run make style

huggingface · May 18, 2023 · 4b7f114 · 4b7f114
1 parent 6b1e3b1
commit 4b7f114
Show file tree

Hide file tree

Showing 223 changed files with 541 additions and 2 deletions.
diff --git a/docs/source/en/contributing.md b/docs/source/en/contributing.md
diff --git a/docs/source/en/notebooks.md b/docs/source/en/notebooks.md
diff --git a/docs/source/fr/_toctree.yml b/docs/source/fr/_toctree.yml
diff --git a/examples/flax/language-modeling/run_clm_flax.py b/examples/flax/language-modeling/run_clm_flax.py
diff --git a/examples/flax/language-modeling/run_mlm_flax.py b/examples/flax/language-modeling/run_mlm_flax.py
diff --git a/examples/flax/language-modeling/run_t5_mlm_flax.py b/examples/flax/language-modeling/run_t5_mlm_flax.py
diff --git a/examples/flax/language-modeling/t5_tokenizer_model.py b/examples/flax/language-modeling/t5_tokenizer_model.py
diff --git a/examples/flax/text-classification/run_flax_glue.py b/examples/flax/text-classification/run_flax_glue.py
diff --git a/examples/legacy/pytorch-lightning/run_glue.sh b/examples/legacy/pytorch-lightning/run_glue.sh
diff --git a/examples/legacy/pytorch-lightning/run_ner.sh b/examples/legacy/pytorch-lightning/run_ner.sh
diff --git a/examples/legacy/pytorch-lightning/run_pos.sh b/examples/legacy/pytorch-lightning/run_pos.sh
diff --git a/examples/legacy/run_camembert.py b/examples/legacy/run_camembert.py
diff --git a/examples/legacy/run_chinese_ref.py b/examples/legacy/run_chinese_ref.py
diff --git a/examples/legacy/run_language_modeling.py b/examples/legacy/run_language_modeling.py
diff --git a/examples/legacy/run_openai_gpt.py b/examples/legacy/run_openai_gpt.py
diff --git a/examples/legacy/run_swag.py b/examples/legacy/run_swag.py
diff --git a/examples/legacy/run_transfo_xl.py b/examples/legacy/run_transfo_xl.py
diff --git a/examples/legacy/seq2seq/convert_model_to_fp16.py b/examples/legacy/seq2seq/convert_model_to_fp16.py
diff --git a/examples/legacy/seq2seq/download_wmt.py b/examples/legacy/seq2seq/download_wmt.py
diff --git a/examples/legacy/seq2seq/finetune_trainer.py b/examples/legacy/seq2seq/finetune_trainer.py
diff --git a/examples/legacy/seq2seq/minify_dataset.py b/examples/legacy/seq2seq/minify_dataset.py
diff --git a/examples/legacy/seq2seq/pack_dataset.py b/examples/legacy/seq2seq/pack_dataset.py
diff --git a/examples/legacy/seq2seq/run_distributed_eval.py b/examples/legacy/seq2seq/run_distributed_eval.py
diff --git a/examples/legacy/seq2seq/run_eval.py b/examples/legacy/seq2seq/run_eval.py
diff --git a/examples/legacy/seq2seq/run_eval_search.py b/examples/legacy/seq2seq/run_eval_search.py
diff --git a/examples/legacy/seq2seq/save_len_file.py b/examples/legacy/seq2seq/save_len_file.py
diff --git a/examples/legacy/seq2seq/save_randomly_initialized_model.py b/examples/legacy/seq2seq/save_randomly_initialized_model.py
diff --git a/examples/legacy/seq2seq/test_data/fsmt/build-eval-data.py b/examples/legacy/seq2seq/test_data/fsmt/build-eval-data.py
diff --git a/examples/legacy/text-classification/run_tf_text_classification.py b/examples/legacy/text-classification/run_tf_text_classification.py
diff --git a/examples/legacy/token-classification/run.sh b/examples/legacy/token-classification/run.sh
diff --git a/examples/legacy/token-classification/run_chunk.sh b/examples/legacy/token-classification/run_chunk.sh
diff --git a/examples/legacy/token-classification/run_pos.sh b/examples/legacy/token-classification/run_pos.sh
diff --git a/examples/legacy/token-classification/run_tf_ner.py b/examples/legacy/token-classification/run_tf_ner.py
