Avoid many failing tests in doctesting (#27262)

* fix

* update

* update

* fix

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

utils/check_doctest_list.py

@@ -54,7 +54,7 @@ def clean_doctest_list(doctest_file: str, overwrite: bool = False):
     all_paths = []
     with open(doctest_file, "r", encoding="utf-8") as f:
         for line in f:
-            line = line.strip()
+            line = line.strip().split(" ")[0]
             path = os.path.join(REPO_PATH, line)
             if not (os.path.isfile(path) or os.path.isdir(path)):
                 non_existent_paths.append(line)

utils/not_doctested.txt

-docs/source/en/_config.py
-docs/source/en/accelerate.md
-docs/source/en/add_new_model.md
-docs/source/en/add_new_pipeline.md
-docs/source/en/add_tensorflow_model.md
-docs/source/en/attention.md
-docs/source/en/benchmarks.md
-docs/source/en/bertology.md
-docs/source/en/big_models.md
-docs/source/en/community.md
-docs/source/en/contributing.md
-docs/source/en/create_a_model.md
-docs/source/en/custom_models.md
-docs/source/en/custom_tools.md
-docs/source/en/debugging.md
-docs/source/en/fast_tokenizers.md
-docs/source/en/glossary.md
-docs/source/en/hpo_train.md
-docs/source/en/index.md
-docs/source/en/installation.md
-docs/source/en/internal/audio_utils.md
-docs/source/en/internal/file_utils.md
-docs/source/en/internal/image_processing_utils.md
-docs/source/en/internal/modeling_utils.md
-docs/source/en/internal/pipelines_utils.md
-docs/source/en/internal/time_series_utils.md
-docs/source/en/internal/tokenization_utils.md
-docs/source/en/internal/trainer_utils.md
-docs/source/en/llm_tutorial.md
-docs/source/en/main_classes/agent.md
-docs/source/en/main_classes/callback.md
-docs/source/en/main_classes/configuration.md
-docs/source/en/main_classes/data_collator.md
-docs/source/en/main_classes/deepspeed.md
-docs/source/en/main_classes/feature_extractor.md
-docs/source/en/main_classes/image_processor.md
-docs/source/en/main_classes/keras_callbacks.md
-docs/source/en/main_classes/logging.md
-docs/source/en/main_classes/model.md
-docs/source/en/main_classes/onnx.md
-docs/source/en/main_classes/optimizer_schedules.md
-docs/source/en/main_classes/output.md
-docs/source/en/main_classes/pipelines.md
-docs/source/en/main_classes/processors.md
-docs/source/en/main_classes/quantization.md
-docs/source/en/main_classes/tokenizer.md
-docs/source/en/main_classes/trainer.md
-docs/source/en/model_doc/albert.md
-docs/source/en/model_doc/align.md
-docs/source/en/model_doc/altclip.md
-docs/source/en/model_doc/audio-spectrogram-transformer.md
-docs/source/en/model_doc/auto.md
-docs/source/en/model_doc/autoformer.md
-docs/source/en/model_doc/bark.md
-docs/source/en/model_doc/bart.md
-docs/source/en/model_doc/barthez.md
-docs/source/en/model_doc/bartpho.md
-docs/source/en/model_doc/beit.md
-docs/source/en/model_doc/bert-generation.md
-docs/source/en/model_doc/bert-japanese.md
-docs/source/en/model_doc/bert.md
-docs/source/en/model_doc/bertweet.md
-docs/source/en/model_doc/big_bird.md
-docs/source/en/model_doc/bigbird_pegasus.md
-docs/source/en/model_doc/biogpt.md
-docs/source/en/model_doc/bit.md
-docs/source/en/model_doc/blenderbot-small.md
-docs/source/en/model_doc/blenderbot.md
-docs/source/en/model_doc/blip-2.md
-docs/source/en/model_doc/blip.md
-docs/source/en/model_doc/bloom.md
-docs/source/en/model_doc/bort.md
-docs/source/en/model_doc/bridgetower.md
-docs/source/en/model_doc/camembert.md
-docs/source/en/model_doc/canine.md
-docs/source/en/model_doc/chinese_clip.md
-docs/source/en/model_doc/clap.md
-docs/source/en/model_doc/clip.md
-docs/source/en/model_doc/clipseg.md
-docs/source/en/model_doc/codegen.md
-docs/source/en/model_doc/conditional_detr.md
-docs/source/en/model_doc/convbert.md
-docs/source/en/model_doc/convnext.md
-docs/source/en/model_doc/convnextv2.md
-docs/source/en/model_doc/cpm.md
-docs/source/en/model_doc/cpmant.md
-docs/source/en/model_doc/ctrl.md
-docs/source/en/model_doc/cvt.md
-docs/source/en/model_doc/data2vec.md
-docs/source/en/model_doc/deberta-v2.md
-docs/source/en/model_doc/deberta.md
-docs/source/en/model_doc/decision_transformer.md
-docs/source/en/model_doc/deformable_detr.md
-docs/source/en/model_doc/deit.md
-docs/source/en/model_doc/deplot.md
-docs/source/en/model_doc/deta.md
-docs/source/en/model_doc/detr.md
-docs/source/en/model_doc/dialogpt.md
-docs/source/en/model_doc/dinat.md
-docs/source/en/model_doc/dinov2.md
-docs/source/en/model_doc/distilbert.md
-docs/source/en/model_doc/dit.md
-docs/source/en/model_doc/dpr.md
-docs/source/en/model_doc/dpt.md
-docs/source/en/model_doc/efficientformer.md
-docs/source/en/model_doc/efficientnet.md
-docs/source/en/model_doc/electra.md
-docs/source/en/model_doc/encodec.md
-docs/source/en/model_doc/ernie.md
-docs/source/en/model_doc/ernie_m.md
-docs/source/en/model_doc/esm.md
-docs/source/en/model_doc/flan-t5.md
-docs/source/en/model_doc/flan-ul2.md
-docs/source/en/model_doc/flaubert.md
-docs/source/en/model_doc/flava.md
-docs/source/en/model_doc/fnet.md
-docs/source/en/model_doc/focalnet.md
-docs/source/en/model_doc/fsmt.md
-docs/source/en/model_doc/funnel.md
-docs/source/en/model_doc/git.md
-docs/source/en/model_doc/glpn.md
-docs/source/en/model_doc/gpt-sw3.md
-docs/source/en/model_doc/gpt2.md
-docs/source/en/model_doc/gpt_bigcode.md
-docs/source/en/model_doc/gpt_neo.md
-docs/source/en/model_doc/gpt_neox.md
-docs/source/en/model_doc/gpt_neox_japanese.md
-docs/source/en/model_doc/gptj.md
-docs/source/en/model_doc/gptsan-japanese.md
-docs/source/en/model_doc/graphormer.md
-docs/source/en/model_doc/groupvit.md
-docs/source/en/model_doc/herbert.md
-docs/source/en/model_doc/hubert.md
-docs/source/en/model_doc/ibert.md
-docs/source/en/model_doc/idefics.md
-docs/source/en/model_doc/imagegpt.md
-docs/source/en/model_doc/informer.md
-docs/source/en/model_doc/instructblip.md
-docs/source/en/model_doc/jukebox.md
-docs/source/en/model_doc/layoutlm.md
-docs/source/en/model_doc/layoutlmv2.md
-docs/source/en/model_doc/layoutlmv3.md
-docs/source/en/model_doc/layoutxlm.md
-docs/source/en/model_doc/led.md
-docs/source/en/model_doc/levit.md
-docs/source/en/model_doc/lilt.md
-docs/source/en/model_doc/llama.md
-docs/source/en/model_doc/llama2.md
-docs/source/en/model_doc/longformer.md
-docs/source/en/model_doc/longt5.md
-docs/source/en/model_doc/luke.md
-docs/source/en/model_doc/lxmert.md
-docs/source/en/model_doc/m2m_100.md
-docs/source/en/model_doc/marian.md
-docs/source/en/model_doc/mask2former.md
-docs/source/en/model_doc/maskformer.md
-docs/source/en/model_doc/matcha.md
-docs/source/en/model_doc/mbart.md
-docs/source/en/model_doc/mctct.md
-docs/source/en/model_doc/mega.md
-docs/source/en/model_doc/megatron-bert.md
-docs/source/en/model_doc/megatron_gpt2.md
-docs/source/en/model_doc/mgp-str.md
-docs/source/en/model_doc/mistral.md
-docs/source/en/model_doc/mluke.md
-docs/source/en/model_doc/mms.md
-docs/source/en/model_doc/mobilebert.md
-docs/source/en/model_doc/mobilenet_v1.md
-docs/source/en/model_doc/mobilenet_v2.md
-docs/source/en/model_doc/mobilevit.md
-docs/source/en/model_doc/mobilevitv2.md
-docs/source/en/model_doc/mpnet.md
-docs/source/en/model_doc/mpt.md
-docs/source/en/model_doc/mra.md
-docs/source/en/model_doc/mt5.md
-docs/source/en/model_doc/musicgen.md
-docs/source/en/model_doc/mvp.md
-docs/source/en/model_doc/nat.md
-docs/source/en/model_doc/nezha.md
-docs/source/en/model_doc/nllb-moe.md
-docs/source/en/model_doc/nllb.md
-docs/source/en/model_doc/nystromformer.md
-docs/source/en/model_doc/oneformer.md
-docs/source/en/model_doc/open-llama.md
-docs/source/en/model_doc/openai-gpt.md
-docs/source/en/model_doc/opt.md
-docs/source/en/model_doc/owlvit.md
-docs/source/en/model_doc/pegasus.md
-docs/source/en/model_doc/pegasus_x.md
-docs/source/en/model_doc/perceiver.md
-docs/source/en/model_doc/phobert.md
-docs/source/en/model_doc/pix2struct.md
-docs/source/en/model_doc/plbart.md
-docs/source/en/model_doc/poolformer.md
-docs/source/en/model_doc/pop2piano.md
-docs/source/en/model_doc/prophetnet.md
-docs/source/en/model_doc/pvt.md
-docs/source/en/model_doc/qdqbert.md
-docs/source/en/model_doc/rag.md
-docs/source/en/model_doc/realm.md
-docs/source/en/model_doc/reformer.md
-docs/source/en/model_doc/regnet.md
-docs/source/en/model_doc/rembert.md
-docs/source/en/model_doc/resnet.md
-docs/source/en/model_doc/retribert.md
-docs/source/en/model_doc/roberta-prelayernorm.md
-docs/source/en/model_doc/roberta.md
-docs/source/en/model_doc/roc_bert.md
-docs/source/en/model_doc/roformer.md
-docs/source/en/model_doc/rwkv.md
-docs/source/en/model_doc/sam.md
-docs/source/en/model_doc/segformer.md
-docs/source/en/model_doc/sew-d.md
-docs/source/en/model_doc/sew.md
-docs/source/en/model_doc/speech-encoder-decoder.md
-docs/source/en/model_doc/speech_to_text_2.md
-docs/source/en/model_doc/speecht5.md
-docs/source/en/model_doc/splinter.md
-docs/source/en/model_doc/squeezebert.md
-docs/source/en/model_doc/swiftformer.md
-docs/source/en/model_doc/swin.md
-docs/source/en/model_doc/swin2sr.md
-docs/source/en/model_doc/swinv2.md
-docs/source/en/model_doc/table-transformer.md
-docs/source/en/model_doc/tapas.md
