx/__pycache__/utils.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..193f36e7a4ec6a90f2e0dff3a3f9050ac1ce2c56 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/onnx/__pycache__/utils.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/utils/__pycache__/__init__.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/utils/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..7fa3f95bdbb67bac0bc201255625c7aa482dc53d Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/utils/__pycache__/__init__.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/utils/__pycache__/constants.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/utils/__pycache__/constants.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..ea0d6e7406b3181d4ba44bfd596fc2a44fc33db7 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/utils/__pycache__/constants.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/utils/__pycache__/doc.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/utils/__pycache__/doc.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..1116deed1167e4f6cf15cf9087d4fe4fbe40c9f7 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/utils/__pycache__/doc.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/utils/__pycache__/dummy_flax_objects.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/utils/__pycache__/dummy_flax_objects.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..04f1c9990a11d969808025cf1e0103665cf73a26 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/utils/__pycache__/dummy_flax_objects.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/utils/__pycache__/dummy_keras_nlp_objects.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/utils/__pycache__/dummy_keras_nlp_objects.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..8e544e36bc6f2c055e56cbff3f88962869f9735d Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/utils/__pycache__/dummy_keras_nlp_objects.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/utils/__pycache__/dummy_tensorflow_text_objects.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/utils/__pycache__/dummy_tensorflow_text_objects.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..a5af06efc5086770eab38c5d6ffdf0310c04d25e Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/utils/__pycache__/dummy_tensorflow_text_objects.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/utils/__pycache__/dummy_tf_objects.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/utils/__pycache__/dummy_tf_objects.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..19969cdd42987bf2fd3feaec745c7c80cf416984 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/utils/__pycache__/dummy_tf_objects.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/utils/__pycache__/generic.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/utils/__pycache__/generic.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..b9e8966d6cdbf46fe0dd5192242a1320a860466e Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/utils/__pycache__/generic.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/utils/__pycache__/hub.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/utils/__pycache__/hub.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..8f954cf9ce001487185a7a3dc4ad8d9c59980bab Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/utils/__pycache__/hub.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/utils/__pycache__/import_utils.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/utils/__pycache__/import_utils.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..51c39ff5f77d3cf23525991c9935ff6bd0ec4a27 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/utils/__pycache__/import_utils.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/utils/__pycache__/logging.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/utils/__pycache__/logging.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..d68de3b41eb2f69194d715892829f6c3b118f4aa Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/utils/__pycache__/logging.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/utils/__pycache__/model_parallel_utils.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/utils/__pycache__/model_parallel_utils.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..0907fa92acbdbebf22c9e5fae274b473de3f2040 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/utils/__pycache__/model_parallel_utils.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/utils/__pycache__/quantization_config.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/utils/__pycache__/quantization_config.