diff --git a/examples/pytorch/benchmarking/run_benchmark.py b/examples/pytorch/benchmarking/run_benchmark.py
diff --git a/examples/pytorch/language-modeling/run_clm.py b/examples/pytorch/language-modeling/run_clm.py
diff --git a/examples/pytorch/language-modeling/run_clm_no_trainer.py b/examples/pytorch/language-modeling/run_clm_no_trainer.py
diff --git a/examples/pytorch/language-modeling/run_mlm.py b/examples/pytorch/language-modeling/run_mlm.py
diff --git a/examples/pytorch/language-modeling/run_mlm_no_trainer.py b/examples/pytorch/language-modeling/run_mlm_no_trainer.py
diff --git a/examples/pytorch/language-modeling/run_plm.py b/examples/pytorch/language-modeling/run_plm.py
diff --git a/examples/pytorch/multiple-choice/run_no_trainer.sh b/examples/pytorch/multiple-choice/run_no_trainer.sh
diff --git a/examples/pytorch/multiple-choice/run_swag.py b/examples/pytorch/multiple-choice/run_swag.py
diff --git a/examples/pytorch/multiple-choice/run_swag_no_trainer.py b/examples/pytorch/multiple-choice/run_swag_no_trainer.py
diff --git a/examples/pytorch/question-answering/run_qa.py b/examples/pytorch/question-answering/run_qa.py
diff --git a/examples/pytorch/question-answering/run_qa_beam_search.py b/examples/pytorch/question-answering/run_qa_beam_search.py
diff --git a/examples/pytorch/question-answering/run_qa_no_trainer.py b/examples/pytorch/question-answering/run_qa_no_trainer.py
diff --git a/examples/pytorch/speech-pretraining/run_wav2vec2_pretraining_no_trainer.py b/examples/pytorch/speech-pretraining/run_wav2vec2_pretraining_no_trainer.py
diff --git a/examples/pytorch/speech-recognition/run_speech_recognition_ctc.py b/examples/pytorch/speech-recognition/run_speech_recognition_ctc.py
diff --git a/examples/pytorch/speech-recognition/run_speech_recognition_seq2seq.py b/examples/pytorch/speech-recognition/run_speech_recognition_seq2seq.py
diff --git a/examples/pytorch/summarization/run_summarization.py b/examples/pytorch/summarization/run_summarization.py
diff --git a/examples/pytorch/text-classification/run_glue.py b/examples/pytorch/text-classification/run_glue.py
diff --git a/examples/pytorch/text-classification/run_xnli.py b/examples/pytorch/text-classification/run_xnli.py
diff --git a/examples/pytorch/text-generation/run_generation.py b/examples/pytorch/text-generation/run_generation.py
diff --git a/examples/pytorch/text-generation/run_generation_contrastive_search.py b/examples/pytorch/text-generation/run_generation_contrastive_search.py
diff --git a/examples/pytorch/token-classification/run.sh b/examples/pytorch/token-classification/run.sh
diff --git a/examples/pytorch/token-classification/run_ner.py b/examples/pytorch/token-classification/run_ner.py
diff --git a/examples/pytorch/token-classification/run_ner_no_trainer.py b/examples/pytorch/token-classification/run_ner_no_trainer.py
diff --git a/examples/pytorch/token-classification/run_no_trainer.sh b/examples/pytorch/token-classification/run_no_trainer.sh
diff --git a/examples/pytorch/translation/run_translation.py b/examples/pytorch/translation/run_translation.py
diff --git a/examples/research_projects/bert-loses-patience/README.md b/examples/research_projects/bert-loses-patience/README.md
diff --git a/examples/research_projects/bert-loses-patience/run_glue_with_pabee.py b/examples/research_projects/bert-loses-patience/run_glue_with_pabee.py
diff --git a/examples/research_projects/deebert/entropy_eval.sh b/examples/research_projects/deebert/entropy_eval.sh