-docs/source/en/model_doc/time_series_transformer.md
-docs/source/en/model_doc/timesformer.md
-docs/source/en/model_doc/trajectory_transformer.md
-docs/source/en/model_doc/transfo-xl.md
-docs/source/en/model_doc/trocr.md
-docs/source/en/model_doc/tvlt.md
-docs/source/en/model_doc/ul2.md
-docs/source/en/model_doc/umt5.md
-docs/source/en/model_doc/unispeech-sat.md
-docs/source/en/model_doc/unispeech.md
-docs/source/en/model_doc/upernet.md
-docs/source/en/model_doc/van.md
-docs/source/en/model_doc/videomae.md
-docs/source/en/model_doc/vilt.md
-docs/source/en/model_doc/vision-encoder-decoder.md
-docs/source/en/model_doc/vision-text-dual-encoder.md
-docs/source/en/model_doc/visual_bert.md
-docs/source/en/model_doc/vit.md
-docs/source/en/model_doc/vit_hybrid.md
-docs/source/en/model_doc/vit_mae.md
-docs/source/en/model_doc/vit_msn.md
-docs/source/en/model_doc/vivit.md
-docs/source/en/model_doc/wav2vec2-conformer.md
-docs/source/en/model_doc/wav2vec2.md
-docs/source/en/model_doc/wav2vec2_phoneme.md
-docs/source/en/model_doc/wavlm.md
-docs/source/en/model_doc/whisper.md
-docs/source/en/model_doc/xclip.md
-docs/source/en/model_doc/xglm.md
-docs/source/en/model_doc/xlm-prophetnet.md
-docs/source/en/model_doc/xlm-roberta-xl.md
-docs/source/en/model_doc/xlm-roberta.md
-docs/source/en/model_doc/xlm-v.md
-docs/source/en/model_doc/xlm.md
-docs/source/en/model_doc/xlnet.md
-docs/source/en/model_doc/xls_r.md
-docs/source/en/model_doc/xlsr_wav2vec2.md
-docs/source/en/model_doc/xmod.md
-docs/source/en/model_doc/yolos.md
-docs/source/en/model_doc/yoso.md
-docs/source/en/model_memory_anatomy.md
-docs/source/en/model_sharing.md
-docs/source/en/model_summary.md
-docs/source/en/multilingual.md
-docs/source/en/notebooks.md
-docs/source/en/pad_truncation.md
-docs/source/en/peft.md
-docs/source/en/perf_hardware.md
-docs/source/en/perf_infer_cpu.md
-docs/source/en/perf_infer_gpu_one.md
-docs/source/en/perf_torch_compile.md
-docs/source/en/perf_train_cpu.md
-docs/source/en/perf_train_cpu_many.md
-docs/source/en/perf_train_gpu_many.md
-docs/source/en/perf_train_gpu_one.md
-docs/source/en/perf_train_special.md
-docs/source/en/perf_train_tpu.md
-docs/source/en/perf_train_tpu_tf.md
-docs/source/en/performance.md
-docs/source/en/perplexity.md
-docs/source/en/philosophy.md
-docs/source/en/pipeline_webserver.md
-docs/source/en/pr_checks.md
-docs/source/en/preprocessing.md
-docs/source/en/run_scripts.md
-docs/source/en/sagemaker.md
-docs/source/en/serialization.md
-docs/source/en/tasks/asr.md
-docs/source/en/tasks/audio_classification.md
-docs/source/en/tasks/document_question_answering.md
-docs/source/en/tasks/image_captioning.md
-docs/source/en/tasks/image_classification.md
-docs/source/en/tasks/language_modeling.md
-docs/source/en/tasks/masked_language_modeling.md
-docs/source/en/tasks/monocular_depth_estimation.md
-docs/source/en/tasks/multiple_choice.md
-docs/source/en/tasks/object_detection.md
-docs/source/en/tasks/question_answering.md
-docs/source/en/tasks/semantic_segmentation.md
-docs/source/en/tasks/sequence_classification.md
-docs/source/en/tasks/summarization.md
-docs/source/en/tasks/text-to-speech.md
-docs/source/en/tasks/token_classification.md
-docs/source/en/tasks/translation.md
-docs/source/en/tasks/video_classification.md
-docs/source/en/tasks/visual_question_answering.md
-docs/source/en/tasks/zero_shot_image_classification.md
-docs/source/en/tasks/zero_shot_object_detection.md
-docs/source/en/tasks_explained.md
-docs/source/en/tf_xla.md
-docs/source/en/tflite.md
-docs/source/en/tokenizer_summary.md
-docs/source/en/torchscript.md
-docs/source/en/training.md
-docs/source/en/transformers_agents.md
-docs/source/en/troubleshooting.md
-src/transformers/activations.py
-src/transformers/activations_tf.py
-src/transformers/audio_utils.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/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/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/data/data_collator.py
-src/transformers/data/datasets/glue.py
-src/transformers/data/datasets/language_modeling.py
-src/transformers/data/datasets/squad.py
-src/transformers/data/metrics/squad_metrics.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/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/hf_argparser.py
-src/transformers/hyperparameter_search.py
-src/transformers/image_processing_utils.py
-src/transformers/image_transforms.py
-src/transformers/image_utils.py
-src/transformers/integrations/bitsandbytes.py
-src/transformers/integrations/deepspeed.py
-src/transformers/integrations/integration_utils.py
-src/transformers/integrations/peft.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/models/albert/convert_albert_original_tf_checkpoint_to_pytorch.py
-src/transformers/models/albert/modeling_flax_albert.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/altclip/configuration_altclip.py
-src/transformers/models/altclip/modeling_altclip.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/auto/auto_factory.py
-src/transformers/models/auto/configuration_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/autoformer/configuration_autoformer.py
-src/transformers/models/autoformer/modeling_autoformer.py
-src/transformers/models/bark/convert_suno_to_hf.py
-src/transformers/models/bart/convert_bart_original_pytorch_checkpoint_to_pytorch.py
-src/transformers/models/bart/modeling_flax_bart.py
-src/transformers/models/bart/modeling_tf_bart.py
-src/transformers/models/beit/convert_beit_unilm_to_pytorch.py
-src/transformers/models/beit/modeling_flax_beit.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_flax_bert.py
-src/transformers/models/bert_generation/modeling_bert_generation.py
-src/transformers/models/big_bird/convert_bigbird_original_tf_checkpoint_to_pytorch.py
-src/transformers/models/big_bird/modeling_flax_big_bird.py
-src/transformers/models/bigbird_pegasus/convert_bigbird_pegasus_tf_to_pytorch.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/bit/configuration_bit.py
-src/transformers/models/bit/convert_bit_to_pytorch.py
-src/transformers/models/bit/modeling_bit.py
-src/transformers/models/blenderbot/convert_blenderbot_original_pytorch_checkpoint_to_pytorch.py
-src/transformers/models/blenderbot/modeling_flax_blenderbot.py
-src/transformers/models/blenderbot/modeling_tf_blenderbot.py
-src/transformers/models/blenderbot_small/modeling_flax_blenderbot_small.py
-src/transformers/models/blenderbot_small/modeling_tf_blenderbot_small.py
-src/transformers/models/blip/configuration_blip.py
-src/transformers/models/blip/convert_blip_original_pytorch_to_hf.py
-src/transformers/models/blip/modeling_blip_text.py
-src/transformers/models/blip/modeling_tf_blip_text.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/bloom/convert_bloom_original_checkpoint_to_pytorch.py
-src/transformers/models/bloom/modeling_bloom.py
-src/transformers/models/bloom/modeling_flax_bloom.py
-src/transformers/models/bridgetower/configuration_bridgetower.py
-src/transformers/models/bridgetower/modeling_bridgetower.py
-src/transformers/models/bros/convert_bros_to_pytorch.py
-src/transformers/models/byt5/convert_byt5_original_tf_checkpoint_to_pytorch.py
-src/transformers/models/camembert/modeling_camembert.py
-src/transformers/models/camembert/modeling_tf_camembert.py
-src/transformers/models/canine/convert_canine_original_tf_checkpoint_to_pytorch.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/modeling_chinese_clip.py
-src/transformers/models/clap/convert_clap_original_pytorch_to_hf.py
-src/transformers/models/clip/convert_clip_original_pytorch_to_hf.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/clipseg/configuration_clipseg.py
-src/transformers/models/clipseg/convert_clipseg_original_pytorch_to_hf.py
-src/transformers/models/codegen/modeling_codegen.py
-src/transformers/models/conditional_detr/convert_conditional_detr_original_pytorch_checkpoint_to_pytorch.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/convnext/convert_convnext_to_pytorch.py
-src/transformers/models/convnext/modeling_tf_convnext.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/cpmant/configuration_cpmant.py
-src/transformers/models/cpmant/modeling_cpmant.py
-src/transformers/models/cpmant/tokenization_cpmant.py
-src/transformers/models/ctrl/modeling_tf_ctrl.py
-src/transformers/models/cvt/convert_cvt_original_pytorch_checkpoint_to_pytorch.py
-src/transformers/models/cvt/modeling_tf_cvt.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_text.py
-src/transformers/models/data2vec/modeling_tf_data2vec_vision.py
-src/transformers/models/deberta/modeling_tf_deberta.py
-src/transformers/models/deberta_v2/modeling_tf_deberta_v2.py
-src/transformers/models/decision_transformer/modeling_decision_transformer.py
-src/transformers/models/deformable_detr/convert_deformable_detr_to_pytorch.py
-src/transformers/models/deformable_detr/load_custom.py
-src/transformers/models/deit/convert_deit_timm_to_pytorch.py
-src/transformers/models/deprecated/bort/convert_bort_original_gluonnlp_checkpoint_to_pytorch.py
-src/transformers/models/deprecated/mctct/configuration_mctct.py