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..13cf56f0e2430d5934c1583c663a18bc81ed5cf0 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/utils/__pycache__/quantization_config.cpython-310.pyc differ diff --git a/hf-dev-train/transformers-main/src/transformers/utils/__pycache__/versions.cpython-310.pyc b/hf-dev-train/transformers-main/src/transformers/utils/__pycache__/versions.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..6b7bcea7e9b0e62f483a9fd816c702cd274023c5 Binary files /dev/null and b/hf-dev-train/transformers-main/src/transformers/utils/__pycache__/versions.cpython-310.pyc differ diff --git a/peft-main/src/peft.egg-info/PKG-INFO b/peft-main/src/peft.egg-info/PKG-INFO new file mode 100644 index 0000000000000000000000000000000000000000..d23c567205b204fb405a019333d0f4b8695c8813 --- /dev/null +++ b/peft-main/src/peft.egg-info/PKG-INFO @@ -0,0 +1,426 @@ +Metadata-Version: 2.1 +Name: peft +Version: 0.3.0.dev0 +Summary: Parameter-Efficient Fine-Tuning (PEFT) +Home-page: https://github.com/huggingface/peft +Author: The HuggingFace team +Author-email: sourab@huggingface.co +License: Apache +Keywords: deep learning +Classifier: Development Status :: 5 - Production/Stable +Classifier: Intended Audience :: Developers +Classifier: Intended Audience :: Education +Classifier: Intended Audience :: Science/Research +Classifier: License :: OSI Approved :: Apache Software License +Classifier: Operating System :: OS Independent +Classifier: Programming Language :: Python :: 3 +Classifier: Programming Language :: Python :: 3.7 +Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence +Requires-Python: >=3.7.0 +Description-Content-Type: text/markdown +License-File: LICENSE +Requires-Dist: numpy>=1.17 +Requires-Dist: packaging>=20.0 +Requires-Dist: psutil +Requires-Dist: pyyaml +Requires-Dist: torch>=1.13.0 +Requires-Dist: transformers +Requires-Dist: accelerate +Provides-Extra: quality +Requires-Dist: black~=22.0; extra == "quality" +Requires-Dist: ruff>=0.0.241; extra == "quality" +Provides-Extra: docs-specific +Requires-Dist: hf-doc-builder; extra == "docs-specific" +Provides-Extra: dev +Requires-Dist: black~=22.0; extra == "dev" +Requires-Dist: ruff>=0.0.241; extra == "dev" +Requires-Dist: hf-doc-builder; extra == "dev" +Provides-Extra: test +Requires-Dist: black~=22.0; extra == "test" +Requires-Dist: ruff>=0.0.241; extra == "test" +Requires-Dist: hf-doc-builder; extra == "test" +Requires-Dist: pytest; extra == "test" +Requires-Dist: pytest-xdist; extra == "test" +Requires-Dist: parameterized; extra == "test" +Requires-Dist: datasets; extra == "test" + + + +

🤗 PEFT

+

+

State-of-the-art Parameter-Efficient Fine-Tuning (PEFT) methods

+

+ +Parameter-Efficient Fine-Tuning (PEFT) methods enable efficient adaptation of pre-trained language models (PLMs) to various downstream applications without fine-tuning all the model's parameters. Fine-tuning large-scale PLMs is often prohibitively costly. In this regard, PEFT methods only fine-tune a small number of (extra) model parameters, thereby greatly decreasing the computational and storage costs. Recent State-of-the-Art PEFT techniques achieve performance comparable to that of full fine-tuning. + +Seamlessly integrated with 🤗 Accelerate for large scale models leveraging DeepSpeed and Big Model Inference. + +Supported methods: + +1. LoRA: [LORA: LOW-RANK ADAPTATION OF LARGE LANGUAGE MODELS](https://arxiv.org/abs/2106.09685) +2. Prefix Tuning: [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://aclanthology.org/2021.acl-long.353/), [P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks](https://arxiv.org/pdf/2110.07602.pdf) +3. P-Tuning: [GPT Understands, Too](https://arxiv.org/abs/2103.10385) +4. Prompt Tuning: [The Power of Scale for Parameter-Efficient Prompt Tuning](https://arxiv.org/abs/2104.08691) +5. AdaLoRA: [Adaptive Budget Allocation for Parameter-Efficient Fine-Tuning](https://arxiv.org/abs/2303.10512) + +## Getting started + +```python +from transformers import AutoModelForSeq2SeqLM +from peft import get_peft_config, get_peft_model, LoraConfig, TaskType +model_name_or_path = "bigscience/mt0-large" +tokenizer_name_or_path = "bigscience/mt0-large" + +peft_config = LoraConfig( + task_type=TaskType.SEQ_2_SEQ_LM, inference_mode=False, r=8, lora_alpha=32, lora_dropout=0.1 +) + +model = AutoModelForSeq2SeqLM.from_pretrained(model_name_or_path) +model = get_peft_model(model, peft_config) +model.print_trainable_parameters() +# output: trainable params: 2359296 || all params: 