diff --git a/examples/research_projects/deebert/eval_deebert.sh b/examples/research_projects/deebert/eval_deebert.sh
diff --git a/examples/research_projects/deebert/train_deebert.sh b/examples/research_projects/deebert/train_deebert.sh
diff --git a/examples/research_projects/jax-projects/dataset-streaming/run_mlm_flax_stream.py b/examples/research_projects/jax-projects/dataset-streaming/run_mlm_flax_stream.py
diff --git a/examples/research_projects/jax-projects/wav2vec2/run_wav2vec2_pretrain_flax.py b/examples/research_projects/jax-projects/wav2vec2/run_wav2vec2_pretrain_flax.py
diff --git a/examples/research_projects/performer/full_script.sh b/examples/research_projects/performer/full_script.sh
diff --git a/examples/research_projects/performer/sanity_script.sh b/examples/research_projects/performer/sanity_script.sh
diff --git a/examples/research_projects/quantization-qdqbert/evaluate-hf-trt-qa.py b/examples/research_projects/quantization-qdqbert/evaluate-hf-trt-qa.py
diff --git a/examples/research_projects/quantization-qdqbert/quant_trainer.py b/examples/research_projects/quantization-qdqbert/quant_trainer.py
diff --git a/examples/research_projects/quantization-qdqbert/run_quant_qa.py b/examples/research_projects/quantization-qdqbert/run_quant_qa.py
diff --git a/examples/research_projects/rag-end2end-retriever/finetune_rag_ray_end2end.sh b/examples/research_projects/rag-end2end-retriever/finetune_rag_ray_end2end.sh
diff --git a/examples/research_projects/rag-end2end-retriever/test_run/test_finetune.sh b/examples/research_projects/rag-end2end-retriever/test_run/test_finetune.sh
diff --git a/examples/research_projects/rag-end2end-retriever/test_run/test_rag_new_features.sh b/examples/research_projects/rag-end2end-retriever/test_run/test_rag_new_features.sh
diff --git a/examples/research_projects/rag/finetune_rag.sh b/examples/research_projects/rag/finetune_rag.sh
diff --git a/examples/research_projects/rag/finetune_rag_ray.sh b/examples/research_projects/rag/finetune_rag_ray.sh
diff --git a/examples/research_projects/robust-speech-event/eval.py b/examples/research_projects/robust-speech-event/eval.py
diff --git a/examples/research_projects/robust-speech-event/run_speech_recognition_ctc_bnb.py b/examples/research_projects/robust-speech-event/run_speech_recognition_ctc_bnb.py
diff --git a/examples/research_projects/self-training-text-classification/run.sh b/examples/research_projects/self-training-text-classification/run.sh
diff --git a/examples/research_projects/seq2seq-distillation/convert_pl_checkpoint_to_hf.py b/examples/research_projects/seq2seq-distillation/convert_pl_checkpoint_to_hf.py
diff --git a/examples/research_projects/seq2seq-distillation/distil_marian_enro_teacher.sh b/examples/research_projects/seq2seq-distillation/distil_marian_enro_teacher.sh
diff --git a/examples/research_projects/seq2seq-distillation/distil_marian_no_teacher.sh b/examples/research_projects/seq2seq-distillation/distil_marian_no_teacher.sh
diff --git a/examples/research_projects/seq2seq-distillation/distillation.py b/examples/research_projects/seq2seq-distillation/distillation.py
diff --git a/examples/research_projects/seq2seq-distillation/dynamic_bs_example.sh b/examples/research_projects/seq2seq-distillation/dynamic_bs_example.sh
diff --git a/examples/research_projects/seq2seq-distillation/finetune.py b/examples/research_projects/seq2seq-distillation/finetune.py
diff --git a/examples/research_projects/seq2seq-distillation/finetune.sh b/examples/research_projects/seq2seq-distillation/finetune.sh