-src/transformers/models/deprecated/mctct/feature_extraction_mctct.py
-src/transformers/models/deprecated/mctct/modeling_mctct.py
-src/transformers/models/deprecated/mctct/processing_mctct.py
-src/transformers/models/deprecated/mmbt/configuration_mmbt.py
-src/transformers/models/deprecated/mmbt/modeling_mmbt.py
-src/transformers/models/deprecated/open_llama/configuration_open_llama.py
-src/transformers/models/deprecated/open_llama/modeling_open_llama.py
-src/transformers/models/deprecated/retribert/configuration_retribert.py
-src/transformers/models/deprecated/retribert/modeling_retribert.py
-src/transformers/models/deprecated/retribert/tokenization_retribert.py
-src/transformers/models/deprecated/retribert/tokenization_retribert_fast.py
-src/transformers/models/deprecated/tapex/tokenization_tapex.py
-src/transformers/models/deprecated/trajectory_transformer/configuration_trajectory_transformer.py
-src/transformers/models/deprecated/trajectory_transformer/convert_trajectory_transformer_original_pytorch_checkpoint_to_pytorch.py
-src/transformers/models/deprecated/trajectory_transformer/modeling_trajectory_transformer.py
-src/transformers/models/deprecated/van/configuration_van.py
-src/transformers/models/deprecated/van/convert_van_to_pytorch.py
-src/transformers/models/deprecated/van/modeling_van.py
-src/transformers/models/deta/convert_deta_resnet_to_pytorch.py
-src/transformers/models/deta/convert_deta_swin_to_pytorch.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/dialogpt/convert_dialogpt_original_pytorch_checkpoint_to_pytorch.py
-src/transformers/models/dinov2/configuration_dinov2.py
-src/transformers/models/dinov2/convert_dinov2_to_hf.py
-src/transformers/models/dinov2/modeling_dinov2.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/dit/convert_dit_unilm_to_pytorch.py
-src/transformers/models/donut/configuration_donut_swin.py
-src/transformers/models/donut/convert_donut_to_pytorch.py
-src/transformers/models/donut/modeling_donut_swin.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/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/efficientformer/configuration_efficientformer.py
-src/transformers/models/efficientformer/convert_efficientformer_original_pytorch_checkpoint_to_pytorch.py
-src/transformers/models/efficientformer/modeling_efficientformer.py
-src/transformers/models/efficientnet/configuration_efficientnet.py
-src/transformers/models/efficientnet/convert_efficientnet_to_pytorch.py
-src/transformers/models/efficientnet/modeling_efficientnet.py
-src/transformers/models/electra/convert_electra_original_tf_checkpoint_to_pytorch.py
-src/transformers/models/electra/modeling_flax_electra.py
-src/transformers/models/encodec/configuration_encodec.py
-src/transformers/models/encodec/convert_encodec_checkpoint_to_pytorch.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/modeling_ernie.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/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/falcon/configuration_falcon.py
-src/transformers/models/falcon/modeling_falcon.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/flava/convert_dalle_to_flava_codebook.py
-src/transformers/models/flava/convert_flava_original_pytorch_to_hf.py
-src/transformers/models/flava/modeling_flava.py
-src/transformers/models/fnet/convert_fnet_original_flax_checkpoint_to_pytorch.py
-src/transformers/models/fnet/modeling_fnet.py
-src/transformers/models/focalnet/configuration_focalnet.py
-src/transformers/models/focalnet/convert_focalnet_to_hf_format.py
-src/transformers/models/focalnet/modeling_focalnet.py
-src/transformers/models/fsmt/convert_fsmt_original_pytorch_checkpoint_to_pytorch.py
-src/transformers/models/fsmt/modeling_fsmt.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/fuyu/convert_fuyu_model_weights_to_hf.py
-src/transformers/models/git/configuration_git.py
-src/transformers/models/git/convert_git_to_pytorch.py
-src/transformers/models/glpn/configuration_glpn.py
-src/transformers/models/glpn/convert_glpn_to_pytorch.py
-src/transformers/models/gpt2/CONVERSION.md
-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_tf_gpt2.py
-src/transformers/models/gpt_bigcode/configuration_gpt_bigcode.py
-src/transformers/models/gpt_bigcode/modeling_gpt_bigcode.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/modeling_gpt_neox.py
-src/transformers/models/gpt_neox_japanese/modeling_gpt_neox_japanese.py
-src/transformers/models/gpt_sw3/convert_megatron_to_pytorch.py
-src/transformers/models/gptj/configuration_gptj.py
-src/transformers/models/gptj/modeling_flax_gptj.py
-src/transformers/models/gptj/modeling_tf_gptj.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/graphormer/collating_graphormer.py
-src/transformers/models/graphormer/configuration_graphormer.py
-src/transformers/models/graphormer/modeling_graphormer.py
-src/transformers/models/groupvit/configuration_groupvit.py
-src/transformers/models/groupvit/convert_groupvit_nvlab_to_hf.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_tf_hubert.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/idefics/configuration_idefics.py
-src/transformers/models/idefics/image_processing_idefics.py
-src/transformers/models/idefics/modeling_idefics.py
-src/transformers/models/idefics/perceiver.py
-src/transformers/models/idefics/processing_idefics.py
-src/transformers/models/idefics/vision.py
-src/transformers/models/imagegpt/convert_imagegpt_original_tf2_to_pytorch.py
-src/transformers/models/informer/configuration_informer.py
-src/transformers/models/informer/modeling_informer.py
-src/transformers/models/instructblip/configuration_instructblip.py
-src/transformers/models/instructblip/convert_instructblip_original_to_pytorch.py
-src/transformers/models/instructblip/modeling_instructblip.py
-src/transformers/models/instructblip/processing_instructblip.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/kosmos2/convert_kosmos2_original_pytorch_checkpoint_to_pytorch.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/levit/convert_levit_timm_to_pytorch.py
-src/transformers/models/levit/modeling_levit.py
-src/transformers/models/lilt/configuration_lilt.py
-src/transformers/models/llama/configuration_llama.py
-src/transformers/models/llama/convert_llama_weights_to_hf.py
-src/transformers/models/llama/modeling_llama.py
-src/transformers/models/longformer/configuration_longformer.py
-src/transformers/models/longformer/convert_longformer_original_pytorch_lightning_to_pytorch.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/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/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/m2m_100/convert_m2m100_original_checkpoint_to_pytorch.py
-src/transformers/models/m2m_100/modeling_m2m_100.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_tf_marian.py
-src/transformers/models/markuplm/configuration_markuplm.py
-src/transformers/models/markuplm/feature_extraction_markuplm.py
-src/transformers/models/mask2former/convert_mask2former_original_pytorch_checkpoint_to_pytorch.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/modeling_maskformer_swin.py
-src/transformers/models/mbart/convert_mbart_original_checkpoint_to_pytorch.py
-src/transformers/models/mbart/modeling_flax_mbart.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/convert_megatron_bert_checkpoint.py
-src/transformers/models/megatron_bert/modeling_megatron_bert.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/configuration_mgp_str.py
-src/transformers/models/mgp_str/modeling_mgp_str.py
-src/transformers/models/mistral/configuration_mistral.py
-src/transformers/models/mistral/modeling_mistral.py
-src/transformers/models/mluke/convert_mluke_original_pytorch_checkpoint_to_pytorch.py
-src/transformers/models/mobilebert/convert_mobilebert_original_tf_checkpoint_to_pytorch.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_v2/configuration_mobilenet_v2.py
-src/transformers/models/mobilenet_v2/convert_original_tf_checkpoint_to_pytorch.py
-src/transformers/models/mobilevit/configuration_mobilevit.py
-src/transformers/models/mobilevit/convert_mlcvnets_to_pytorch.py
-src/transformers/models/mobilevitv2/convert_mlcvnets_to_pytorch.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/mpt/configuration_mpt.py
-src/transformers/models/mpt/modeling_mpt.py
-src/transformers/models/mra/configuration_mra.py
-src/transformers/models/mra/convert_mra_pytorch_to_pytorch.py
-src/transformers/models/mra/modeling_mra.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/musicgen/convert_musicgen_transformers.py
-src/transformers/models/mvp/modeling_mvp.py
-src/transformers/models/nezha/modeling_nezha.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/nougat/convert_nougat_to_hf.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/convert_to_hf_oneformer.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/opt/convert_opt_original_pytorch_checkpoint_to_pytorch.py
-src/transformers/models/opt/modeling_flax_opt.py
-src/transformers/models/owlvit/configuration_owlvit.py
-src/transformers/models/owlvit/convert_owlvit_original_flax_to_hf.py
-src/transformers/models/pegasus/convert_pegasus_tf_to_pytorch.py