1231940608 || trainable%: 0.19151053100118282 +``` + +## Use Cases + +### Get comparable performance to full finetuning by adapting LLMs to downstream tasks using consumer hardware + +GPU memory required for adapting LLMs on the few-shot dataset [`ought/raft/twitter_complaints`](https://huggingface.co/datasets/ought/raft/viewer/twitter_complaints). Here, settings considered +are full finetuning, PEFT-LoRA using plain PyTorch and PEFT-LoRA using DeepSpeed with CPU Offloading. + +Hardware: Single A100 80GB GPU with CPU RAM above 64GB + +| Model | Full Finetuning | PEFT-LoRA PyTorch | PEFT-LoRA DeepSpeed with CPU Offloading | +| --------- | ---- | ---- | ---- | +| bigscience/T0_3B (3B params) | 47.14GB GPU / 2.96GB CPU | 14.4GB GPU / 2.96GB CPU | 9.8GB GPU / 17.8GB CPU | +| bigscience/mt0-xxl (12B params) | OOM GPU | 56GB GPU / 3GB CPU | 22GB GPU / 52GB CPU | +| bigscience/bloomz-7b1 (7B params) | OOM GPU | 32GB GPU / 3.8GB CPU | 18.1GB GPU / 35GB CPU | + +Performance of PEFT-LoRA tuned [`bigscience/T0_3B`](https://huggingface.co/bigscience/T0_3B) on [`ought/raft/twitter_complaints`](https://huggingface.co/datasets/ought/raft/viewer/twitter_complaints) leaderboard. +A point to note is that we didn't try to squeeze performance by playing around with input instruction templates, LoRA hyperparams and other training related hyperparams. Also, we didn't use the larger 13B [mt0-xxl](https://huggingface.co/bigscience/mt0-xxl) model. +So, we are already seeing comparable performance to SoTA with parameter efficient tuning. Also, the final checkpoint size is just `19MB` in comparison to `11GB` size of the backbone [`bigscience/T0_3B`](https://huggingface.co/bigscience/T0_3B) model. + +| Submission Name | Accuracy | +| --------- | ---- | +| Human baseline (crowdsourced) | 0.897 | +| Flan-T5 | 0.892 | +| lora-t0-3b | 0.863 | + +**Therefore, we can see that performance comparable to SoTA is achievable by PEFT methods with consumer hardware such as 16GB and 24GB GPUs.** + +A insightful blogpost explaining the advantages of using PEFT for fine-tuning FlanT5-XXL: [https://www.philschmid.de/fine-tune-flan-t5-peft](https://www.philschmid.de/fine-tune-flan-t5-peft) + +### Parameter Efficient Tuning of Diffusion Models + +GPU memory required by different settings during training is given below. The final checkpoint size is `8.8 MB`. + +Hardware: Single A100 80GB GPU with CPU RAM above 64GB + +| Model | Full Finetuning | PEFT-LoRA | PEFT-LoRA with Gradient Checkpointing | +| --------- | ---- | ---- | ---- | +| CompVis/stable-diffusion-v1-4 | 27.5GB GPU / 3.97GB CPU | 15.5GB GPU / 3.84GB CPU | 8.12GB GPU / 3.77GB CPU | + + +**Training** +An example of using LoRA for parameter efficient dreambooth training is given in `~examples/lora_dreambooth/train_dreambooth.py` + +```bash +export MODEL_NAME= "CompVis/stable-diffusion-v1-4" #"stabilityai/stable-diffusion-2-1" +export INSTANCE_DIR="path-to-instance-images" +export CLASS_DIR="path-to-class-images" +export OUTPUT_DIR="path-to-save-model" + +accelerate launch train_dreambooth.py \ + --pretrained_model_name_or_path=$MODEL_NAME \ + --instance_data_dir=$INSTANCE_DIR \ + --class_data_dir=$CLASS_DIR \ + --output_dir=$OUTPUT_DIR \ + --train_text_encoder \ + --with_prior_preservation --prior_loss_weight=1.0 \ + --instance_prompt="a photo of sks dog" \ + --class_prompt="a photo of dog" \ + --resolution=512 \ + --train_batch_size=1 \ + --lr_scheduler="constant" \ + --lr_warmup_steps=0 \ + --num_class_images=200 \ + --use_lora \ + --lora_r 16 \ + --lora_alpha 27 \ + --lora_text_encoder_r 16 \ + --lora_text_encoder_alpha 17 \ + --learning_rate=1e-4 \ + --gradient_accumulation_steps=1 \ + --gradient_checkpointing \ + --max_train_steps=800 +``` + +Try out the 🤗 Gradio Space which should run seamlessly on a T4 instance: +[smangrul/peft-lora-sd-dreambooth](https://huggingface.co/spaces/smangrul/peft-lora-sd-dreambooth). + +![peft lora dreambooth gradio space](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/peft/peft_lora_dreambooth_gradio_space.png) + +**NEW** ✨ Multi Adapter support and combining multiple LoRA adapters in a weighted combination +![peft lora dreambooth weighted adapter](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/peft/weighted_adapter_dreambooth_lora.png) + +### Parameter Efficient Tuning of LLMs for RLHF components such as Ranker and Policy +- Here is an example in [trl](https://github.com/lvwerra/trl) library using PEFT+INT8 for tuning policy model: [gpt2-sentiment_peft.py](https://github.com/lvwerra/trl/blob/main/examples/sentiment/scripts/gpt2-sentiment_peft.py) and