diff --git a/examples/research_projects/seq2seq-distillation/finetune_bart_tiny.sh b/examples/research_projects/seq2seq-distillation/finetune_bart_tiny.sh
diff --git a/examples/research_projects/seq2seq-distillation/finetune_pegasus_xsum.sh b/examples/research_projects/seq2seq-distillation/finetune_pegasus_xsum.sh
diff --git a/examples/research_projects/seq2seq-distillation/finetune_t5.sh b/examples/research_projects/seq2seq-distillation/finetune_t5.sh
diff --git a/examples/research_projects/seq2seq-distillation/run_eval.py b/examples/research_projects/seq2seq-distillation/run_eval.py
diff --git a/examples/research_projects/seq2seq-distillation/train_distilbart_cnn.sh b/examples/research_projects/seq2seq-distillation/train_distilbart_cnn.sh
diff --git a/examples/research_projects/seq2seq-distillation/train_distilbart_xsum.sh b/examples/research_projects/seq2seq-distillation/train_distilbart_xsum.sh
diff --git a/examples/research_projects/seq2seq-distillation/train_mbart_cc25_enro.sh b/examples/research_projects/seq2seq-distillation/train_mbart_cc25_enro.sh
diff --git a/examples/research_projects/wav2vec2/finetune_base_100.sh b/examples/research_projects/wav2vec2/finetune_base_100.sh
diff --git a/examples/research_projects/wav2vec2/finetune_base_timit_asr.sh b/examples/research_projects/wav2vec2/finetune_base_timit_asr.sh
diff --git a/examples/research_projects/wav2vec2/finetune_large_lv60_100.sh b/examples/research_projects/wav2vec2/finetune_large_lv60_100.sh
diff --git a/examples/research_projects/wav2vec2/finetune_large_lv60_timit_asr.sh b/examples/research_projects/wav2vec2/finetune_large_lv60_timit_asr.sh
diff --git a/examples/research_projects/wav2vec2/finetune_large_xlsr_53_arabic_speech_corpus.sh b/examples/research_projects/wav2vec2/finetune_large_xlsr_53_arabic_speech_corpus.sh
diff --git a/examples/research_projects/wav2vec2/run_asr.py b/examples/research_projects/wav2vec2/run_asr.py
diff --git a/examples/research_projects/wav2vec2/run_pretrain.py b/examples/research_projects/wav2vec2/run_pretrain.py
diff --git a/examples/tensorflow/benchmarking/run_benchmark_tf.py b/examples/tensorflow/benchmarking/run_benchmark_tf.py
diff --git a/examples/tensorflow/language-modeling/run_clm.py b/examples/tensorflow/language-modeling/run_clm.py
diff --git a/examples/tensorflow/language-modeling/run_mlm.py b/examples/tensorflow/language-modeling/run_mlm.py
diff --git a/examples/tensorflow/question-answering/run_qa.py b/examples/tensorflow/question-answering/run_qa.py
diff --git a/scripts/benchmark/trainer-benchmark.py b/scripts/benchmark/trainer-benchmark.py
diff --git a/scripts/distributed/torch-distributed-gpu-test.py b/scripts/distributed/torch-distributed-gpu-test.py
diff --git a/scripts/fsmt/convert-allenai-wmt16.sh b/scripts/fsmt/convert-allenai-wmt16.sh
diff --git a/scripts/fsmt/convert-allenai-wmt19.sh b/scripts/fsmt/convert-allenai-wmt19.sh
diff --git a/scripts/fsmt/convert-facebook-wmt19.sh b/scripts/fsmt/convert-facebook-wmt19.sh
diff --git a/scripts/fsmt/eval-allenai-wmt16.sh b/scripts/fsmt/eval-allenai-wmt16.sh
diff --git a/scripts/fsmt/eval-allenai-wmt19.sh b/scripts/fsmt/eval-allenai-wmt19.sh
diff --git a/scripts/fsmt/eval-facebook-wmt19.sh b/scripts/fsmt/eval-facebook-wmt19.sh
diff --git a/scripts/fsmt/fsmt-make-super-tiny-model.py b/scripts/fsmt/fsmt-make-super-tiny-model.py
diff --git a/scripts/fsmt/fsmt-make-tiny-model.py b/scripts/fsmt/fsmt-make-tiny-model.py
diff --git a/scripts/fsmt/gen-card-allenai-wmt16.py b/scripts/fsmt/gen-card-allenai-wmt16.py
diff --git a/scripts/fsmt/gen-card-allenai-wmt19.py b/scripts/fsmt/gen-card-allenai-wmt19.py