-src/transformers/models/pegasus/modeling_flax_pegasus.py
-src/transformers/models/pegasus/modeling_tf_pegasus.py
-src/transformers/models/pegasus_x/modeling_pegasus_x.py
-src/transformers/models/perceiver/configuration_perceiver.py
-src/transformers/models/perceiver/convert_perceiver_haiku_to_pytorch.py
-src/transformers/models/persimmon/convert_persimmon_weights_to_hf.py
-src/transformers/models/persimmon/modeling_persimmon.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/processing_pix2struct.py
-src/transformers/models/plbart/convert_plbart_original_checkpoint_to_torch.py
-src/transformers/models/poolformer/convert_poolformer_original_to_pytorch.py
-src/transformers/models/pop2piano/convert_pop2piano_weights_to_hf.py
-src/transformers/models/pop2piano/feature_extraction_pop2piano.py
-src/transformers/models/pop2piano/processing_pop2piano.py
-src/transformers/models/pop2piano/tokenization_pop2piano.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/pvt/configuration_pvt.py
-src/transformers/models/pvt/convert_pvt_to_pytorch.py
-src/transformers/models/pvt/image_processing_pvt.py
-src/transformers/models/pvt/modeling_pvt.py
-src/transformers/models/qdqbert/configuration_qdqbert.py
-src/transformers/models/qdqbert/modeling_qdqbert.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/realm/modeling_realm.py
-src/transformers/models/realm/retrieval_realm.py
-src/transformers/models/reformer/convert_reformer_trax_checkpoint_to_pytorch.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_flax_regnet.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/resnet/convert_resnet_to_pytorch.py
-src/transformers/models/resnet/modeling_flax_resnet.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_prelayernorm/convert_roberta_prelayernorm_original_pytorch_checkpoint_to_pytorch.py
-src/transformers/models/roberta_prelayernorm/modeling_flax_roberta_prelayernorm.py
-src/transformers/models/roc_bert/configuration_roc_bert.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/rwkv/configuration_rwkv.py
-src/transformers/models/rwkv/convert_rwkv_checkpoint_to_hf.py
-src/transformers/models/rwkv/modeling_rwkv.py
-src/transformers/models/sam/configuration_sam.py
-src/transformers/models/sam/convert_sam_original_to_hf_format.py
-src/transformers/models/sam/image_processing_sam.py
-src/transformers/models/sam/modeling_sam.py
-src/transformers/models/sam/modeling_tf_sam.py
-src/transformers/models/sam/processing_sam.py
-src/transformers/models/seamless_m4t/convert_fairseq2_to_hf.py
-src/transformers/models/segformer/configuration_segformer.py
-src/transformers/models/segformer/convert_segformer_original_to_pytorch.py
-src/transformers/models/sew/convert_sew_original_pytorch_checkpoint_to_pytorch.py
-src/transformers/models/sew_d/convert_sew_d_original_pytorch_checkpoint_to_pytorch.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_to_text/convert_s2t_fairseq_to_tfms.py
-src/transformers/models/speech_to_text/modeling_tf_speech_to_text.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/number_normalizer.py
-src/transformers/models/splinter/configuration_splinter.py
-src/transformers/models/splinter/modeling_splinter.py
-src/transformers/models/squeezebert/modeling_squeezebert.py
-src/transformers/models/swiftformer/configuration_swiftformer.py
-src/transformers/models/swiftformer/convert_swiftformer_original_to_hf.py
-src/transformers/models/swiftformer/modeling_swiftformer.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_tf_swin.py
-src/transformers/models/swin2sr/configuration_swin2sr.py
-src/transformers/models/swin2sr/convert_swin2sr_original_to_pytorch.py
-src/transformers/models/swinv2/convert_swinv2_timm_to_pytorch.py
-src/transformers/models/swinv2/modeling_swinv2.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/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/table_transformer/configuration_table_transformer.py
-src/transformers/models/table_transformer/convert_table_transformer_original_pytorch_checkpoint_to_pytorch.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/timesformer/convert_timesformer_to_pytorch.py
-src/transformers/models/timm_backbone/configuration_timm_backbone.py
-src/transformers/models/timm_backbone/modeling_timm_backbone.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/trocr/convert_trocr_unilm_to_pytorch.py
-src/transformers/models/tvlt/configuration_tvlt.py
-src/transformers/models/tvlt/modeling_tvlt.py
-src/transformers/models/umt5/configuration_umt5.py
-src/transformers/models/umt5/convert_umt5_checkpoint_to_pytorch.py
-src/transformers/models/umt5/modeling_umt5.py
-src/transformers/models/unispeech/convert_unispeech_original_pytorch_checkpoint_to_pytorch.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/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/videomae/configuration_videomae.py
-src/transformers/models/videomae/convert_videomae_to_pytorch.py
-src/transformers/models/vilt/configuration_vilt.py
-src/transformers/models/vilt/convert_vilt_original_to_pytorch.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_text_dual_encoder/modeling_flax_vision_text_dual_encoder.py
-src/transformers/models/vision_text_dual_encoder/modeling_vision_text_dual_encoder.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/convert_dino_to_pytorch.py
-src/transformers/models/vit/convert_vit_timm_to_pytorch.py
-src/transformers/models/vit/modeling_flax_vit.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/modeling_vit_hybrid.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_msn/configuration_vit_msn.py
-src/transformers/models/vit_msn/convert_msn_to_pytorch.py
-src/transformers/models/vivit/configuration_vivit.py
-src/transformers/models/vivit/convert_vivit_flax_to_pytorch.py
-src/transformers/models/vivit/image_processing_vivit.py
-src/transformers/models/vivit/modeling_vivit.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/modeling_flax_wav2vec2.py
-src/transformers/models/wav2vec2/modeling_tf_wav2vec2.py
-src/transformers/models/wav2vec2_conformer/convert_wav2vec2_conformer_original_pytorch_checkpoint_to_pytorch.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/whisper/convert_openai_to_hf.py
-src/transformers/models/whisper/english_normalizer.py
-src/transformers/models/whisper/modeling_flax_whisper.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/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/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_prophetnet/configuration_xlm_prophetnet.py
-src/transformers/models/xlm_prophetnet/modeling_xlm_prophetnet.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_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/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/xmod/convert_xmod_original_pytorch_checkpoint_to_pytorch.py
-src/transformers/models/yolos/convert_yolos_to_pytorch.py
-src/transformers/models/yoso/convert_yoso_pytorch_to_pytorch.py
-src/transformers/models/yoso/modeling_yoso.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/optimization.py
-src/transformers/optimization_tf.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/mask_generation.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/text_classification.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/processing_utils.py
-src/transformers/pytorch_utils.py
-src/transformers/sagemaker/trainer_sm.py
-src/transformers/sagemaker/training_args_sm.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/tools/agent_types.py
-src/transformers/tools/agents.py
-src/transformers/tools/base.py
-src/transformers/tools/document_question_answering.py
-src/transformers/tools/evaluate_agent.py
-src/transformers/tools/image_captioning.py
-src/transformers/tools/image_question_answering.py
-src/transformers/tools/image_segmentation.py
-src/transformers/tools/prompts.py
-src/transformers/tools/python_interpreter.py
-src/transformers/tools/speech_to_text.py
-src/transformers/tools/text_classification.py
-src/transformers/tools/text_question_answering.py
-src/transformers/tools/text_summarization.py
-src/transformers/tools/text_to_speech.py
-src/transformers/tools/translation.py
-src/transformers/trainer.py
-src/transformers/trainer_callback.py
-src/transformers/trainer_pt_utils.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/utils/backbone_utils.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_essentia_and_librosa_and_pretty_midi_and_scipy_and_torch_objects.py
-src/transformers/utils/dummy_flax_objects.py
-src/transformers/utils/dummy_keras_nlp_objects.py
-src/transformers/utils/dummy_music_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/peft_utils.py
-src/transformers/utils/quantization_config.py
-src/transformers/utils/sentencepiece_model_pb2.py
-src/transformers/utils/sentencepiece_model_pb2_new.py
-src/transformers/utils/versions.py
+docs/source/en/_config.py
+docs/source/en/accelerate.md
+docs/source/en/add_new_model.md
+docs/source/en/add_new_pipeline.md
+docs/source/en/add_tensorflow_model.md
+docs/source/en/attention.md
+docs/source/en/benchmarks.md
+docs/source/en/bertology.md
+docs/source/en/big_models.md