corresponding [Blog](https://huggingface.co/blog/trl-peft) +- Example using PEFT for Instrction finetuning, reward model and policy : [stack_llama](https://github.com/lvwerra/trl/tree/main/examples/stack_llama/scripts) and corresponding [Blog](https://huggingface.co/blog/stackllama) + +### INT8 training of large models in Colab using PEFT LoRA and bits_and_bytes + +- Here is now a demo on how to fine tune [OPT-6.7b](https://huggingface.co/facebook/opt-6.7b) (14GB in fp16) in a Google Colab: [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1jCkpikz0J2o20FBQmYmAGdiKmJGOMo-o?usp=sharing) + +- Here is now a demo on how to fine tune [whishper-large](openai/whisper-large-v2) (1.5B params) (14GB in fp16) in a Google Colab: [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1DOkD_5OUjFa0r5Ik3SgywJLJtEo2qLxO?usp=sharing) and [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1vhF8yueFqha3Y3CpTHN6q9EVcII9EYzs?usp=sharing) + +### Save compute and storage even for medium and small models + +Save storage by avoiding full finetuning of models on each of the downstream tasks/datasets, +With PEFT methods, users only need to store tiny checkpoints in the order of `MBs` all the while retaining +performance comparable to full finetuning. + +An example of using LoRA for the task of adapting `LayoutLMForTokenClassification` on `FUNSD` dataset is given in `~examples/token_classification/PEFT_LoRA_LayoutLMForTokenClassification_on_FUNSD.py`. We can observe that with only `0.62 %` of parameters being trainable, we achieve performance (F1 0.777) comparable to full finetuning (F1 0.786) (without any hyerparam tuning runs for extracting more performance), and the checkpoint of this is only `2.8MB`. Now, if there are `N` such datasets, just have these PEFT models one for each dataset and save a lot of storage without having to worry about the problem of catastrophic forgetting or overfitting of backbone/base model. + +Another example is fine-tuning [`roberta-large`](https://huggingface.co/roberta-large) on [`MRPC` GLUE](https://huggingface.co/datasets/glue/viewer/mrpc) dataset using different PEFT methods. The notebooks are given in `~examples/sequence_classification`. + + +## PEFT + 🤗 Accelerate + +PEFT models work with 🤗 Accelerate out of the box. Use 🤗 Accelerate for Distributed training on various hardware such as GPUs, Apple Silicon devices, etc during training. +Use 🤗 Accelerate for inferencing on consumer hardware with small resources. + +### Example of PEFT model training using 🤗 Accelerate's DeepSpeed integration + +DeepSpeed version required `v0.8.0`. An example is provided in `~examples/conditional_generation/peft_lora_seq2seq_accelerate_ds_zero3_offload.py`. + a. First, run `accelerate config --config_file ds_zero3_cpu.yaml` and answer the questionnaire. + Below are the contents of the config file. + ```yaml + compute_environment: LOCAL_MACHINE + deepspeed_config: + gradient_accumulation_steps: 1 + gradient_clipping: 1.0 + offload_optimizer_device: cpu + offload_param_device: cpu + zero3_init_flag: true + zero3_save_16bit_model: true + zero_stage: 3 + distributed_type: DEEPSPEED + downcast_bf16: 'no' + dynamo_backend: 'NO' + fsdp_config: {} + machine_rank: 0 + main_training_function: main + megatron_lm_config: {} + mixed_precision: 'no' + num_machines: 1 + num_processes: 1 + rdzv_backend: static + same_network: true + use_cpu: false + ``` + b. run the below command to launch the example script + ```bash + accelerate launch --config_file ds_zero3_cpu.yaml examples/peft_lora_seq2seq_accelerate_ds_zero3_offload.py + ``` + + c. output logs: + ```bash + GPU Memory before entering the train : 1916 + GPU Memory consumed at the end of the train (end-begin): 66 + GPU Peak Memory consumed during the train (max-begin): 7488 + GPU Total Peak Memory consumed during the train (max): 9404 + CPU Memory before entering the train : 19411 + CPU Memory consumed at the end of the train (end-begin): 0 + CPU Peak Memory consumed during the train (max-begin): 0 + CPU Total Peak Memory consumed during the train (max): 19411 + epoch=4: train_ppl=tensor(1.0705, device='cuda:0') train_epoch_loss=tensor(0.0681, device='cuda:0') + 100%|████████████████████████████████████████████████████████████████████████████████████████████| 7/7 [00:27<00:00, 3.92s/it] + GPU Memory before entering the eval : 1982 + GPU Memory consumed at the end of the eval (end-begin): -66 + GPU Peak Memory consumed during the eval (max-begin): 672 + GPU Total Peak Memory consumed during the eval (max): 