diff --git a/scripts/fsmt/gen-card-facebook-wmt19.py b/scripts/fsmt/gen-card-facebook-wmt19.py
diff --git a/scripts/fsmt/tests-to-run.sh b/scripts/fsmt/tests-to-run.sh
diff --git a/scripts/pegasus/build_test_sample_spm_no_bos.py b/scripts/pegasus/build_test_sample_spm_no_bos.py
diff --git a/scripts/tatoeba/upload_models.sh b/scripts/tatoeba/upload_models.sh
diff --git a/src/transformers/configuration_utils.py b/src/transformers/configuration_utils.py
diff --git a/src/transformers/convert_pytorch_checkpoint_to_tf2.py b/src/transformers/convert_pytorch_checkpoint_to_tf2.py
diff --git a/src/transformers/convert_slow_tokenizers_checkpoints_to_fast.py b/src/transformers/convert_slow_tokenizers_checkpoints_to_fast.py
diff --git a/src/transformers/convert_tf_hub_seq_to_seq_bert_to_pytorch.py b/src/transformers/convert_tf_hub_seq_to_seq_bert_to_pytorch.py
diff --git a/src/transformers/modeling_outputs.py b/src/transformers/modeling_outputs.py
diff --git a/src/transformers/models/albert/modeling_albert.py b/src/transformers/models/albert/modeling_albert.py
diff --git a/src/transformers/models/altclip/__init__.py b/src/transformers/models/altclip/__init__.py
diff --git a/src/transformers/models/altclip/configuration_altclip.py b/src/transformers/models/altclip/configuration_altclip.py
diff --git a/src/transformers/models/altclip/modeling_altclip.py b/src/transformers/models/altclip/modeling_altclip.py
diff --git a/src/transformers/models/auto/configuration_auto.py b/src/transformers/models/auto/configuration_auto.py
diff --git a/src/transformers/models/auto/modeling_auto.py b/src/transformers/models/auto/modeling_auto.py
diff --git a/src/transformers/models/bart/modeling_bart.py b/src/transformers/models/bart/modeling_bart.py
diff --git a/src/transformers/models/beit/modeling_beit.py b/src/transformers/models/beit/modeling_beit.py
diff --git a/src/transformers/models/bert/convert_bert_original_tf_checkpoint_to_pytorch.py b/src/transformers/models/bert/convert_bert_original_tf_checkpoint_to_pytorch.py
diff --git a/src/transformers/models/bert/modeling_bert.py b/src/transformers/models/bert/modeling_bert.py
diff --git a/src/transformers/models/bert_generation/modeling_bert_generation.py b/src/transformers/models/bert_generation/modeling_bert_generation.py
diff --git a/src/transformers/models/big_bird/modeling_big_bird.py b/src/transformers/models/big_bird/modeling_big_bird.py
diff --git a/src/transformers/models/bigbird_pegasus/modeling_bigbird_pegasus.py b/src/transformers/models/bigbird_pegasus/modeling_bigbird_pegasus.py
diff --git a/src/transformers/models/biogpt/convert_biogpt_original_pytorch_checkpoint_to_pytorch.py b/src/transformers/models/biogpt/convert_biogpt_original_pytorch_checkpoint_to_pytorch.py
diff --git a/src/transformers/models/biogpt/modeling_biogpt.py b/src/transformers/models/biogpt/modeling_biogpt.py
diff --git a/src/transformers/models/blenderbot/modeling_blenderbot.py b/src/transformers/models/blenderbot/modeling_blenderbot.py
diff --git a/src/transformers/models/blenderbot_small/modeling_blenderbot_small.py b/src/transformers/models/blenderbot_small/modeling_blenderbot_small.py
diff --git a/src/transformers/models/byt5/convert_byt5_original_tf_checkpoint_to_pytorch.py b/src/transformers/models/byt5/convert_byt5_original_tf_checkpoint_to_pytorch.py
diff --git a/src/transformers/models/convbert/modeling_convbert.py b/src/transformers/models/convbert/modeling_convbert.py
diff --git a/src/transformers/models/convnext/modeling_convnext.py b/src/transformers/models/convnext/modeling_convnext.py