+docs/source/en/community.md
+docs/source/en/contributing.md
+docs/source/en/create_a_model.md
+docs/source/en/custom_models.md
+docs/source/en/custom_tools.md
+docs/source/en/debugging.md
+docs/source/en/fast_tokenizers.md
+docs/source/en/glossary.md
+docs/source/en/hpo_train.md
+docs/source/en/index.md
+docs/source/en/installation.md
+docs/source/en/internal/audio_utils.md
+docs/source/en/internal/file_utils.md
+docs/source/en/internal/image_processing_utils.md
+docs/source/en/internal/modeling_utils.md
+docs/source/en/internal/pipelines_utils.md
+docs/source/en/internal/time_series_utils.md
+docs/source/en/internal/tokenization_utils.md
+docs/source/en/internal/trainer_utils.md
+docs/source/en/llm_tutorial.md
+docs/source/en/main_classes/agent.md
+docs/source/en/main_classes/callback.md
+docs/source/en/main_classes/configuration.md
+docs/source/en/main_classes/data_collator.md
+docs/source/en/main_classes/deepspeed.md
+docs/source/en/main_classes/feature_extractor.md
+docs/source/en/main_classes/image_processor.md
+docs/source/en/main_classes/keras_callbacks.md
+docs/source/en/main_classes/logging.md
+docs/source/en/main_classes/model.md
+docs/source/en/main_classes/onnx.md
+docs/source/en/main_classes/optimizer_schedules.md
+docs/source/en/main_classes/output.md
+docs/source/en/main_classes/pipelines.md
+docs/source/en/main_classes/processors.md
+docs/source/en/main_classes/quantization.md
+docs/source/en/main_classes/tokenizer.md
+docs/source/en/main_classes/trainer.md
+docs/source/en/model_doc/albert.md
+docs/source/en/model_doc/align.md
+docs/source/en/model_doc/altclip.md
+docs/source/en/model_doc/audio-spectrogram-transformer.md
+docs/source/en/model_doc/auto.md
+docs/source/en/model_doc/autoformer.md
+docs/source/en/model_doc/bark.md
+docs/source/en/model_doc/bart.md
+docs/source/en/model_doc/barthez.md
+docs/source/en/model_doc/bartpho.md
+docs/source/en/model_doc/beit.md
+docs/source/en/model_doc/bert-generation.md
+docs/source/en/model_doc/bert-japanese.md
+docs/source/en/model_doc/bert.md
+docs/source/en/model_doc/bertweet.md
+docs/source/en/model_doc/big_bird.md
+docs/source/en/model_doc/bigbird_pegasus.md
+docs/source/en/model_doc/biogpt.md
+docs/source/en/model_doc/bit.md
+docs/source/en/model_doc/blenderbot-small.md
+docs/source/en/model_doc/blenderbot.md
+docs/source/en/model_doc/blip-2.md
+docs/source/en/model_doc/blip.md
+docs/source/en/model_doc/bloom.md
+docs/source/en/model_doc/bort.md
+docs/source/en/model_doc/bridgetower.md
+docs/source/en/model_doc/camembert.md
+docs/source/en/model_doc/canine.md
+docs/source/en/model_doc/chinese_clip.md
+docs/source/en/model_doc/clap.md
+docs/source/en/model_doc/clip.md
+docs/source/en/model_doc/clipseg.md
+docs/source/en/model_doc/codegen.md
+docs/source/en/model_doc/conditional_detr.md
+docs/source/en/model_doc/convbert.md
+docs/source/en/model_doc/convnext.md
+docs/source/en/model_doc/convnextv2.md
+docs/source/en/model_doc/cpm.md
+docs/source/en/model_doc/cpmant.md
+docs/source/en/model_doc/ctrl.md
+docs/source/en/model_doc/cvt.md
+docs/source/en/model_doc/data2vec.md
+docs/source/en/model_doc/deberta-v2.md
+docs/source/en/model_doc/deberta.md
+docs/source/en/model_doc/decision_transformer.md
+docs/source/en/model_doc/deformable_detr.md
+docs/source/en/model_doc/deit.md
+docs/source/en/model_doc/deplot.md
+docs/source/en/model_doc/deta.md
+docs/source/en/model_doc/detr.md
+docs/source/en/model_doc/dialogpt.md
+docs/source/en/model_doc/dinat.md
+docs/source/en/model_doc/dinov2.md
+docs/source/en/model_doc/distilbert.md
+docs/source/en/model_doc/dit.md
+docs/source/en/model_doc/dpr.md
+docs/source/en/model_doc/dpt.md
+docs/source/en/model_doc/efficientformer.md
+docs/source/en/model_doc/efficientnet.md
+docs/source/en/model_doc/electra.md
+docs/source/en/model_doc/encodec.md
+docs/source/en/model_doc/ernie.md
+docs/source/en/model_doc/ernie_m.md
+docs/source/en/model_doc/esm.md
+docs/source/en/model_doc/flan-t5.md
+docs/source/en/model_doc/flan-ul2.md
+docs/source/en/model_doc/flaubert.md
+docs/source/en/model_doc/flava.md
+docs/source/en/model_doc/fnet.md
+docs/source/en/model_doc/focalnet.md
+docs/source/en/model_doc/fsmt.md
+docs/source/en/model_doc/funnel.md
+docs/source/en/model_doc/git.md
+docs/source/en/model_doc/glpn.md
+docs/source/en/model_doc/gpt-sw3.md
+docs/source/en/model_doc/gpt2.md
+docs/source/en/model_doc/gpt_bigcode.md
+docs/source/en/model_doc/gpt_neo.md
+docs/source/en/model_doc/gpt_neox.md
+docs/source/en/model_doc/gpt_neox_japanese.md
+docs/source/en/model_doc/gptj.md
+docs/source/en/model_doc/gptsan-japanese.md
+docs/source/en/model_doc/graphormer.md
+docs/source/en/model_doc/groupvit.md
+docs/source/en/model_doc/herbert.md
+docs/source/en/model_doc/hubert.md
+docs/source/en/model_doc/ibert.md
+docs/source/en/model_doc/idefics.md
+docs/source/en/model_doc/imagegpt.md
+docs/source/en/model_doc/informer.md
+docs/source/en/model_doc/instructblip.md
+docs/source/en/model_doc/jukebox.md
+docs/source/en/model_doc/layoutlm.md
+docs/source/en/model_doc/layoutlmv2.md
+docs/source/en/model_doc/layoutlmv3.md
+docs/source/en/model_doc/layoutxlm.md
+docs/source/en/model_doc/led.md
+docs/source/en/model_doc/levit.md
+docs/source/en/model_doc/lilt.md
+docs/source/en/model_doc/llama.md
+docs/source/en/model_doc/llama2.md
+docs/source/en/model_doc/longformer.md
+docs/source/en/model_doc/longt5.md
+docs/source/en/model_doc/luke.md
+docs/source/en/model_doc/lxmert.md
+docs/source/en/model_doc/m2m_100.md
+docs/source/en/model_doc/marian.md
+docs/source/en/model_doc/mask2former.md
+docs/source/en/model_doc/maskformer.md
+docs/source/en/model_doc/matcha.md
+docs/source/en/model_doc/mbart.md
+docs/source/en/model_doc/mctct.md
+docs/source/en/model_doc/mega.md
+docs/source/en/model_doc/megatron-bert.md
+docs/source/en/model_doc/megatron_gpt2.md
+docs/source/en/model_doc/mgp-str.md
+docs/source/en/model_doc/mistral.md
+docs/source/en/model_doc/mluke.md
+docs/source/en/model_doc/mms.md
+docs/source/en/model_doc/mobilebert.md
+docs/source/en/model_doc/mobilenet_v1.md
+docs/source/en/model_doc/mobilenet_v2.md
+docs/source/en/model_doc/mobilevit.md
+docs/source/en/model_doc/mobilevitv2.md
+docs/source/en/model_doc/mpnet.md
+docs/source/en/model_doc/mpt.md
+docs/source/en/model_doc/mra.md
+docs/source/en/model_doc/mt5.md
+docs/source/en/model_doc/musicgen.md
+docs/source/en/model_doc/mvp.md
+docs/source/en/model_doc/nat.md
+docs/source/en/model_doc/nezha.md
+docs/source/en/model_doc/nllb-moe.md
+docs/source/en/model_doc/nllb.md
+docs/source/en/model_doc/nystromformer.md
+docs/source/en/model_doc/oneformer.md
+docs/source/en/model_doc/open-llama.md
+docs/source/en/model_doc/openai-gpt.md
+docs/source/en/model_doc/opt.md
+docs/source/en/model_doc/owlvit.md
+docs/source/en/model_doc/pegasus.md
+docs/source/en/model_doc/pegasus_x.md
+docs/source/en/model_doc/perceiver.md
+docs/source/en/model_doc/phobert.md
+docs/source/en/model_doc/pix2struct.md
+docs/source/en/model_doc/plbart.md
+docs/source/en/model_doc/poolformer.md
+docs/source/en/model_doc/pop2piano.md
+docs/source/en/model_doc/prophetnet.md
+docs/source/en/model_doc/pvt.md
+docs/source/en/model_doc/qdqbert.md
+docs/source/en/model_doc/rag.md
+docs/source/en/model_doc/realm.md
+docs/source/en/model_doc/reformer.md
+docs/source/en/model_doc/regnet.md
+docs/source/en/model_doc/rembert.md
+docs/source/en/model_doc/resnet.md
+docs/source/en/model_doc/retribert.md
+docs/source/en/model_doc/roberta-prelayernorm.md
+docs/source/en/model_doc/roberta.md
+docs/source/en/model_doc/roc_bert.md
+docs/source/en/model_doc/roformer.md
+docs/source/en/model_doc/rwkv.md
+docs/source/en/model_doc/sam.md
+docs/source/en/model_doc/segformer.md
+docs/source/en/model_doc/sew-d.md
+docs/source/en/model_doc/sew.md
+docs/source/en/model_doc/speech-encoder-decoder.md
+docs/source/en/model_doc/speech_to_text_2.md
+docs/source/en/model_doc/speecht5.md
+docs/source/en/model_doc/splinter.md
+docs/source/en/model_doc/squeezebert.md
+docs/source/en/model_doc/swiftformer.md
+docs/source/en/model_doc/swin.md
+docs/source/en/model_doc/swin2sr.md
+docs/source/en/model_doc/swinv2.md
+docs/source/en/model_doc/table-transformer.md
+docs/source/en/model_doc/tapas.md
+docs/source/en/model_doc/time_series_transformer.md
+docs/source/en/model_doc/timesformer.md
+docs/source/en/model_doc/trajectory_transformer.md
+docs/source/en/model_doc/transfo-xl.md
+docs/source/en/model_doc/trocr.md
+docs/source/en/model_doc/tvlt.md
+docs/source/en/model_doc/ul2.md
+docs/source/en/model_doc/umt5.md
+docs/source/en/model_doc/unispeech-sat.md
+docs/source/en/model_doc/unispeech.md
+docs/source/en/model_doc/upernet.md
+docs/source/en/model_doc/van.md
+docs/source/en/model_doc/videomae.md
+docs/source/en/model_doc/vilt.md
+docs/source/en/model_doc/vision-encoder-decoder.md
+docs/source/en/model_doc/vision-text-dual-encoder.md
+docs/source/en/model_doc/visual_bert.md
+docs/source/en/model_doc/vit.md
+docs/source/en/model_doc/vit_hybrid.md
+docs/source/en/model_doc/vit_mae.md
+docs/source/en/model_doc/vit_msn.md
+docs/source/en/model_doc/vivit.md
+docs/source/en/model_doc/wav2vec2-conformer.md