2654 + CPU Memory before entering the eval : 19411 + CPU Memory consumed at the end of the eval (end-begin): 0 + CPU Peak Memory consumed during the eval (max-begin): 0 + CPU Total Peak Memory consumed during the eval (max): 19411 + accuracy=100.0 + eval_preds[:10]=['no complaint', 'no complaint', 'complaint', 'complaint', 'no complaint', 'no complaint', 'no complaint', 'complaint', 'complaint', 'no complaint'] + dataset['train'][label_column][:10]=['no complaint', 'no complaint', 'complaint', 'complaint', 'no complaint', 'no complaint', 'no complaint', 'complaint', 'complaint', 'no complaint'] + ``` + +### Example of PEFT model inference using 🤗 Accelerate's Big Model Inferencing capabilities +An example is provided in `~examples/causal_language_modeling/peft_lora_clm_accelerate_big_model_inference.ipynb`. + + +## Models support matrix + +### Causal Language Modeling +| Model | LoRA | Prefix Tuning | P-Tuning | Prompt Tuning | +|--------------| ---- | ---- | ---- | ---- | +| GPT-2 | ✅ | ✅ | ✅ | ✅ | +| Bloom | ✅ | ✅ | ✅ | ✅ | +| OPT | ✅ | ✅ | ✅ | ✅ | +| GPT-Neo | ✅ | ✅ | ✅ | ✅ | +| GPT-J | ✅ | ✅ | ✅ | ✅ | +| GPT-NeoX-20B | ✅ | ✅ | ✅ | ✅ | +| LLaMA | ✅ | ✅ | ✅ | ✅ | +| ChatGLM | ✅ | ✅ | ✅ | ✅ | + +### Conditional Generation +| Model | LoRA | Prefix Tuning | P-Tuning | Prompt Tuning | +| --------- | ---- | ---- | ---- | ---- | +| T5 | ✅ | ✅ | ✅ | ✅ | +| BART | ✅ | ✅ | ✅ | ✅ | + +### Sequence Classification +| Model | LoRA | Prefix Tuning | P-Tuning | Prompt Tuning | +| --------- | ---- | ---- | ---- | ---- | +| BERT | ✅ | ✅ | ✅ | ✅ | +| RoBERTa | ✅ | ✅ | ✅ | ✅ | +| GPT-2 | ✅ | ✅ | ✅ | ✅ | +| Bloom | ✅ | ✅ | ✅ | ✅ | +| OPT | ✅ | ✅ | ✅ | ✅ | +| GPT-Neo | ✅ | ✅ | ✅ | ✅ | +| GPT-J | ✅ | ✅ | ✅ | ✅ | +| Deberta | ✅ | | ✅ | ✅ | +| Deberta-v2 | ✅ | | ✅ | ✅ | + +### Token Classification +| Model | LoRA | Prefix Tuning | P-Tuning | Prompt Tuning | +| --------- | ---- | ---- | ---- | ---- | +| BERT | ✅ | ✅ | | | +| RoBERTa | ✅ | ✅ | | | +| GPT-2 | ✅ | ✅ | | | +| Bloom | ✅ | ✅ | | | +| OPT | ✅ | ✅ | | | +| GPT-Neo | ✅ | ✅ | | | +| GPT-J | ✅ | ✅ | | | +| Deberta | ✅ | | | | +| Deberta-v2 | ✅ | | | | + +### Text-to-Image Generation + +| Model | LoRA | Prefix Tuning | P-Tuning | Prompt Tuning | +| --------- | ---- | ---- | ---- | ---- | +| Stable Diffusion | ✅ | | | | + + +### Image Classification + +| Model | LoRA | Prefix Tuning | P-Tuning | Prompt Tuning | +| --------- | ---- | ---- | ---- | ---- | +| ViT | ✅ | | | | +| Swin | ✅ | | | | + +### Image to text (Multi-modal models) + +| Model | LoRA | Prefix Tuning | P-Tuning | Prompt Tuning | +| --------- | ---- | ---- | ---- | ---- | +| Blip-2 | ✅ | | | | + +___Note that we have tested LoRA for [ViT](https://huggingface.co/docs/transformers/model_doc/vit) and [Swin](https://huggingface.co/docs/transformers/model_doc/swin) for fine-tuning on image classification. However, it should be possible to use LoRA for any compatible model [provided](https://huggingface.co/models?pipeline_tag=image-classification&sort=downloads&search=vit) by 🤗 Transformers. Check out the respective +examples to learn more. If you run into problems, please open an issue.___ + +The same principle applies to our [segmentation models](https://huggingface.co/models?pipeline_tag=image-segmentation&sort=downloads) as well. + +### Semantic Segmentation + +| Model | LoRA | Prefix Tuning | P-Tuning | Prompt Tuning | +| --------- | ---- | ---- | ---- | ---- | +| SegFormer | ✅ | | | | + + +## Caveats: + +1. Below is an example of using PyTorch FSDP for training. However, it doesn't lead to +any GPU memory savings. Please refer issue [[FSDP] FSDP with CPU offload consumes 1.65X more GPU memory when training models with most of the params frozen](https://github.com/pytorch/pytorch/issues/91165). + + ```python + from peft.utils.other import fsdp_auto_wrap_policy + + ... + + if os.environ.get("ACCELERATE_USE_FSDP", None) is not None: + accelerator.state.fsdp_plugin.auto_wrap_policy = fsdp_auto_wrap_policy(model) + + model = accelerator.prepare(model) + ``` + + Example of parameter efficient tuning with [`mt0-xxl`](https://huggingface.co/bigscience/mt0-xxl) base model using 🤗 Accelerate is provided in `~examples/conditional_generation/peft_lora_seq2seq_accelerate_fsdp.py`. + a. First, run `accelerate config --config_file fsdp_config.yaml` and answer the questionnaire. + Below are the contents of the config file. + ```yaml + command_file: null + commands: null + compute_environment: LOCAL_MACHINE + deepspeed_config: {} + distributed_type: FSDP + downcast_bf16: 'no' + dynamo_backend: 