diff --git a/src/transformers/models/cpmant/modeling_cpmant.py b/src/transformers/models/cpmant/modeling_cpmant.py
diff --git a/...formers/models/data2vec/convert_data2vec_vision_original_pytorch_checkpoint_to_pytorch.py b/...formers/models/data2vec/convert_data2vec_vision_original_pytorch_checkpoint_to_pytorch.py
diff --git a/src/transformers/models/data2vec/modeling_data2vec_audio.py b/src/transformers/models/data2vec/modeling_data2vec_audio.py
diff --git a/src/transformers/models/decision_transformer/modeling_decision_transformer.py b/src/transformers/models/decision_transformer/modeling_decision_transformer.py
diff --git a/src/transformers/models/deformable_detr/modeling_deformable_detr.py b/src/transformers/models/deformable_detr/modeling_deformable_detr.py
diff --git a/src/transformers/models/distilbert/modeling_distilbert.py b/src/transformers/models/distilbert/modeling_distilbert.py
diff --git a/src/transformers/models/dpt/modeling_dpt.py b/src/transformers/models/dpt/modeling_dpt.py
diff --git a/src/transformers/models/ernie_m/modeling_ernie_m.py b/src/transformers/models/ernie_m/modeling_ernie_m.py
diff --git a/src/transformers/models/esm/modeling_esm.py b/src/transformers/models/esm/modeling_esm.py
diff --git a/src/transformers/models/fnet/modeling_fnet.py b/src/transformers/models/fnet/modeling_fnet.py
diff --git a/src/transformers/models/fsmt/convert_fsmt_original_pytorch_checkpoint_to_pytorch.py b/src/transformers/models/fsmt/convert_fsmt_original_pytorch_checkpoint_to_pytorch.py
diff --git a/src/transformers/models/funnel/convert_funnel_original_tf_checkpoint_to_pytorch.py b/src/transformers/models/funnel/convert_funnel_original_tf_checkpoint_to_pytorch.py
diff --git a/src/transformers/models/glpn/modeling_glpn.py b/src/transformers/models/glpn/modeling_glpn.py
diff --git a/src/transformers/models/gpt2/convert_gpt2_original_tf_checkpoint_to_pytorch.py b/src/transformers/models/gpt2/convert_gpt2_original_tf_checkpoint_to_pytorch.py
diff --git a/src/transformers/models/gpt_neo/modeling_gpt_neo.py b/src/transformers/models/gpt_neo/modeling_gpt_neo.py
diff --git a/src/transformers/models/gpt_neox/modeling_gpt_neox.py b/src/transformers/models/gpt_neox/modeling_gpt_neox.py
diff --git a/src/transformers/models/gpt_neox_japanese/modeling_gpt_neox_japanese.py b/src/transformers/models/gpt_neox_japanese/modeling_gpt_neox_japanese.py
diff --git a/src/transformers/models/graphormer/modeling_graphormer.py b/src/transformers/models/graphormer/modeling_graphormer.py
diff --git a/src/transformers/models/hubert/modeling_hubert.py b/src/transformers/models/hubert/modeling_hubert.py
diff --git a/src/transformers/models/imagegpt/modeling_imagegpt.py b/src/transformers/models/imagegpt/modeling_imagegpt.py
diff --git a/src/transformers/models/jukebox/modeling_jukebox.py b/src/transformers/models/jukebox/modeling_jukebox.py
diff --git a/src/transformers/models/layoutlmv2/modeling_layoutlmv2.py b/src/transformers/models/layoutlmv2/modeling_layoutlmv2.py
diff --git a/src/transformers/models/led/modeling_led.py b/src/transformers/models/led/modeling_led.py
diff --git a/src/transformers/models/llama/modeling_llama.py b/src/transformers/models/llama/modeling_llama.py
diff --git a/src/transformers/models/longformer/modeling_longformer.py b/src/transformers/models/longformer/modeling_longformer.py
diff --git a/src/transformers/models/lxmert/convert_lxmert_original_tf_checkpoint_to_pytorch.py b/src/transformers/models/lxmert/convert_lxmert_original_tf_checkpoint_to_pytorch.py