+docs/source/en/model_doc/wav2vec2.md
+docs/source/en/model_doc/wav2vec2_phoneme.md
+docs/source/en/model_doc/wavlm.md
+docs/source/en/model_doc/whisper.md
+docs/source/en/model_doc/xclip.md
+docs/source/en/model_doc/xglm.md
+docs/source/en/model_doc/xlm-prophetnet.md
+docs/source/en/model_doc/xlm-roberta-xl.md
+docs/source/en/model_doc/xlm-roberta.md
+docs/source/en/model_doc/xlm-v.md
+docs/source/en/model_doc/xlm.md
+docs/source/en/model_doc/xlnet.md
+docs/source/en/model_doc/xls_r.md
+docs/source/en/model_doc/xlsr_wav2vec2.md
+docs/source/en/model_doc/xmod.md
+docs/source/en/model_doc/yolos.md
+docs/source/en/model_doc/yoso.md
+docs/source/en/model_memory_anatomy.md
+docs/source/en/model_sharing.md
+docs/source/en/model_summary.md
+docs/source/en/multilingual.md
+docs/source/en/notebooks.md
+docs/source/en/pad_truncation.md
+docs/source/en/peft.md
+docs/source/en/perf_hardware.md
+docs/source/en/perf_infer_cpu.md
+docs/source/en/perf_infer_gpu_one.md
+docs/source/en/perf_torch_compile.md
+docs/source/en/perf_train_cpu.md
+docs/source/en/perf_train_cpu_many.md
+docs/source/en/perf_train_gpu_many.md
+docs/source/en/perf_train_gpu_one.md
+docs/source/en/perf_train_special.md
+docs/source/en/perf_train_tpu.md
+docs/source/en/perf_train_tpu_tf.md
+docs/source/en/performance.md
+docs/source/en/perplexity.md
+docs/source/en/philosophy.md
+docs/source/en/pipeline_webserver.md
+docs/source/en/pr_checks.md
+docs/source/en/preprocessing.md
+docs/source/en/run_scripts.md
+docs/source/en/sagemaker.md
+docs/source/en/serialization.md
+docs/source/en/tasks/asr.md
+docs/source/en/tasks/audio_classification.md
+docs/source/en/tasks/document_question_answering.md
+docs/source/en/tasks/idefics.md  # causes other tests to fail
+docs/source/en/tasks/image_captioning.md
+docs/source/en/tasks/image_classification.md
+docs/source/en/tasks/language_modeling.md
+docs/source/en/tasks/masked_language_modeling.md
+docs/source/en/tasks/monocular_depth_estimation.md
+docs/source/en/tasks/multiple_choice.md
+docs/source/en/tasks/object_detection.md
+docs/source/en/tasks/question_answering.md
+docs/source/en/tasks/semantic_segmentation.md
+docs/source/en/tasks/sequence_classification.md
+docs/source/en/tasks/summarization.md
+docs/source/en/tasks/text-to-speech.md
+docs/source/en/tasks/token_classification.md
+docs/source/en/tasks/translation.md
+docs/source/en/tasks/video_classification.md
+docs/source/en/tasks/visual_question_answering.md
+docs/source/en/tasks/zero_shot_image_classification.md
+docs/source/en/tasks/zero_shot_object_detection.md
+docs/source/en/tasks_explained.md
+docs/source/en/tf_xla.md
+docs/source/en/tflite.md
+docs/source/en/tokenizer_summary.md
+docs/source/en/torchscript.md
+docs/source/en/training.md
+docs/source/en/transformers_agents.md
+docs/source/en/troubleshooting.md
+src/transformers/activations.py
+src/transformers/activations_tf.py
+src/transformers/audio_utils.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/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/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/data/data_collator.py
+src/transformers/data/datasets/glue.py
+src/transformers/data/datasets/language_modeling.py
+src/transformers/data/datasets/squad.py
+src/transformers/data/metrics/squad_metrics.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/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/hf_argparser.py
+src/transformers/hyperparameter_search.py
+src/transformers/image_processing_utils.py
+src/transformers/image_transforms.py
+src/transformers/image_utils.py
+src/transformers/integrations/bitsandbytes.py
+src/transformers/integrations/deepspeed.py
+src/transformers/integrations/integration_utils.py
+src/transformers/integrations/peft.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/models/albert/convert_albert_original_tf_checkpoint_to_pytorch.py
+src/transformers/models/albert/modeling_flax_albert.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/altclip/configuration_altclip.py
+src/transformers/models/altclip/modeling_altclip.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/auto/auto_factory.py
+src/transformers/models/auto/configuration_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/autoformer/configuration_autoformer.py
+src/transformers/models/autoformer/modeling_autoformer.py
+src/transformers/models/bark/convert_suno_to_hf.py
+src/transformers/models/bart/convert_bart_original_pytorch_checkpoint_to_pytorch.py
+src/transformers/models/bart/modeling_flax_bart.py
+src/transformers/models/bart/modeling_tf_bart.py
+src/transformers/models/beit/convert_beit_unilm_to_pytorch.py
+src/transformers/models/beit/modeling_flax_beit.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_flax_bert.py
+src/transformers/models/bert_generation/modeling_bert_generation.py
+src/transformers/models/big_bird/convert_bigbird_original_tf_checkpoint_to_pytorch.py
+src/transformers/models/big_bird/modeling_flax_big_bird.py
+src/transformers/models/bigbird_pegasus/convert_bigbird_pegasus_tf_to_pytorch.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/bit/configuration_bit.py
+src/transformers/models/bit/convert_bit_to_pytorch.py
+src/transformers/models/bit/modeling_bit.py
+src/transformers/models/blenderbot/convert_blenderbot_original_pytorch_checkpoint_to_pytorch.py
+src/transformers/models/blenderbot/modeling_flax_blenderbot.py
+src/transformers/models/blenderbot/modeling_tf_blenderbot.py
+src/transformers/models/blenderbot_small/modeling_flax_blenderbot_small.py
+src/transformers/models/blenderbot_small/modeling_tf_blenderbot_small.py
+src/transformers/models/blip/configuration_blip.py
+src/transformers/models/blip/convert_blip_original_pytorch_to_hf.py
+src/transformers/models/blip/modeling_blip_text.py
+src/transformers/models/blip/modeling_tf_blip_text.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  # causes other tests to fail
+src/transformers/models/bloom/convert_bloom_original_checkpoint_to_pytorch.py
+src/transformers/models/bloom/modeling_bloom.py
+src/transformers/models/bloom/modeling_flax_bloom.py
+src/transformers/models/bridgetower/configuration_bridgetower.py
+src/transformers/models/bridgetower/modeling_bridgetower.py
+src/transformers/models/bros/convert_bros_to_pytorch.py
+src/transformers/models/byt5/convert_byt5_original_tf_checkpoint_to_pytorch.py
+src/transformers/models/camembert/modeling_camembert.py
+src/transformers/models/camembert/modeling_tf_camembert.py
+src/transformers/models/canine/convert_canine_original_tf_checkpoint_to_pytorch.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/modeling_chinese_clip.py
+src/transformers/models/clap/convert_clap_original_pytorch_to_hf.py
+src/transformers/models/clip/convert_clip_original_pytorch_to_hf.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/clipseg/configuration_clipseg.py
+src/transformers/models/clipseg/convert_clipseg_original_pytorch_to_hf.py
+src/transformers/models/codegen/modeling_codegen.py
+src/transformers/models/conditional_detr/convert_conditional_detr_original_pytorch_checkpoint_to_pytorch.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/convnext/convert_convnext_to_pytorch.py
+src/transformers/models/convnext/modeling_tf_convnext.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/cpmant/configuration_cpmant.py
+src/transformers/models/cpmant/modeling_cpmant.py
+src/transformers/models/cpmant/tokenization_cpmant.py
+src/transformers/models/ctrl/modeling_tf_ctrl.py
+src/transformers/models/cvt/convert_cvt_original_pytorch_checkpoint_to_pytorch.py
+src/transformers/models/cvt/modeling_tf_cvt.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_text.py
+src/transformers/models/data2vec/modeling_tf_data2vec_vision.py
+src/transformers/models/deberta/modeling_tf_deberta.py
+src/transformers/models/deberta_v2/modeling_tf_deberta_v2.py
+src/transformers/models/decision_transformer/modeling_decision_transformer.py
+src/transformers/models/deformable_detr/convert_deformable_detr_to_pytorch.py
+src/transformers/models/deformable_detr/load_custom.py
+src/transformers/models/deit/convert_deit_timm_to_pytorch.py
+src/transformers/models/deprecated/bort/convert_bort_original_gluonnlp_checkpoint_to_pytorch.py
+src/transformers/models/deprecated/mctct/configuration_mctct.py
+src/transformers/models/deprecated/mctct/feature_extraction_mctct.py
+src/transformers/models/deprecated/mctct/modeling_mctct.py
+src/transformers/models/deprecated/mctct/processing_mctct.py
+src/transformers/models/deprecated/mmbt/configuration_mmbt.py
+src/transformers/models/deprecated/mmbt/modeling_mmbt.py
+src/transformers/models/deprecated/open_llama/configuration_open_llama.py
+src/transformers/models/deprecated/open_llama/modeling_open_llama.py
+src/transformers/models/deprecated/retribert/configuration_retribert.py
+src/transformers/models/deprecated/retribert/modeling_retribert.py
+src/transformers/models/deprecated/retribert/tokenization_retribert.py
+src/transformers/models/deprecated/retribert/tokenization_retribert_fast.py
+src/transformers/models/deprecated/tapex/tokenization_tapex.py