'NO' + fsdp_config: + fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP + fsdp_backward_prefetch_policy: BACKWARD_PRE + fsdp_offload_params: true + fsdp_sharding_strategy: 1 + fsdp_state_dict_type: FULL_STATE_DICT + fsdp_transformer_layer_cls_to_wrap: T5Block + gpu_ids: null + machine_rank: 0 + main_process_ip: null + main_process_port: null + main_training_function: main + megatron_lm_config: {} + mixed_precision: 'no' + num_machines: 1 + num_processes: 2 + rdzv_backend: static + same_network: true + tpu_name: null + tpu_zone: null + use_cpu: false + ``` + b. run the below command to launch the example script + ```bash + accelerate launch --config_file fsdp_config.yaml examples/peft_lora_seq2seq_accelerate_fsdp.py + ``` + +2. When using `P_TUNING` or `PROMPT_TUNING` with `SEQ_2_SEQ` task, remember to remove the `num_virtual_token` virtual prompt predictions from the left side of the model outputs during evaluations. + +3. For encoder-decoder models, `P_TUNING` or `PROMPT_TUNING` doesn't support `generate` functionality of transformers because `generate` strictly requires `decoder_input_ids` but +`P_TUNING`/`PROMPT_TUNING` appends soft prompt embeddings to `input_embeds` to create +new `input_embeds` to be given to the model. Therefore, `generate` doesn't support this yet. + +4. When using ZeRO3 with zero3_init_flag=True, if you find the gpu memory increase with training steps. we might need to set zero3_init_flag=false in accelerate config.yaml. The related issue is [[BUG] memory leak under zero.Init](https://github.com/microsoft/DeepSpeed/issues/2637) + +## Backlog: +- [x] Add tests +- [x] Multi Adapter training and inference support +- [x] Add more use cases and examples +- [ ] Explore and possibly integrate `Bottleneck Adapters`, `(IA)^3`, `AdaptionPrompt` ... + +## Citing 🤗 PEFT + +If you use 🤗 PEFT in your publication, please cite it by using the following BibTeX entry. + +```bibtex +@Misc{peft, + title = {PEFT: State-of-the-art Parameter-Efficient Fine-Tuning methods}, + author = {Sourab Mangrulkar, Sylvain Gugger, Lysandre Debut, Younes Belkada, Sayak Paul}, + howpublished = {\url{https://github.com/huggingface/peft}}, + year = {2022} +} +``` diff --git a/peft-main/src/peft.egg-info/SOURCES.txt b/peft-main/src/peft.egg-info/SOURCES.txt new file mode 100644 index 0000000000000000000000000000000000000000..097baa9feb64750133ce2d6f96bdbad5cf736988 --- /dev/null +++ b/peft-main/src/peft.egg-info/SOURCES.txt @@ -0,0 +1,30 @@ +LICENSE +README.md +pyproject.toml +setup.py +src/peft/__init__.py +src/peft/import_utils.py +src/peft/mapping.py +src/peft/peft_model.py +src/peft.egg-info/PKG-INFO +src/peft.egg-info/SOURCES.txt +src/peft.egg-info/dependency_links.txt +src/peft.egg-info/requires.txt +src/peft.egg-info/top_level.txt +src/peft/tuners/__init__.py +src/peft/tuners/adalora.py +src/peft/tuners/lora.py +src/peft/tuners/p_tuning.py +src/peft/tuners/prefix_tuning.py +src/peft/tuners/prompt_tuning.py +src/peft/utils/__init__.py +src/peft/utils/config.py +src/peft/utils/other.py +src/peft/utils/save_and_load.py +tests/test_common_gpu.py +tests/test_config.py +tests/test_decoder_models.py +tests/test_encoder_decoder_models.py +tests/test_gpu_examples.py +tests/testing_common.py +tests/testing_utils.py \ No newline at end of file diff --git a/peft-main/src/peft.egg-info/dependency_links.txt b/peft-main/src/peft.egg-info/dependency_links.txt new file mode 100644 index 0000000000000000000000000000000000000000..8b137891791fe96927ad78e64b0aad7bded08bdc --- /dev/null +++ b/peft-main/src/peft.egg-info/dependency_links.txt @@ -0,0 +1 @@ + diff --git a/peft-main/src/peft.egg-info/requires.txt b/peft-main/src/peft.egg-info/requires.txt new file mode 100644 index 0000000000000000000000000000000000000000..33a25d2cfc40c25135ac53e7cb861995816e1b34 --- /dev/null +++ b/peft-main/src/peft.egg-info/requires.txt @@ -0,0 +1,28 @@ +numpy>=1.17 +packaging>=20.0 +psutil +pyyaml +torch>=1.13.0 +transformers +accelerate + +[dev] +black~=22.0 +ruff>=0.0.241 +hf-doc-builder + +[docs_specific] +hf-doc-builder + +[quality] +black~=22.0 +ruff>=0.0.241 + +[test] +black~=22.0 +ruff>=0.0.241 +hf-doc-builder +pytest +pytest-xdist +parameterized +datasets diff --git a/peft-main/src/peft.egg-info/top_level.txt b/peft-main/src/peft.egg-info/top_level.txt new file mode 100644 index 0000000000000000000000000000000000000000..dc89ba063e639dfa24fd7f53340bc368adbebb7a --- /dev/null +++ b/peft-main/src/peft.egg-info/top_level.txt @@ -0,0 +1 @@ +peft diff --git a/peft-main/src/peft/__pycache__/__init__.cpython-310.pyc b/peft-main/src/peft/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..05faf9a6215ba498c43bdf4110d0d708d5d13cae Binary files /dev/null and b/peft-main/src/peft/__pycache__/__init__.cpython-310.pyc differ diff --git a/peft-main/src/peft/__pycache__/__init__.cpython-39.pyc b/peft-main/src/peft/__pycache__/__init__.cpython-39.pyc new file mode 100644 index 0000000000000000000000000000000000000000..ad528ff32608cbe4afa6e8319bb8a844288a3585 Binary files /dev/null and b/peft-main/src/peft/__pycache__/__init__.cpython-39.pyc differ diff --git a/peft-main/src/peft/__pycache__/import_utils.cpython-310.pyc b/peft-main/src/peft/__pycache__/import_utils.