diff --git a/src/transformers/models/m2m_100/modeling_m2m_100.py b/src/transformers/models/m2m_100/modeling_m2m_100.py
diff --git a/src/transformers/models/marian/modeling_marian.py b/src/transformers/models/marian/modeling_marian.py
diff --git a/src/transformers/models/markuplm/modeling_markuplm.py b/src/transformers/models/markuplm/modeling_markuplm.py
diff --git a/src/transformers/models/mbart/modeling_mbart.py b/src/transformers/models/mbart/modeling_mbart.py
diff --git a/src/transformers/models/mctct/modeling_mctct.py b/src/transformers/models/mctct/modeling_mctct.py
diff --git a/src/transformers/models/megatron_bert/modeling_megatron_bert.py b/src/transformers/models/megatron_bert/modeling_megatron_bert.py
diff --git a/src/transformers/models/mobilenet_v1/modeling_mobilenet_v1.py b/src/transformers/models/mobilenet_v1/modeling_mobilenet_v1.py
diff --git a/src/transformers/models/mobilenet_v2/modeling_mobilenet_v2.py b/src/transformers/models/mobilenet_v2/modeling_mobilenet_v2.py
diff --git a/src/transformers/models/mobilevit/modeling_mobilevit.py b/src/transformers/models/mobilevit/modeling_mobilevit.py
diff --git a/src/transformers/models/nystromformer/modeling_nystromformer.py b/src/transformers/models/nystromformer/modeling_nystromformer.py
diff --git a/src/transformers/models/openai/convert_openai_original_tf_checkpoint_to_pytorch.py b/src/transformers/models/openai/convert_openai_original_tf_checkpoint_to_pytorch.py
diff --git a/src/transformers/models/pegasus/modeling_pegasus.py b/src/transformers/models/pegasus/modeling_pegasus.py
diff --git a/src/transformers/models/pegasus_x/modeling_pegasus_x.py b/src/transformers/models/pegasus_x/modeling_pegasus_x.py
diff --git a/src/transformers/models/perceiver/modeling_perceiver.py b/src/transformers/models/perceiver/modeling_perceiver.py
diff --git a/src/transformers/models/poolformer/modeling_poolformer.py b/src/transformers/models/poolformer/modeling_poolformer.py
diff --git a/src/transformers/models/qdqbert/modeling_qdqbert.py b/src/transformers/models/qdqbert/modeling_qdqbert.py
diff --git a/src/transformers/models/reformer/configuration_reformer.py b/src/transformers/models/reformer/configuration_reformer.py
diff --git a/src/transformers/models/reformer/convert_reformer_trax_checkpoint_to_pytorch.py b/src/transformers/models/reformer/convert_reformer_trax_checkpoint_to_pytorch.py
diff --git a/src/transformers/models/reformer/modeling_reformer.py b/src/transformers/models/reformer/modeling_reformer.py
diff --git a/src/transformers/models/rembert/convert_rembert_tf_checkpoint_to_pytorch.py b/src/transformers/models/rembert/convert_rembert_tf_checkpoint_to_pytorch.py
diff --git a/src/transformers/models/rembert/modeling_rembert.py b/src/transformers/models/rembert/modeling_rembert.py
diff --git a/src/transformers/models/roformer/convert_roformer_original_tf_checkpoint_to_pytorch.py b/src/transformers/models/roformer/convert_roformer_original_tf_checkpoint_to_pytorch.py
diff --git a/src/transformers/models/segformer/modeling_segformer.py b/src/transformers/models/segformer/modeling_segformer.py
diff --git a/src/transformers/models/speech_to_text/modeling_speech_to_text.py b/src/transformers/models/speech_to_text/modeling_speech_to_text.py
diff --git a/src/transformers/models/speech_to_text/modeling_tf_speech_to_text.py b/src/transformers/models/speech_to_text/modeling_tf_speech_to_text.py
diff --git a/src/transformers/models/speech_to_text_2/modeling_speech_to_text_2.py b/src/transformers/models/speech_to_text_2/modeling_speech_to_text_2.py