+src/transformers/models/deprecated/trajectory_transformer/configuration_trajectory_transformer.py
+src/transformers/models/deprecated/trajectory_transformer/convert_trajectory_transformer_original_pytorch_checkpoint_to_pytorch.py
+src/transformers/models/deprecated/trajectory_transformer/modeling_trajectory_transformer.py
+src/transformers/models/deprecated/van/configuration_van.py
+src/transformers/models/deprecated/van/convert_van_to_pytorch.py
+src/transformers/models/deprecated/van/modeling_van.py
+src/transformers/models/deta/convert_deta_resnet_to_pytorch.py
+src/transformers/models/deta/convert_deta_swin_to_pytorch.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/dialogpt/convert_dialogpt_original_pytorch_checkpoint_to_pytorch.py
+src/transformers/models/dinov2/configuration_dinov2.py
+src/transformers/models/dinov2/convert_dinov2_to_hf.py
+src/transformers/models/dinov2/modeling_dinov2.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/dit/convert_dit_unilm_to_pytorch.py
+src/transformers/models/donut/configuration_donut_swin.py
+src/transformers/models/donut/convert_donut_to_pytorch.py
+src/transformers/models/donut/modeling_donut_swin.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/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/efficientformer/configuration_efficientformer.py
+src/transformers/models/efficientformer/convert_efficientformer_original_pytorch_checkpoint_to_pytorch.py
+src/transformers/models/efficientformer/modeling_efficientformer.py
+src/transformers/models/efficientnet/configuration_efficientnet.py
+src/transformers/models/efficientnet/convert_efficientnet_to_pytorch.py
+src/transformers/models/efficientnet/modeling_efficientnet.py
+src/transformers/models/electra/convert_electra_original_tf_checkpoint_to_pytorch.py
+src/transformers/models/electra/modeling_flax_electra.py
+src/transformers/models/encodec/configuration_encodec.py
+src/transformers/models/encodec/convert_encodec_checkpoint_to_pytorch.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/modeling_ernie.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/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/falcon/configuration_falcon.py
+src/transformers/models/falcon/modeling_falcon.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/flava/convert_dalle_to_flava_codebook.py
+src/transformers/models/flava/convert_flava_original_pytorch_to_hf.py
+src/transformers/models/flava/modeling_flava.py
+src/transformers/models/fnet/convert_fnet_original_flax_checkpoint_to_pytorch.py
+src/transformers/models/fnet/modeling_fnet.py
+src/transformers/models/focalnet/configuration_focalnet.py
+src/transformers/models/focalnet/convert_focalnet_to_hf_format.py
+src/transformers/models/focalnet/modeling_focalnet.py
+src/transformers/models/fsmt/convert_fsmt_original_pytorch_checkpoint_to_pytorch.py
+src/transformers/models/fsmt/modeling_fsmt.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/fuyu/convert_fuyu_model_weights_to_hf.py
+src/transformers/models/git/configuration_git.py
+src/transformers/models/git/convert_git_to_pytorch.py
+src/transformers/models/glpn/configuration_glpn.py
+src/transformers/models/glpn/convert_glpn_to_pytorch.py
+src/transformers/models/gpt2/CONVERSION.md
+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_tf_gpt2.py
+src/transformers/models/gpt_bigcode/configuration_gpt_bigcode.py
+src/transformers/models/gpt_bigcode/modeling_gpt_bigcode.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/modeling_gpt_neox.py
+src/transformers/models/gpt_neox_japanese/modeling_gpt_neox_japanese.py
+src/transformers/models/gpt_sw3/convert_megatron_to_pytorch.py
+src/transformers/models/gptj/configuration_gptj.py
+src/transformers/models/gptj/modeling_flax_gptj.py
+src/transformers/models/gptj/modeling_tf_gptj.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/graphormer/collating_graphormer.py
+src/transformers/models/graphormer/configuration_graphormer.py
+src/transformers/models/graphormer/modeling_graphormer.py
+src/transformers/models/groupvit/configuration_groupvit.py
+src/transformers/models/groupvit/convert_groupvit_nvlab_to_hf.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_tf_hubert.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/idefics/configuration_idefics.py
+src/transformers/models/idefics/image_processing_idefics.py
+src/transformers/models/idefics/modeling_idefics.py
+src/transformers/models/idefics/perceiver.py
+src/transformers/models/idefics/processing_idefics.py
+src/transformers/models/idefics/vision.py
+src/transformers/models/imagegpt/convert_imagegpt_original_tf2_to_pytorch.py
+src/transformers/models/informer/configuration_informer.py
+src/transformers/models/informer/modeling_informer.py
+src/transformers/models/instructblip/configuration_instructblip.py
+src/transformers/models/instructblip/convert_instructblip_original_to_pytorch.py
+src/transformers/models/instructblip/modeling_instructblip.py
+src/transformers/models/instructblip/processing_instructblip.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/kosmos2/convert_kosmos2_original_pytorch_checkpoint_to_pytorch.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/levit/convert_levit_timm_to_pytorch.py
+src/transformers/models/levit/modeling_levit.py
+src/transformers/models/lilt/configuration_lilt.py
+src/transformers/models/llama/configuration_llama.py
+src/transformers/models/llama/convert_llama_weights_to_hf.py
+src/transformers/models/llama/modeling_llama.py
+src/transformers/models/longformer/configuration_longformer.py
+src/transformers/models/longformer/convert_longformer_original_pytorch_lightning_to_pytorch.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/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/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/m2m_100/convert_m2m100_original_checkpoint_to_pytorch.py
+src/transformers/models/m2m_100/modeling_m2m_100.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_tf_marian.py
+src/transformers/models/markuplm/configuration_markuplm.py
+src/transformers/models/markuplm/feature_extraction_markuplm.py
+src/transformers/models/mask2former/convert_mask2former_original_pytorch_checkpoint_to_pytorch.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/modeling_maskformer_swin.py
+src/transformers/models/mbart/convert_mbart_original_checkpoint_to_pytorch.py
+src/transformers/models/mbart/modeling_flax_mbart.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/convert_megatron_bert_checkpoint.py
+src/transformers/models/megatron_bert/modeling_megatron_bert.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/configuration_mgp_str.py
+src/transformers/models/mgp_str/modeling_mgp_str.py
+src/transformers/models/mistral/configuration_mistral.py
+src/transformers/models/mistral/modeling_mistral.py
+src/transformers/models/mluke/convert_mluke_original_pytorch_checkpoint_to_pytorch.py
+src/transformers/models/mobilebert/convert_mobilebert_original_tf_checkpoint_to_pytorch.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_v2/configuration_mobilenet_v2.py
+src/transformers/models/mobilenet_v2/convert_original_tf_checkpoint_to_pytorch.py
+src/transformers/models/mobilevit/configuration_mobilevit.py
+src/transformers/models/mobilevit/convert_mlcvnets_to_pytorch.py
+src/transformers/models/mobilevitv2/convert_mlcvnets_to_pytorch.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/mpt/configuration_mpt.py
+src/transformers/models/mpt/modeling_mpt.py
+src/transformers/models/mra/configuration_mra.py
+src/transformers/models/mra/convert_mra_pytorch_to_pytorch.py
+src/transformers/models/mra/modeling_mra.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/musicgen/convert_musicgen_transformers.py
+src/transformers/models/mvp/modeling_mvp.py
+src/transformers/models/nezha/modeling_nezha.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/nougat/convert_nougat_to_hf.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/convert_to_hf_oneformer.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/opt/convert_opt_original_pytorch_checkpoint_to_pytorch.py
+src/transformers/models/opt/modeling_flax_opt.py
+src/transformers/models/owlvit/configuration_owlvit.py
+src/transformers/models/owlvit/convert_owlvit_original_flax_to_hf.py
+src/transformers/models/pegasus/convert_pegasus_tf_to_pytorch.py
+src/transformers/models/pegasus/modeling_flax_pegasus.py
+src/transformers/models/pegasus/modeling_tf_pegasus.py
+src/transformers/models/pegasus_x/modeling_pegasus_x.py
+src/transformers/models/perceiver/configuration_perceiver.py
+src/transformers/models/perceiver/convert_perceiver_haiku_to_pytorch.py
+src/transformers/models/persimmon/convert_persimmon_weights_to_hf.py
+src/transformers/models/persimmon/modeling_persimmon.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/processing_pix2struct.py
+src/transformers/models/plbart/convert_plbart_original_checkpoint_to_torch.py
+src/transformers/models/poolformer/convert_poolformer_original_to_pytorch.py
+src/transformers/models/pop2piano/convert_pop2piano_weights_to_hf.py
+src/transformers/models/pop2piano/feature_extraction_pop2piano.py