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..1c7ef468e7c3300741dd6e88bf24718e6c9da8a3 Binary files /dev/null and b/peft-main/src/peft/__pycache__/import_utils.cpython-310.pyc differ diff --git a/peft-main/src/peft/__pycache__/import_utils.cpython-39.pyc b/peft-main/src/peft/__pycache__/import_utils.cpython-39.pyc new file mode 100644 index 0000000000000000000000000000000000000000..a3cbf9d927ac1bd82747fb20aed04e41832d9334 Binary files /dev/null and b/peft-main/src/peft/__pycache__/import_utils.cpython-39.pyc differ diff --git a/peft-main/src/peft/__pycache__/mapping.cpython-310.pyc b/peft-main/src/peft/__pycache__/mapping.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..a31e29462f704357ca972d5330844ead4c1ee209 Binary files /dev/null and b/peft-main/src/peft/__pycache__/mapping.cpython-310.pyc differ diff --git a/peft-main/src/peft/__pycache__/mapping.cpython-39.pyc b/peft-main/src/peft/__pycache__/mapping.cpython-39.pyc new file mode 100644 index 0000000000000000000000000000000000000000..9da8d354e95bef1f4f1991eda0b7b9cf2776bbdd Binary files /dev/null and b/peft-main/src/peft/__pycache__/mapping.cpython-39.pyc differ diff --git a/peft-main/src/peft/__pycache__/peft_model.cpython-310.pyc b/peft-main/src/peft/__pycache__/peft_model.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..87c950a585d0f445b3299b2cc3ecd7753322f66d Binary files /dev/null and b/peft-main/src/peft/__pycache__/peft_model.cpython-310.pyc differ diff --git a/peft-main/src/peft/__pycache__/peft_model.cpython-39.pyc b/peft-main/src/peft/__pycache__/peft_model.cpython-39.pyc new file mode 100644 index 0000000000000000000000000000000000000000..cae938a3d5106510f9d0548744d30321e0435955 Binary files /dev/null and b/peft-main/src/peft/__pycache__/peft_model.cpython-39.pyc differ diff --git a/peft-main/src/peft/tuners/__pycache__/__init__.cpython-310.pyc b/peft-main/src/peft/tuners/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..04f9629a4ab864472683926bb47ede43fa21cd72 Binary files /dev/null and b/peft-main/src/peft/tuners/__pycache__/__init__.cpython-310.pyc differ diff --git a/peft-main/src/peft/tuners/__pycache__/__init__.cpython-39.pyc b/peft-main/src/peft/tuners/__pycache__/__init__.cpython-39.pyc new file mode 100644 index 0000000000000000000000000000000000000000..4a1e01c4315d0eb7103b0451f985a379bb67a917 Binary files /dev/null and b/peft-main/src/peft/tuners/__pycache__/__init__.cpython-39.pyc differ diff --git a/peft-main/src/peft/tuners/__pycache__/adalora.cpython-310.pyc b/peft-main/src/peft/tuners/__pycache__/adalora.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..47a99ef6ce3e554a434815f63297bce2dbfe727b Binary files /dev/null and b/peft-main/src/peft/tuners/__pycache__/adalora.cpython-310.pyc differ diff --git a/peft-main/src/peft/tuners/__pycache__/adalora.cpython-39.pyc b/peft-main/src/peft/tuners/__pycache__/adalora.cpython-39.pyc new file mode 100644 index 0000000000000000000000000000000000000000..9d87084220e374595df1e038229e9f7293343687 Binary files /dev/null and b/peft-main/src/peft/tuners/__pycache__/adalora.cpython-39.pyc differ diff --git a/peft-main/src/peft/tuners/__pycache__/lora.cpython-310.pyc b/peft-main/src/peft/tuners/__pycache__/lora.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..beae0b167d0994a34f853dfb134a73750a68b1c0 Binary files /dev/null and b/peft-main/src/peft/tuners/__pycache__/lora.cpython-310.pyc differ diff --git a/peft-main/src/peft/tuners/__pycache__/lora.cpython-39.pyc b/peft-main/src/peft/tuners/__pycache__/lora.cpython-39.pyc new file mode 100644 index 0000000000000000000000000000000000000000..355c714a678993eeebf36acbef385273e63fc7c6 Binary files /dev/null and b/peft-main/src/peft/tuners/__pycache__/lora.cpython-39.pyc differ diff --git a/peft-main/src/peft/tuners/__pycache__/p_tuning.cpython-310.pyc b/peft-main/src/peft/tuners/__pycache__/p_tuning.