diff --git a/src/transformers/models/splinter/modeling_splinter.py b/src/transformers/models/splinter/modeling_splinter.py
diff --git a/src/transformers/models/t5/convert_t5_original_tf_checkpoint_to_pytorch.py b/src/transformers/models/t5/convert_t5_original_tf_checkpoint_to_pytorch.py
diff --git a/src/transformers/models/t5/convert_t5x_checkpoint_to_pytorch.py b/src/transformers/models/t5/convert_t5x_checkpoint_to_pytorch.py
diff --git a/src/transformers/models/t5/download_from_gcp.sh b/src/transformers/models/t5/download_from_gcp.sh
diff --git a/src/transformers/models/transfo_xl/convert_transfo_xl_original_tf_checkpoint_to_pytorch.py b/src/transformers/models/transfo_xl/convert_transfo_xl_original_tf_checkpoint_to_pytorch.py
diff --git a/src/transformers/models/unispeech/modeling_unispeech.py b/src/transformers/models/unispeech/modeling_unispeech.py
diff --git a/src/transformers/models/unispeech_sat/modeling_unispeech_sat.py b/src/transformers/models/unispeech_sat/modeling_unispeech_sat.py
diff --git a/src/transformers/models/vilt/modeling_vilt.py b/src/transformers/models/vilt/modeling_vilt.py
diff --git a/src/transformers/models/vision_text_dual_encoder/modeling_vision_text_dual_encoder.py b/src/transformers/models/vision_text_dual_encoder/modeling_vision_text_dual_encoder.py
diff --git a/src/transformers/models/visual_bert/modeling_visual_bert.py b/src/transformers/models/visual_bert/modeling_visual_bert.py
diff --git a/src/transformers/models/vit_mae/modeling_vit_mae.py b/src/transformers/models/vit_mae/modeling_vit_mae.py
diff --git a/src/transformers/models/wav2vec2/modeling_wav2vec2.py b/src/transformers/models/wav2vec2/modeling_wav2vec2.py
diff --git a/src/transformers/models/wavlm/modeling_wavlm.py b/src/transformers/models/wavlm/modeling_wavlm.py
diff --git a/src/transformers/models/xglm/modeling_xglm.py b/src/transformers/models/xglm/modeling_xglm.py
diff --git a/src/transformers/models/xlm/convert_xlm_original_pytorch_checkpoint_to_pytorch.py b/src/transformers/models/xlm/convert_xlm_original_pytorch_checkpoint_to_pytorch.py
diff --git a/src/transformers/models/xlm/modeling_xlm.py b/src/transformers/models/xlm/modeling_xlm.py
diff --git a/src/transformers/models/xlnet/convert_xlnet_original_tf_checkpoint_to_pytorch.py b/src/transformers/models/xlnet/convert_xlnet_original_tf_checkpoint_to_pytorch.py
diff --git a/src/transformers/models/xlnet/modeling_xlnet.py b/src/transformers/models/xlnet/modeling_xlnet.py
diff --git a/src/transformers/models/yolos/modeling_yolos.py b/src/transformers/models/yolos/modeling_yolos.py
diff --git a/src/transformers/pipelines/__init__.py b/src/transformers/pipelines/__init__.py
diff --git a/src/transformers/trainer.py b/src/transformers/trainer.py
diff --git a/src/transformers/utils/fx.py b/src/transformers/utils/fx.py
diff --git a/...w_example_script/{{cookiecutter.directory_name}}/run_{{cookiecutter.example_shortcut}}.py b/...w_example_script/{{cookiecutter.directory_name}}/run_{{cookiecutter.example_shortcut}}.py
diff --git a/...tter-template-{{cookiecutter.modelname}}/modeling_{{cookiecutter.lowercase_modelname}}.py b/...tter-template-{{cookiecutter.modelname}}/modeling_{{cookiecutter.lowercase_modelname}}.py
diff --git a/tests/models/altclip/__init__.py b/tests/models/altclip/__init__.py
diff --git a/tests/models/altclip/test_modeling_altclip.py b/tests/models/altclip/test_modeling_altclip.py
diff --git a/tests/test_modeling_common.py b/tests/test_modeling_common.py