+src/transformers/models/pop2piano/processing_pop2piano.py
+src/transformers/models/pop2piano/tokenization_pop2piano.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/pvt/configuration_pvt.py
+src/transformers/models/pvt/convert_pvt_to_pytorch.py
+src/transformers/models/pvt/image_processing_pvt.py
+src/transformers/models/pvt/modeling_pvt.py
+src/transformers/models/qdqbert/configuration_qdqbert.py
+src/transformers/models/qdqbert/modeling_qdqbert.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/realm/modeling_realm.py
+src/transformers/models/realm/retrieval_realm.py
+src/transformers/models/reformer/convert_reformer_trax_checkpoint_to_pytorch.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_flax_regnet.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/resnet/convert_resnet_to_pytorch.py
+src/transformers/models/resnet/modeling_flax_resnet.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_prelayernorm/convert_roberta_prelayernorm_original_pytorch_checkpoint_to_pytorch.py
+src/transformers/models/roberta_prelayernorm/modeling_flax_roberta_prelayernorm.py
+src/transformers/models/roc_bert/configuration_roc_bert.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/rwkv/configuration_rwkv.py
+src/transformers/models/rwkv/convert_rwkv_checkpoint_to_hf.py
+src/transformers/models/rwkv/modeling_rwkv.py
+src/transformers/models/sam/configuration_sam.py
+src/transformers/models/sam/convert_sam_original_to_hf_format.py
+src/transformers/models/sam/image_processing_sam.py
+src/transformers/models/sam/modeling_sam.py
+src/transformers/models/sam/modeling_tf_sam.py
+src/transformers/models/sam/processing_sam.py
+src/transformers/models/seamless_m4t/convert_fairseq2_to_hf.py
+src/transformers/models/segformer/configuration_segformer.py
+src/transformers/models/segformer/convert_segformer_original_to_pytorch.py
+src/transformers/models/sew/convert_sew_original_pytorch_checkpoint_to_pytorch.py
+src/transformers/models/sew_d/convert_sew_d_original_pytorch_checkpoint_to_pytorch.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_to_text/convert_s2t_fairseq_to_tfms.py
+src/transformers/models/speech_to_text/modeling_tf_speech_to_text.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/number_normalizer.py
+src/transformers/models/splinter/configuration_splinter.py
+src/transformers/models/splinter/modeling_splinter.py
+src/transformers/models/squeezebert/modeling_squeezebert.py
+src/transformers/models/swiftformer/configuration_swiftformer.py
+src/transformers/models/swiftformer/convert_swiftformer_original_to_hf.py
+src/transformers/models/swiftformer/modeling_swiftformer.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_tf_swin.py
+src/transformers/models/swin2sr/configuration_swin2sr.py
+src/transformers/models/swin2sr/convert_swin2sr_original_to_pytorch.py
+src/transformers/models/swinv2/convert_swinv2_timm_to_pytorch.py
+src/transformers/models/swinv2/modeling_swinv2.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/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/table_transformer/configuration_table_transformer.py
+src/transformers/models/table_transformer/convert_table_transformer_original_pytorch_checkpoint_to_pytorch.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/timesformer/convert_timesformer_to_pytorch.py
+src/transformers/models/timm_backbone/configuration_timm_backbone.py
+src/transformers/models/timm_backbone/modeling_timm_backbone.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/trocr/convert_trocr_unilm_to_pytorch.py
+src/transformers/models/tvlt/configuration_tvlt.py
+src/transformers/models/tvlt/modeling_tvlt.py
+src/transformers/models/umt5/configuration_umt5.py
+src/transformers/models/umt5/convert_umt5_checkpoint_to_pytorch.py
+src/transformers/models/umt5/modeling_umt5.py
+src/transformers/models/unispeech/convert_unispeech_original_pytorch_checkpoint_to_pytorch.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/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/videomae/configuration_videomae.py
+src/transformers/models/videomae/convert_videomae_to_pytorch.py
+src/transformers/models/vilt/configuration_vilt.py
+src/transformers/models/vilt/convert_vilt_original_to_pytorch.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_text_dual_encoder/modeling_flax_vision_text_dual_encoder.py
+src/transformers/models/vision_text_dual_encoder/modeling_vision_text_dual_encoder.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/convert_dino_to_pytorch.py
+src/transformers/models/vit/convert_vit_timm_to_pytorch.py
+src/transformers/models/vit/modeling_flax_vit.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/modeling_vit_hybrid.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_msn/configuration_vit_msn.py
+src/transformers/models/vit_msn/convert_msn_to_pytorch.py
+src/transformers/models/vivit/configuration_vivit.py
+src/transformers/models/vivit/convert_vivit_flax_to_pytorch.py
+src/transformers/models/vivit/image_processing_vivit.py
+src/transformers/models/vivit/modeling_vivit.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/modeling_flax_wav2vec2.py
+src/transformers/models/wav2vec2/modeling_tf_wav2vec2.py
+src/transformers/models/wav2vec2_conformer/convert_wav2vec2_conformer_original_pytorch_checkpoint_to_pytorch.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/whisper/convert_openai_to_hf.py
+src/transformers/models/whisper/english_normalizer.py
+src/transformers/models/whisper/modeling_flax_whisper.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/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/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_prophetnet/configuration_xlm_prophetnet.py
+src/transformers/models/xlm_prophetnet/modeling_xlm_prophetnet.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_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/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/xmod/convert_xmod_original_pytorch_checkpoint_to_pytorch.py
+src/transformers/models/yolos/convert_yolos_to_pytorch.py
+src/transformers/models/yoso/convert_yoso_pytorch_to_pytorch.py
+src/transformers/models/yoso/modeling_yoso.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/optimization.py
+src/transformers/optimization_tf.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/mask_generation.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/text_classification.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/processing_utils.py
+src/transformers/pytorch_utils.py
+src/transformers/sagemaker/trainer_sm.py
+src/transformers/sagemaker/training_args_sm.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/tools/agent_types.py
+src/transformers/tools/agents.py
+src/transformers/tools/base.py
+src/transformers/tools/document_question_answering.py
+src/transformers/tools/evaluate_agent.py
+src/transformers/tools/image_captioning.py
+src/transformers/tools/image_question_answering.py
+src/transformers/tools/image_segmentation.py
+src/transformers/tools/prompts.py
+src/transformers/tools/python_interpreter.py
+src/transformers/tools/speech_to_text.py
+src/transformers/tools/text_classification.py
+src/transformers/tools/text_question_answering.py
+src/transformers/tools/text_summarization.py
+src/transformers/tools/text_to_speech.py
+src/transformers/tools/translation.py
+src/transformers/trainer.py
+src/transformers/trainer_callback.py
+src/transformers/trainer_pt_utils.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/utils/backbone_utils.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_essentia_and_librosa_and_pretty_midi_and_scipy_and_torch_objects.py
+src/transformers/utils/dummy_flax_objects.py
+src/transformers/utils/dummy_keras_nlp_objects.py
+src/transformers/utils/dummy_music_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/peft_utils.py
+src/transformers/utils/quantization_config.py
+src/transformers/utils/sentencepiece_model_pb2.py
+src/transformers/utils/sentencepiece_model_pb2_new.py
+src/transformers/utils/versions.py

utils/tests_fetcher.py

@@ -387,7 +387,7 @@ def get_all_doctest_files() -> List[str]:
 
     # These are files not doctested yet.
     with open("utils/not_doctested.txt") as fp:
-        not_doctested = set(fp.read().strip().split("\n"))
+        not_doctested = {x.split(" ")[0] for x in fp.read().strip().split("\n")}
 
     # So far we don't have 100% coverage for doctest. This line will be removed once we achieve 100%.
     test_files_to_run = [x for x in test_files_to_run if x not in not_doctested]
@@ -415,7 +415,9 @@ def get_new_doctest_files(repo, base_commit, branching_commit) -> List[str]:
         with open(folder / "utils/not_doctested.txt", "r", encoding="utf-8") as f:
             new_content = f.read()
         # Compute the removed lines and return them
-        removed_content = set(old_content.split("\n")) - set(new_content.split("\n"))
+        removed_content = {x.split(" ")[0] for x in old_content.split("\n")} - {
+            x.split(" ")[0] for x in new_content.split("\n")
+        }
         return sorted(removed_content)
     return []