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..133d37afb5ce775de8c2bac44c94d5e9ce3aaa9b Binary files /dev/null and b/peft-main/src/peft/tuners/__pycache__/p_tuning.cpython-310.pyc differ diff --git a/peft-main/src/peft/tuners/__pycache__/p_tuning.cpython-39.pyc b/peft-main/src/peft/tuners/__pycache__/p_tuning.cpython-39.pyc new file mode 100644 index 0000000000000000000000000000000000000000..963f5cb21cb49ea388156218926c1b38db40033b Binary files /dev/null and b/peft-main/src/peft/tuners/__pycache__/p_tuning.cpython-39.pyc differ diff --git a/peft-main/src/peft/tuners/__pycache__/prefix_tuning.cpython-310.pyc b/peft-main/src/peft/tuners/__pycache__/prefix_tuning.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..f6fb832a3b72e9d946a1ff746b7e5af1cc801e4d Binary files /dev/null and b/peft-main/src/peft/tuners/__pycache__/prefix_tuning.cpython-310.pyc differ diff --git a/peft-main/src/peft/tuners/__pycache__/prefix_tuning.cpython-39.pyc b/peft-main/src/peft/tuners/__pycache__/prefix_tuning.cpython-39.pyc new file mode 100644 index 0000000000000000000000000000000000000000..1506594bbec9d5342df9e94471e949c7c30a35d4 Binary files /dev/null and b/peft-main/src/peft/tuners/__pycache__/prefix_tuning.cpython-39.pyc differ diff --git a/peft-main/src/peft/tuners/__pycache__/prompt_tuning.cpython-310.pyc b/peft-main/src/peft/tuners/__pycache__/prompt_tuning.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..ce785ec3c26482c837666841e37642f1b96f4179 Binary files /dev/null and b/peft-main/src/peft/tuners/__pycache__/prompt_tuning.cpython-310.pyc differ diff --git a/peft-main/src/peft/tuners/__pycache__/prompt_tuning.cpython-39.pyc b/peft-main/src/peft/tuners/__pycache__/prompt_tuning.cpython-39.pyc new file mode 100644 index 0000000000000000000000000000000000000000..2dafc3660cec2cd82c1e1ef3c81bfea07b59fb6d Binary files /dev/null and b/peft-main/src/peft/tuners/__pycache__/prompt_tuning.cpython-39.pyc differ diff --git a/peft-main/src/peft/utils/__pycache__/__init__.cpython-310.pyc b/peft-main/src/peft/utils/__pycache__/__init__.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..74c9ff11783ec54bc3b7cbc11ba399bf3aa9acc2 Binary files /dev/null and b/peft-main/src/peft/utils/__pycache__/__init__.cpython-310.pyc differ diff --git a/peft-main/src/peft/utils/__pycache__/__init__.cpython-39.pyc b/peft-main/src/peft/utils/__pycache__/__init__.cpython-39.pyc new file mode 100644 index 0000000000000000000000000000000000000000..5ae08ecc5527a25adc2db470fbbaa8a0b7588da2 Binary files /dev/null and b/peft-main/src/peft/utils/__pycache__/__init__.cpython-39.pyc differ diff --git a/peft-main/src/peft/utils/__pycache__/config.cpython-310.pyc b/peft-main/src/peft/utils/__pycache__/config.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..947da96cba906f11e473567502745f4c4351c789 Binary files /dev/null and b/peft-main/src/peft/utils/__pycache__/config.cpython-310.pyc differ diff --git a/peft-main/src/peft/utils/__pycache__/config.cpython-39.pyc b/peft-main/src/peft/utils/__pycache__/config.cpython-39.pyc new file mode 100644 index 0000000000000000000000000000000000000000..edad9985f35dc8a26b4efed5b817105c6ae5748a Binary files /dev/null and b/peft-main/src/peft/utils/__pycache__/config.cpython-39.pyc differ diff --git a/peft-main/src/peft/utils/__pycache__/other.cpython-310.pyc b/peft-main/src/peft/utils/__pycache__/other.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..f08a4f622cc57cc9bd85a9b17284aef442a97862 Binary files /dev/null and b/peft-main/src/peft/utils/__pycache__/other.cpython-310.pyc differ diff --git a/peft-main/src/peft/utils/__pycache__/other.cpython-39.pyc b/peft-main/src/peft/utils/__pycache__/other.cpython-39.pyc new file mode 100644 index 0000000000000000000000000000000000000000..52a671a012ea434ec0ae9625ea47730df0f88f0d Binary files /dev/null and b/peft-main/src/peft/utils/__pycache__/other.cpython-39.pyc differ diff --git a/peft-main/src/peft/utils/__pycache__/save_and_load.cpython-310.pyc b/peft-main/src/peft/utils/__pycache__/save_and_load.cpython-310.pyc new file mode 100644 index 0000000000000000000000000000000000000000..f4e90b1d1337ff86b97617260561b3b64be9931a Binary files /dev/null and b/peft-main/src/peft/utils/__pycache__/save_and_load.cpython-310.pyc differ diff --git a/peft-main/src/peft/utils/__pycache__/save_and_load.cpython-39.pyc b/peft-main/src/peft/utils/__pycache__/save_and_load.cpython-39.pyc new file mode 100644 index 0000000000000000000000000000000000000000..0e1fd728e0452ef87e9cbbe08afd136c69d6cb9e Binary files /dev/null and b/peft-main/src/peft/utils/__pycache__/save_and_load.cpython-39.pyc differ