├── LICENSE ├── README.md ├── src ├── Weights & Biases.pdf ├── bart_config_10_7.json ├── baseline │ ├── .ipynb_checkpoints │ │ └── test_generations-checkpoint.txt │ └── test_generations.txt ├── callbacks.py ├── composit │ ├── .ipynb_checkpoints │ │ ├── test_generations-checkpoint.txt │ │ └── test_results-checkpoint.txt │ ├── hparams.pkl │ ├── metrics.json │ ├── test_generations.txt │ └── test_results.txt ├── data │ ├── extract_actions.ipynb │ └── pre_process.ipynb ├── eval.ipynb ├── lightning_base.py ├── save_len_file.py ├── train.py ├── train_base.sh ├── train_multi_graph.sh └── utils.py └── transformers ├── .coveragerc ├── MANIFEST.in ├── Makefile ├── README.md ├── docker ├── transformers-cpu │ └── Dockerfile ├── transformers-gpu │ └── Dockerfile ├── transformers-pytorch-cpu │ └── Dockerfile ├── transformers-pytorch-gpu │ └── Dockerfile ├── transformers-pytorch-tpu │ ├── Dockerfile │ ├── bert-base-cased.jsonnet │ ├── dataset.yaml │ └── docker-entrypoint.sh ├── transformers-tensorflow-cpu │ └── Dockerfile └── transformers-tensorflow-gpu │ └── Dockerfile ├── docs ├── Makefile ├── README.md └── source │ ├── _static │ ├── css │ │ ├── Calibre-Light.ttf │ │ ├── Calibre-Medium.otf │ │ ├── Calibre-Regular.otf │ │ ├── Calibre-Thin.otf │ │ ├── code-snippets.css │ │ └── huggingface.css │ └── js │ │ ├── custom.js │ │ └── huggingface_logo.svg │ ├── benchmarks.rst │ ├── bertology.rst │ ├── conf.py │ ├── contributing.md │ ├── converting_tensorflow_models.rst │ ├── custom_datasets.rst │ ├── examples.md │ ├── favicon.ico │ ├── glossary.rst │ ├── imgs │ ├── local_attention_mask.png │ ├── ppl_chunked.gif │ ├── ppl_full.gif │ ├── ppl_sliding.gif │ ├── transformers_logo_name.png │ ├── warmup_constant_schedule.png │ ├── warmup_cosine_hard_restarts_schedule.png │ ├── warmup_cosine_schedule.png │ ├── warmup_cosine_warm_restarts_schedule.png │ └── warmup_linear_schedule.png │ ├── index.rst │ ├── installation.md │ ├── internal │ ├── modeling_utils.rst │ ├── pipelines_utils.rst │ └── tokenization_utils.rst │ ├── main_classes │ ├── configuration.rst │ ├── logging.rst │ ├── model.rst │ ├── optimizer_schedules.rst │ ├── output.rst │ ├── pipelines.rst │ ├── processors.rst │ ├── tokenizer.rst │ └── trainer.rst │ ├── migration.md │ ├── model_doc │ ├── albert.rst │ ├── auto.rst │ ├── bart.rst │ ├── bert.rst │ ├── bertgeneration.rst │ ├── camembert.rst │ ├── ctrl.rst │ ├── dialogpt.rst │ ├── distilbert.rst │ ├── dpr.rst │ ├── electra.rst │ ├── encoderdecoder.rst │ ├── flaubert.rst │ ├── fsmt.rst │ ├── funnel.rst │ ├── gpt.rst │ ├── gpt2.rst │ ├── layoutlm.rst │ ├── longformer.rst │ ├── lxmert.rst │ ├── marian.rst │ ├── mbart.rst │ ├── mobilebert.rst │ ├── pegasus.rst │ ├── reformer.rst │ ├── retribert.rst │ ├── roberta.rst │ ├── t5.rst │ ├── transformerxl.rst │ ├── xlm.rst │ ├── xlmroberta.rst │ └── xlnet.rst │ ├── model_sharing.rst │ ├── model_summary.rst │ ├── multilingual.rst │ ├── notebooks.md │ ├── perplexity.rst │ ├── philosophy.rst │ ├── preprocessing.rst │ ├── pretrained_models.rst │ ├── quicktour.rst │ ├── serialization.rst │ ├── task_summary.rst │ ├── testing.rst │ ├── tokenizer_summary.rst │ └── training.rst ├── examples ├── README.md ├── adversarial │ ├── README.md │ ├── run_hans.py │ └── utils_hans.py ├── benchmarking │ ├── README.md │ ├── plot_csv_file.py │ ├── run_benchmark.py │ └── run_benchmark_tf.py ├── bert-loses-patience │ ├── README.md │ ├── pabee │ │ ├── __init__.py │ │ ├── modeling_pabee_albert.py │ │ └── modeling_pabee_bert.py │ ├── run_glue_with_pabee.py │ └── test_run_glue_with_pabee.py ├── bertology │ └── run_bertology.py ├── conftest.py ├── contrib │ ├── README.md │ ├── mm-imdb │ │ ├── README.md │ │ ├── run_mmimdb.py │ │ └── utils_mmimdb.py │ ├── run_camembert.py │ ├── run_openai_gpt.py │ ├── run_swag.py │ └── run_transfo_xl.py ├── deebert │ ├── README.md │ ├── entropy_eval.sh │ ├── eval_deebert.sh │ ├── run_glue_deebert.py │ ├── src │ │ ├── __init__.py │ │ ├── modeling_highway_bert.py │ │ └── modeling_highway_roberta.py │ ├── test_glue_deebert.py │ └── train_deebert.sh ├── distillation │ ├── README.md │ ├── distiller.py │ ├── grouped_batch_sampler.py │ ├── lm_seqs_dataset.py │ ├── requirements.txt │ ├── run_squad_w_distillation.py │ ├── scripts │ │ ├── binarized_data.py │ │ ├── extract.py │ │ ├── extract_distilbert.py │ │ └── token_counts.py │ ├── train.py │ ├── training_configs │ │ ├── distilbert-base-cased.json │ │ ├── distilbert-base-multilingual-cased.json │ │ ├── distilbert-base-uncased.json │ │ ├── distilgpt2.json │ │ └── distilroberta-base.json │ └── utils.py ├── language-modeling │ ├── README.md │ └── run_language_modeling.py ├── lightning_base.py ├── longform-qa │ ├── README.md │ ├── eli5_app.py │ └── eli5_utils.py ├── lxmert │ ├── README.md │ ├── demo.ipynb │ ├── extracting_data.py │ ├── modeling_frcnn.py │ ├── processing_image.py │ ├── requirements.txt │ ├── utils.py │ └── visualizing_image.py ├── movement-pruning │ ├── README.md │ ├── Saving_PruneBERT.ipynb │ ├── bertarize.py │ ├── counts_parameters.py │ ├── emmental │ │ ├── __init__.py │ │ ├── configuration_bert_masked.py │ │ ├── modeling_bert_masked.py │ │ └── modules │ │ │ ├── __init__.py │ │ │ ├── binarizer.py │ │ │ └── masked_nn.py │ ├── masked_run_glue.py │ ├── masked_run_squad.py │ └── requirements.txt ├── multiple-choice │ ├── README.md │ ├── run_multiple_choice.py │ ├── run_tf_multiple_choice.py │ └── utils_multiple_choice.py ├── question-answering │ ├── README.md │ ├── run_squad.py │ ├── run_squad_trainer.py │ └── run_tf_squad.py ├── rag │ ├── README.md │ ├── __init__.py │ ├── callbacks.py │ ├── distributed_retriever.py │ ├── eval_rag.py │ ├── finetune.py │ ├── finetune.sh │ ├── parse_dpr_relevance_data.py │ ├── requirements.txt │ ├── test_distributed_retriever.py │ └── utils.py ├── requirements.txt ├── seq2seq │ ├── README.md │ ├── __init__.py │ ├── bertabs │ │ ├── README.md │ │ ├── __init__.py │ │ ├── configuration_bertabs.py │ │ ├── convert_bertabs_original_pytorch_checkpoint.py │ │ ├── modeling_bertabs.py │ │ ├── requirements.txt │ │ ├── run_summarization.py │ │ ├── test_utils_summarization.py │ │ └── utils_summarization.py │ ├── builtin_trainer │ │ ├── finetune.sh │ │ ├── finetune_tpu.sh │ │ ├── train_distil_marian_enro.sh │ │ ├── train_distil_marian_enro_tpu.sh │ │ ├── train_distilbart_cnn.sh │ │ └── train_mbart_cc25_enro.sh │ ├── callbacks.py │ ├── convert_model_to_fp16.py │ ├── convert_pl_checkpoint_to_hf.py │ ├── distil_marian_enro_teacher.sh │ ├── distil_marian_no_teacher.sh │ ├── distillation.py │ ├── download_wmt.py │ ├── dynamic_bs_example.sh │ ├── finetune.py │ ├── finetune.sh │ ├── finetune_bart_tiny.sh │ ├── finetune_pegasus_xsum.sh │ ├── finetune_t5.sh │ ├── finetune_trainer.py │ ├── initialization_utils.py │ ├── minify_dataset.py │ ├── pack_dataset.py │ ├── romanian_postprocessing.md │ ├── run_distiller.sh │ ├── run_distributed_eval.py │ ├── run_eval.py │ ├── run_eval_search.py │ ├── save_len_file.py │ ├── seq2seq_trainer.py │ ├── test_bash_script.py │ ├── test_data │ │ ├── fsmt │ │ │ ├── build-eval-data.py │ │ │ └── fsmt_val_data.json │ │ └── wmt_en_ro │ │ │ ├── test.source │ │ │ ├── test.target │ │ │ ├── train.len │ │ │ ├── train.source │ │ │ ├── train.target │ │ │ ├── val.len │ │ │ ├── val.source │ │ │ └── val.target │ ├── test_datasets.py │ ├── test_finetune_trainer.py │ ├── test_fsmt_bleu_score.py │ ├── test_seq2seq_examples.py │ ├── train_distilbart_cnn.sh │ ├── train_distilbart_xsum.sh │ ├── train_mbart_cc25_enro.sh │ ├── utils.py │ └── xla_spawn.py ├── test_examples.py ├── test_xla_examples.py ├── text-classification │ ├── README.md │ ├── run_glue.py │ ├── run_pl.sh │ ├── run_pl_glue.py │ ├── run_tf_glue.py │ ├── run_tf_text_classification.py │ └── run_xnli.py ├── text-generation │ ├── README.md │ ├── pplm │ │ ├── README.md │ │ ├── imgs │ │ │ ├── headfigure.png │ │ │ └── wooly.png │ │ ├── pplm_classification_head.py │ │ ├── run_pplm.py │ │ └── run_pplm_discrim_train.py │ └── run_generation.py ├── token-classification │ ├── README.md │ ├── run.sh │ ├── run_chunk.sh │ ├── run_ner.py │ ├── run_pl.sh │ ├── run_pl_ner.py │ ├── run_pos.sh │ ├── run_pos_pl.sh │ ├── run_tf_ner.py │ ├── scripts │ │ └── preprocess.py │ ├── tasks.py │ ├── test_ner_examples.py │ └── utils_ner.py └── xla_spawn.py ├── hubconf.py ├── model_cards ├── DeepPavlov │ ├── bert-base-bg-cs-pl-ru-cased │ │ └── README.md │ ├── bert-base-cased-conversational │ │ └── README.md │ ├── bert-base-multilingual-cased-sentence │ │ └── README.md │ ├── rubert-base-cased-conversational │ │ └── README.md │ ├── rubert-base-cased-sentence │ │ └── README.md │ └── rubert-base-cased │ │ └── README.md ├── Hate-speech-CNERG │ ├── dehatebert-mono-arabic │ │ └── README.md │ ├── dehatebert-mono-english │ │ └── README.md │ ├── dehatebert-mono-french │ │ └── README.md │ ├── dehatebert-mono-german │ │ └── README.md │ ├── dehatebert-mono-indonesian │ │ └── README.md │ ├── dehatebert-mono-italian │ │ └── README.md │ ├── dehatebert-mono-polish │ │ └── README.md │ ├── dehatebert-mono-portugese │ │ └── README.md │ └── dehatebert-mono-spanish │ │ └── README.md ├── HooshvareLab │ ├── bert-base-parsbert-armanner-uncased │ │ └── README.md │ ├── bert-base-parsbert-ner-uncased │ │ └── README.md │ ├── bert-base-parsbert-peymaner-uncased │ │ └── README.md │ ├── bert-base-parsbert-uncased │ │ └── README.md │ └── bert-fa-base-uncased │ │ └── README.md ├── KB │ ├── albert-base-swedish-cased-alpha │ │ └── README.md │ ├── bert-base-swedish-cased-ner │ │ └── README.md │ └── bert-base-swedish-cased │ │ └── README.md ├── LorenzoDeMattei │ └── GePpeTto │ │ └── README.md ├── MoseliMotsoehli │ ├── TswanaBert │ │ └── README.md │ └── zuBERTa │ │ └── README.md ├── Musixmatch │ ├── umberto-commoncrawl-cased-v1 │ │ └── README.md │ └── umberto-wikipedia-uncased-v1 │ │ └── README.md ├── NLP4H │ └── ms_bert │ │ └── README.md ├── Naveen-k │ └── KanBERTo │ │ └── README.md ├── NeuML │ ├── bert-small-cord19-squad2 │ │ └── README.md │ ├── bert-small-cord19 │ │ └── README.md │ └── bert-small-cord19qa │ │ └── README.md ├── Norod78 │ └── hewiki-articles-distilGPT2py-il │ │ └── README.md ├── Primer │ └── bart-squad2 │ │ └── README.md ├── Rostlab │ ├── prot_bert │ │ └── README.md │ └── prot_bert_bfd │ │ └── README.md ├── SZTAKI-HLT │ └── hubert-base-cc │ │ └── README.md ├── SparkBeyond │ └── roberta-large-sts-b │ │ └── README.md ├── T-Systems-onsite │ └── bert-german-dbmdz-uncased-sentence-stsb │ │ └── README.md ├── Tereveni-AI │ └── gpt2-124M-uk-fiction │ │ └── README.md ├── TurkuNLP │ ├── bert-base-finnish-cased-v1 │ │ └── README.md │ └── bert-base-finnish-uncased-v1 │ │ └── README.md ├── Vamsi │ └── T5_Paraphrase_Paws │ │ └── README.md ├── VictorSanh │ └── roberta-base-finetuned-yelp-polarity │ │ └── README.md ├── ViktorAlm │ └── electra-base-norwegian-uncased-discriminator │ │ └── README.md ├── a-ware │ ├── bart-squadv2 │ │ └── README.md │ ├── roberta-large-squad-classification │ │ └── README.md │ └── xlmroberta-squadv2 │ │ └── README.md ├── activebus │ ├── BERT-DK_laptop │ │ └── README.md │ ├── BERT-DK_rest │ │ └── README.md │ ├── BERT-PT_laptop │ │ └── README.md │ ├── BERT-PT_rest │ │ └── README.md │ ├── BERT-XD_Review │ │ └── README.md │ └── BERT_Review │ │ └── README.md ├── ahotrod │ ├── albert_xxlargev1_squad2_512 │ │ └── README.md │ ├── electra_large_discriminator_squad2_512 │ │ └── README.md │ ├── roberta_large_squad2 │ │ └── README.md │ └── xlnet_large_squad2_512 │ │ └── README.md ├── akhooli │ ├── gpt2-small-arabic-poetry │ │ └── README.md │ ├── gpt2-small-arabic │ │ └── README.md │ ├── mbart-large-cc25-ar-en │ │ └── README.md │ ├── mbart-large-cc25-en-ar │ │ └── README.md │ └── xlm-r-large-arabic-sent │ │ └── README.md ├── albert-base-v1-README.md ├── albert-xxlarge-v2-README.md ├── aliosm │ ├── ComVE-distilgpt2 │ │ └── README.md │ ├── ComVE-gpt2-large │ │ └── README.md │ ├── ComVE-gpt2-medium │ │ └── README.md │ └── ComVE-gpt2 │ │ └── README.md ├── allegro │ ├── herbert-klej-cased-tokenizer-v1 │ │ └── README.md │ └── herbert-klej-cased-v1 │ │ └── README.md ├── allenai │ ├── biomed_roberta_base │ │ └── README.md │ ├── longformer-base-4096-extra.pos.embd.only │ │ └── README.md │ ├── longformer-base-4096 │ │ └── README.md │ ├── scibert_scivocab_cased │ │ └── README.md │ ├── scibert_scivocab_uncased │ │ └── README.md │ ├── wmt16-en-de-12-1 │ │ └── README.md │ ├── wmt16-en-de-dist-12-1 │ │ └── README.md │ ├── wmt16-en-de-dist-6-1 │ │ └── README.md │ ├── wmt19-de-en-6-6-base │ │ └── README.md │ └── wmt19-de-en-6-6-big │ │ └── README.md ├── amberoad │ └── bert-multilingual-passage-reranking-msmarco │ │ └── README.md ├── antoiloui │ └── belgpt2 │ │ └── README.md ├── aodiniz │ ├── bert_uncased_L-10_H-512_A-8_cord19-200616 │ │ └── README.md │ ├── bert_uncased_L-10_H-512_A-8_cord19-200616_squad2 │ │ └── README.md │ ├── bert_uncased_L-2_H-512_A-8_cord19-200616 │ │ └── README.md │ └── bert_uncased_L-4_H-256_A-4_cord19-200616 │ │ └── README.md ├── asafaya │ ├── bert-base-arabic │ │ └── README.md │ ├── bert-large-arabic │ │ └── README.md │ ├── bert-medium-arabic │ │ └── README.md │ └── bert-mini-arabic │ │ └── README.md ├── aubmindlab │ ├── bert-base-arabert │ │ └── README.md │ └── bert-base-arabertv01 │ │ └── README.md ├── bart-large-cnn │ └── README.md ├── bart-large-xsum │ └── README.md ├── bashar-talafha │ └── multi-dialect-bert-base-arabic │ │ └── README.md ├── bayartsogt │ └── albert-mongolian │ │ └── README.md ├── bert-base-cased-README.md ├── bert-base-chinese-README.md ├── bert-base-german-cased-README.md ├── bert-base-german-dbmdz-cased-README.md ├── bert-base-german-dbmdz-uncased-README.md ├── bert-base-multilingual-cased-README.md ├── bert-base-multilingual-uncased-README.md ├── bert-base-uncased-README.md ├── bert-large-cased-README.md ├── binwang │ └── xlnet-base-cased │ │ └── README.md ├── blinoff │ └── roberta-base-russian-v0 │ │ └── README.md ├── cahya │ ├── bert-base-indonesian-522M │ │ └── README.md │ ├── gpt2-small-indonesian-522M │ │ └── README.md │ └── roberta-base-indonesian-522M │ │ └── README.md ├── camembert-base-README.md ├── camembert │ ├── camembert-base-ccnet-4gb │ │ └── README.md │ ├── camembert-base-ccnet │ │ └── README.md │ ├── camembert-base-oscar-4gb │ │ └── README.md │ ├── camembert-base-wikipedia-4gb │ │ └── README.md │ └── camembert-large │ │ └── README.md ├── canwenxu │ └── BERT-of-Theseus-MNLI │ │ └── README.md ├── cedpsam │ └── chatbot_fr │ │ └── README.md ├── chrisliu298 │ └── arxiv_ai_gpt2 │ │ └── README.md ├── cimm-kzn │ └── rudr-bert │ │ └── README.md ├── clue │ ├── albert_chinese_small │ │ └── README.md │ ├── albert_chinese_tiny │ │ └── README.md │ ├── roberta_chinese_3L312_clue_tiny │ │ └── README.md │ ├── roberta_chinese_base │ │ └── README.md │ ├── roberta_chinese_large │ │ └── README.md │ └── xlnet_chinese_large │ │ └── README.md ├── codegram │ ├── calbert-base-uncased │ │ └── README.md │ └── calbert-tiny-uncased │ │ └── README.md ├── csarron │ ├── bert-base-uncased-squad-v1 │ │ └── README.md │ ├── mobilebert-uncased-squad-v1 │ │ └── README.md │ ├── mobilebert-uncased-squad-v2 │ │ └── README.md │ └── roberta-base-squad-v1 │ │ └── README.md ├── daigo │ └── bert-base-japanese-sentiment │ │ └── README.md ├── dbmdz │ ├── bert-base-german-cased │ │ └── README.md │ ├── bert-base-german-europeana-cased │ │ └── README.md │ ├── bert-base-german-europeana-uncased │ │ └── README.md │ ├── bert-base-german-uncased │ │ └── README.md │ ├── bert-base-italian-cased │ │ └── README.md │ ├── bert-base-italian-uncased │ │ └── README.md │ ├── bert-base-italian-xxl-cased │ │ └── README.md │ ├── bert-base-italian-xxl-uncased │ │ └── README.md │ ├── bert-base-turkish-128k-cased │ │ └── README.md │ ├── bert-base-turkish-128k-uncased │ │ └── README.md │ ├── bert-base-turkish-cased │ │ └── README.md │ ├── bert-base-turkish-uncased │ │ └── README.md │ ├── distilbert-base-turkish-cased │ │ └── README.md │ ├── electra-base-turkish-cased-discriminator │ │ └── README.md │ └── electra-small-turkish-cased-discriminator │ │ └── README.md ├── dccuchile │ ├── bert-base-spanish-wwm-cased │ │ └── README.md │ └── bert-base-spanish-wwm-uncased │ │ └── README.md ├── deepset │ ├── bert-base-german-cased-oldvocab │ │ └── README.md │ ├── electra-base-squad2 │ │ └── README.md │ ├── minilm-uncased-squad2 │ │ └── README.md │ ├── quora_dedup_bert_base │ │ └── README.md │ ├── roberta-base-squad2-covid │ │ └── README.md │ ├── roberta-base-squad2 │ │ └── README.md │ ├── sentence_bert │ │ └── README.md │ └── xlm-roberta-large-squad2 │ │ └── README.md ├── digitalepidemiologylab │ └── covid-twitter-bert │ │ └── README.md ├── distilbert-base-cased-distilled-squad-README.md ├── distilbert-base-multilingual-cased-README.md ├── distilbert-base-uncased-README.md ├── distilbert-base-uncased-distilled-squad-README.md ├── distilgpt2-README.md ├── distilroberta-base-README.md ├── djstrong │ └── bg_cs_pl_ru_cased_L-12_H-768_A-12 │ │ └── README.md ├── dkleczek │ ├── bert-base-polish-cased-v1 │ │ └── README.md │ └── bert-base-polish-uncased-v1 │ │ └── README.md ├── dumitrescustefan │ ├── bert-base-romanian-cased-v1 │ │ └── README.md │ └── bert-base-romanian-uncased-v1 │ │ └── README.md ├── elgeish │ ├── cs224n-squad2.0-albert-base-v2 │ │ └── README.md │ ├── cs224n-squad2.0-albert-large-v2 │ │ └── README.md │ ├── cs224n-squad2.0-albert-xxlarge-v1 │ │ └── README.md │ ├── cs224n-squad2.0-distilbert-base-uncased │ │ └── README.md │ └── cs224n-squad2.0-roberta-base │ │ └── README.md ├── emilyalsentzer │ ├── Bio_ClinicalBERT │ │ └── README.md │ └── Bio_Discharge_Summary_BERT │ │ └── README.md ├── etalab-ia │ └── camembert-base-squadFR-fquad-piaf │ │ └── README.md ├── facebook │ ├── bart-large-cnn │ │ └── README.md │ ├── bart-large │ │ └── README.md │ ├── rag-sequence-base │ │ └── README.md │ ├── rag-sequence-nq │ │ └── README.md │ ├── rag-token-base │ │ └── README.md │ ├── rag-token-nq │ │ └── README.md │ ├── rag-token-nq_new │ │ └── README.md │ ├── wmt19-de-en │ │ └── README.md │ ├── wmt19-en-de │ │ └── README.md │ ├── wmt19-en-ru │ │ └── README.md │ └── wmt19-ru-en │ │ └── README.md ├── flexudy │ └── t5-base-multi-sentence-doctor │ │ ├── README.md │ │ └── sent-banner.png ├── fmikaelian │ ├── camembert-base-fquad │ │ └── README.md │ ├── camembert-base-squad │ │ └── README.md │ └── flaubert-base-uncased-squad │ │ └── README.md ├── fran-martinez │ └── scibert_scivocab_cased_ner_jnlpba │ │ └── README.md ├── funnel-transformer │ ├── intermediate-base │ │ └── README.md │ ├── intermediate │ │ └── README.md │ ├── large-base │ │ └── README.md │ ├── large │ │ └── README.md │ ├── medium-base │ │ └── README.md │ ├── medium │ │ └── README.md │ ├── small-base │ │ └── README.md │ ├── small │ │ └── README.md │ ├── xlarge-base │ │ └── README.md │ └── xlarge │ │ └── README.md ├── gaochangkuan │ └── model_dir │ │ └── README.md ├── german-nlp-group │ └── electra-base-german-uncased │ │ └── README.md ├── giganticode │ └── StackOBERTflow-comments-small-v1 │ │ └── README.md ├── gilf │ ├── french-camembert-postag-model │ │ └── README.md │ └── french-postag-model │ │ └── README.md ├── google │ ├── bert2bert_L-24_wmt_de_en │ │ └── README.md │ ├── bert2bert_L-24_wmt_en_de │ │ └── README.md │ ├── bert_uncased_L-10_H-128_A-2 │ │ └── README.md │ ├── bert_uncased_L-10_H-256_A-4 │ │ └── README.md │ ├── bert_uncased_L-10_H-512_A-8 │ │ └── README.md │ ├── bert_uncased_L-10_H-768_A-12 │ │ └── README.md │ ├── bert_uncased_L-12_H-128_A-2 │ │ └── README.md │ ├── bert_uncased_L-12_H-256_A-4 │ │ └── README.md │ ├── bert_uncased_L-12_H-512_A-8 │ │ └── README.md │ ├── bert_uncased_L-12_H-768_A-12 │ │ └── README.md │ ├── bert_uncased_L-2_H-128_A-2 │ │ └── README.md │ ├── bert_uncased_L-2_H-256_A-4 │ │ └── README.md │ ├── bert_uncased_L-2_H-512_A-8 │ │ └── README.md │ ├── bert_uncased_L-2_H-768_A-12 │ │ └── README.md │ ├── bert_uncased_L-4_H-128_A-2 │ │ └── README.md │ ├── bert_uncased_L-4_H-256_A-4 │ │ └── README.md │ ├── bert_uncased_L-4_H-512_A-8 │ │ └── README.md │ ├── bert_uncased_L-4_H-768_A-12 │ │ └── README.md │ ├── bert_uncased_L-6_H-128_A-2 │ │ └── README.md │ ├── bert_uncased_L-6_H-256_A-4 │ │ └── README.md │ ├── bert_uncased_L-6_H-512_A-8 │ │ └── README.md │ ├── bert_uncased_L-6_H-768_A-12 │ │ └── README.md │ ├── bert_uncased_L-8_H-128_A-2 │ │ └── README.md │ ├── bert_uncased_L-8_H-256_A-4 │ │ └── README.md │ ├── bert_uncased_L-8_H-512_A-8 │ │ └── README.md │ ├── bert_uncased_L-8_H-768_A-12 │ │ └── README.md │ ├── electra-base-discriminator │ │ └── README.md │ ├── electra-base-generator │ │ └── README.md │ ├── electra-large-discriminator │ │ └── README.md │ ├── electra-large-generator │ │ └── README.md │ ├── electra-small-discriminator │ │ └── README.md │ ├── electra-small-generator │ │ └── README.md │ ├── mobilebert-uncased │ │ └── README.md │ ├── reformer-crime-and-punishment │ │ └── README.md │ ├── reformer-enwik8 │ │ └── README.md │ ├── roberta2roberta_L-24_bbc │ │ └── README.md │ ├── roberta2roberta_L-24_cnn_daily_mail │ │ └── README.md │ ├── roberta2roberta_L-24_discofuse │ │ └── README.md │ ├── roberta2roberta_L-24_gigaword │ │ └── README.md │ └── roberta2roberta_L-24_wikisplit │ │ └── README.md ├── gpt2-README.md ├── gpt2-large-README.md ├── gpt2-medium-README.md ├── gpt2-xl-README.md ├── gsarti │ ├── biobert-nli │ │ └── README.md │ ├── covidbert-nli │ │ └── README.md │ └── scibert-nli │ │ └── README.md ├── healx │ ├── gpt-2-pubmed-large │ │ └── README.md │ └── gpt-2-pubmed-medium │ │ └── README.md ├── henryk │ ├── bert-base-multilingual-cased-finetuned-dutch-squad2 │ │ └── README.md │ ├── bert-base-multilingual-cased-finetuned-polish-squad1 │ │ └── README.md │ └── bert-base-multilingual-cased-finetuned-polish-squad2 │ │ └── README.md ├── huggingface │ ├── CodeBERTa-language-id │ │ └── README.md │ └── CodeBERTa-small-v1 │ │ └── README.md ├── huseinzol05 │ ├── albert-base-bahasa-cased │ │ └── README.md │ ├── albert-tiny-bahasa-cased │ │ └── README.md │ ├── bert-base-bahasa-cased │ │ └── README.md │ ├── electra-base-discriminator-bahasa-cased │ │ └── README.md │ ├── electra-base-generator-bahasa-cased │ │ └── README.md │ ├── electra-small-discriminator-bahasa-cased │ │ └── README.md │ ├── electra-small-generator-bahasa-cased │ │ └── README.md │ ├── gpt2-117M-bahasa-cased │ │ └── README.md │ ├── gpt2-345M-bahasa-cased │ │ └── README.md │ ├── t5-base-bahasa-cased │ │ └── README.md │ ├── t5-base-bahasa-summarization-cased │ │ └── README.md │ ├── t5-small-bahasa-cased │ │ └── README.md │ ├── t5-small-bahasa-summarization-cased │ │ └── README.md │ ├── tiny-bert-bahasa-cased │ │ └── README.md │ └── xlnet-base-bahasa-cased │ │ └── README.md ├── iarfmoose │ ├── bert-base-cased-qa-evaluator │ │ └── README.md │ ├── roberta-base-bulgarian-pos │ │ └── README.md │ ├── roberta-base-bulgarian │ │ └── README.md │ ├── roberta-small-bulgarian-pos │ │ └── README.md │ ├── roberta-small-bulgarian │ │ └── README.md │ └── t5-base-question-generator │ │ └── README.md ├── illuin │ ├── camembert-base-fquad │ │ └── README.md │ ├── camembert-large-fquad │ │ └── README.md │ └── lepetit │ │ └── README.md ├── indobenchmark │ ├── indobert-base-p1 │ │ └── README.md │ ├── indobert-base-p2 │ │ └── README.md │ ├── indobert-large-p1 │ │ └── README.md │ ├── indobert-large-p2 │ │ └── README.md │ ├── indobert-lite-base-p1 │ │ └── README.md │ ├── indobert-lite-base-p2 │ │ └── README.md │ ├── indobert-lite-large-p1 │ │ └── README.md │ └── indobert-lite-large-p2 │ │ └── README.md ├── ipuneetrathore │ └── bert-base-cased-finetuned-finBERT │ │ └── README.md ├── iuliaturc │ └── bert_uncased_L-2_H-128_A-2 │ │ └── README.md ├── ixa-ehu │ ├── berteus-base-cased │ │ └── README.md │ └── ixambert-base-cased │ │ └── README.md ├── jannesg │ ├── bertsson │ │ └── README.md │ ├── takalane_afr_roberta │ │ └── README.md │ ├── takalane_nbl_roberta │ │ └── README.md │ ├── takalane_nso_roberta │ │ └── README.md │ ├── takalane_sot_roberta │ │ └── README.md │ ├── takalane_ssw_roberta │ │ └── README.md │ ├── takalane_tsn_roberta │ │ └── README.md │ ├── takalane_tso_roberta │ │ └── README.md │ ├── takalane_ven_roberta │ │ └── README.md │ ├── takalane_xho_roberta │ │ └── README.md │ └── takalane_zul_roberta │ │ └── README.md ├── jimregan │ └── BERTreach │ │ └── README.md ├── jme-p │ └── shrugging-grace-tweet-classifier │ │ └── README.md ├── joeddav │ ├── bart-large-mnli-yahoo-answers │ │ └── README.md │ └── xlm-roberta-large-xnli │ │ └── README.md ├── jplu │ ├── tf-camembert-base │ │ └── README.md │ ├── tf-xlm-r-ner-40-lang │ │ └── README.md │ ├── tf-xlm-roberta-base │ │ └── README.md │ └── tf-xlm-roberta-large │ │ └── README.md ├── julien-c │ ├── EsperBERTo-small-pos │ │ └── README.md │ ├── EsperBERTo-small │ │ └── README.md │ ├── bert-xsmall-dummy │ │ └── README.md │ └── dummy-unknown │ │ └── README.md ├── krevas │ ├── finance-koelectra-base-discriminator │ │ └── README.md │ ├── finance-koelectra-base-generator │ │ └── README.md │ ├── finance-koelectra-small-discriminator │ │ └── README.md │ └── finance-koelectra-small-generator │ │ └── README.md ├── ktrapeznikov │ ├── albert-xlarge-v2-squad-v2 │ │ └── README.md │ ├── biobert_v1.1_pubmed_squad_v2 │ │ └── README.md │ └── scibert_scivocab_uncased_squad_v2 │ │ └── README.md ├── kuisailab │ ├── albert-base-arabic │ │ └── README.md │ ├── albert-large-arabic │ │ └── README.md │ └── albert-xlarge-arabic │ │ └── README.md ├── loodos │ ├── albert-base-turkish-uncased │ │ └── README.md │ ├── bert-base-turkish-uncased │ │ └── README.md │ ├── electra-base-turkish-64k-uncased-discriminator │ │ └── README.md │ ├── electra-base-turkish-uncased-discriminator │ │ └── README.md │ ├── electra-small-turkish-cased-discriminator │ │ └── README.md │ └── electra-small-turkish-uncased-discriminator │ │ └── README.md ├── lordtt13 │ ├── COVID-SciBERT │ │ └── README.md │ └── emo-mobilebert │ │ └── README.md ├── lserinol │ └── bert-turkish-question-answering │ │ └── README.md ├── lvwerra │ ├── bert-imdb │ │ └── README.md │ ├── gpt2-imdb-ctrl │ │ └── README.md │ ├── gpt2-imdb-pos │ │ └── README.md │ ├── gpt2-imdb │ │ └── README.md │ └── gpt2-medium-taboo │ │ └── README.md ├── lysandre │ ├── arxiv-nlp │ │ └── README.md │ └── arxiv │ │ └── README.md ├── m3hrdadfi │ └── albert-fa-base-v2 │ │ └── README.md ├── microsoft │ ├── DialoGPT-large │ │ └── README.md │ ├── DialoGPT-medium │ │ └── README.md │ ├── DialoGPT-small │ │ └── README.md │ ├── MiniLM-L12-H384-uncased │ │ └── README.md │ ├── Multilingual-MiniLM-L12-H384 │ │ └── README.md │ ├── codebert-base-mlm │ │ └── README.md │ ├── codebert-base │ │ └── README.md │ ├── layoutlm-base-uncased │ │ └── README.md │ └── layoutlm-large-uncased │ │ └── README.md ├── monologg │ ├── koelectra-base-discriminator │ │ └── README.md │ ├── koelectra-base-generator │ │ └── README.md │ ├── koelectra-small-discriminator │ │ └── README.md │ └── koelectra-small-generator │ │ └── README.md ├── monsoon-nlp │ └── dv-wave │ │ └── README.md ├── moumeneb1 │ └── flaubert-base-cased-ecology_crisis │ │ └── README.md ├── mrm8488 │ ├── CodeBERTaPy │ │ └── README.md │ ├── GPT-2-finetuned-CORD19 │ │ └── README.md │ ├── GPT-2-finetuned-covid-bio-medrxiv │ │ └── README.md │ ├── GuaPeTe-2-tiny │ │ └── README.md │ ├── RoBERTinha │ │ └── README.md │ ├── RoBasquERTa │ │ └── README.md │ ├── RuPERTa-base-finetuned-ner │ │ └── README.md │ ├── RuPERTa-base-finetuned-pawsx-es │ │ └── README.md │ ├── RuPERTa-base-finetuned-pos │ │ └── README.md │ ├── RuPERTa-base-finetuned-squadv1 │ │ └── README.md │ ├── RuPERTa-base-finetuned-squadv2 │ │ └── README.md │ ├── RuPERTa-base │ │ └── README.md │ ├── TinyBERT-spanish-uncased-finetuned-ner │ │ └── README.md │ ├── bert-base-german-dbmdz-cased-finetuned-pawsx-de │ │ └── README.md │ ├── bert-base-spanish-wwm-cased-finetuned-spa-squad2-es │ │ └── README.md │ ├── bert-italian-finedtuned-squadv1-it-alfa │ │ └── README.md │ ├── bert-medium-finetuned-squadv2 │ │ └── README.md │ ├── bert-mini-finetuned-squadv2 │ │ └── README.md │ ├── bert-multi-cased-finedtuned-xquad-tydiqa-goldp │ │ └── README.md │ ├── bert-multi-cased-finetuned-xquadv1 │ │ └── README.md │ ├── bert-multi-uncased-finetuned-xquadv1 │ │ └── README.md │ ├── bert-small-finetuned-squadv2 │ │ └── README.md │ ├── bert-small-finetuned-typo-detection │ │ └── README.md │ ├── bert-spanish-cased-finetuned-ner │ │ └── README.md │ ├── bert-spanish-cased-finetuned-pos-syntax │ │ └── README.md │ ├── bert-spanish-cased-finetuned-pos │ │ └── README.md │ ├── bert-tiny-finetuned-squadv2 │ │ └── README.md │ ├── bert-uncased-finetuned-qnli │ │ └── README.md │ ├── camembert-base-finetuned-pawsx-fr │ │ └── README.md │ ├── chEMBL_smiles_v1 │ │ └── README.md │ ├── codeBERTaJS │ │ └── README.md │ ├── distilbert-base-multi-cased-finetuned-typo-detection │ │ └── README.md │ ├── distilbert-multi-finetuned-for-xqua-on-tydiqa │ │ └── README.md │ ├── distill-bert-base-spanish-wwm-cased-finetuned-spa-squad2-es │ │ └── README.md │ ├── distilroberta-base-finetuned-sentiment │ │ └── README.md │ ├── electra-base-finetuned-squadv1 │ │ └── README.md │ ├── electra-small-finetuned-squadv1 │ │ └── README.md │ ├── electra-small-finetuned-squadv2 │ │ └── README.md │ ├── electricidad-base-discriminator │ │ └── README.md │ ├── electricidad-base-finetuned-pawsx-es │ │ └── README.md │ ├── electricidad-base-generator │ │ └── README.md │ ├── electricidad-small-discriminator │ │ └── README.md │ ├── electricidad-small-finetuned-squadv1-es │ │ └── README.md │ ├── gpt2-finetuned-recipes-cooking │ │ └── README.md │ ├── gpt2-finetuned-recipes-cooking_v2 │ │ └── README.md │ ├── gpt2-imdb-neg │ │ └── README.md │ ├── gpt2-imdb-neutral │ │ └── README.md │ ├── longformer-base-4096-finetuned-squadv2 │ │ └── README.md │ ├── mobilebert-uncased-finetuned-squadv1 │ │ └── README.md │ ├── mobilebert-uncased-finetuned-squadv2 │ │ └── README.md │ ├── roberta-base-1B-1-finetuned-squadv1 │ │ └── README.md │ ├── roberta-base-1B-1-finetuned-squadv2 │ │ └── README.md │ ├── roberta-large-finetuned-wsc │ │ └── README.md │ ├── spanbert-base-finetuned-squadv1 │ │ └── README.md │ ├── spanbert-base-finetuned-squadv2 │ │ └── README.md │ ├── spanbert-base-finetuned-tacred │ │ └── README.md │ ├── spanbert-finetuned-squadv1 │ │ └── README.md │ ├── spanbert-finetuned-squadv2 │ │ └── README.md │ ├── spanbert-large-finetuned-squadv1 │ │ └── README.md │ ├── spanbert-large-finetuned-squadv2 │ │ └── README.md │ ├── spanbert-large-finetuned-tacred │ │ └── README.md │ ├── t5-base-finetuned-break_data-question-retrieval │ │ └── README.md │ ├── t5-base-finetuned-break_data │ │ └── README.md │ ├── t5-base-finetuned-e2m-intent │ │ └── README.md │ ├── t5-base-finetuned-emotion │ │ └── README.md │ ├── t5-base-finetuned-imdb-sentiment │ │ └── README.md │ ├── t5-base-finetuned-question-generation-ap │ │ └── README.md │ ├── t5-base-finetuned-sarcasm-twitter │ │ └── README.md │ ├── t5-base-finetuned-span-sentiment-extraction │ │ └── README.md │ ├── t5-base-finetuned-squadv2 │ │ └── README.md │ ├── t5-base-finetuned-summarize-news │ │ └── README.md │ ├── t5-base-finetuned-wikiSQL-sql-to-en │ │ └── README.md │ ├── t5-base-finetuned-wikiSQL │ │ └── README.md │ ├── t5-small-finetuned-emotion │ │ └── README.md │ ├── t5-small-finetuned-imdb-sentiment │ │ └── README.md │ ├── t5-small-finetuned-quora-for-paraphrasing │ │ └── README.md │ ├── t5-small-finetuned-squadv1 │ │ └── README.md │ ├── t5-small-finetuned-squadv2 │ │ └── README.md │ ├── t5-small-finetuned-wikiSQL │ │ └── README.md │ ├── umberto-wikipedia-uncased-v1-finetuned-squadv1-it │ │ └── README.md │ └── xlm-multi-finetuned-xquadv1 │ │ └── README.md ├── mys │ └── electra-base-turkish-cased-ner │ │ └── README.md ├── neuralmind │ ├── bert-base-portuguese-cased │ │ └── README.md │ └── bert-large-portuguese-cased │ │ └── README.md ├── neuraly │ └── bert-base-italian-cased-sentiment │ │ └── README.md ├── nghuyong │ ├── ernie-1.0 │ │ └── README.md │ ├── ernie-2.0-en │ │ └── README.md │ ├── ernie-2.0-large-en │ │ └── README.md │ └── ernie-tiny │ │ └── README.md ├── nlpaueb │ └── bert-base-greek-uncased-v1 │ │ └── README.md ├── nlptown │ └── bert-base-multilingual-uncased-sentiment │ │ └── README.md ├── nyu-mll │ ├── roberta-base-100M-1 │ │ └── README.md │ ├── roberta-base-100M-2 │ │ └── README.md │ ├── roberta-base-100M-3 │ │ └── README.md │ ├── roberta-base-10M-1 │ │ └── README.md │ ├── roberta-base-10M-2 │ │ └── README.md │ ├── roberta-base-10M-3 │ │ └── README.md │ ├── roberta-base-1B-1 │ │ └── README.md │ ├── roberta-base-1B-2 │ │ └── README.md │ ├── roberta-base-1B-3 │ │ └── README.md │ ├── roberta-med-small-1M-1 │ │ └── README.md │ ├── roberta-med-small-1M-2 │ │ └── README.md │ ├── roberta-med-small-1M-3 │ │ └── README.md │ └── roberta_1M_to_1B │ │ └── README.md ├── oliverguhr │ └── german-sentiment-bert │ │ └── README.md ├── patrickvonplaten │ ├── bert2bert-cnn_dailymail-fp16 │ │ └── README.md │ ├── bert2gpt2-cnn_dailymail-fp16 │ │ └── README.md │ ├── longformer2roberta-cnn_dailymail-fp16 │ │ └── README.md │ ├── roberta2roberta-cnn_dailymail-fp16 │ │ └── README.md │ └── roberta2roberta-share-cnn_dailymail-fp16 │ │ └── README.md ├── pdelobelle │ └── robbert-v2-dutch-base │ │ └── README.md ├── pierreguillou │ └── gpt2-small-portuguese │ │ └── README.md ├── pradhyra │ └── AWSBlogBert │ │ └── README.md ├── pranavpsv │ └── gpt2-genre-story-generator │ │ └── README.md ├── pvl │ └── labse_bert │ │ └── README.md ├── ramsrigouthamg │ └── t5_paraphraser │ │ └── README.md ├── rdenadai │ └── BR_BERTo │ │ └── README.md ├── redewiedergabe │ └── bert-base-historical-german-rw-cased │ │ └── README.md ├── rjbownes │ └── Magic-The-Generating │ │ └── README.md ├── roberta-base-README.md ├── roberta-large-README.md ├── roberta-large-mnli-README.md ├── rohanrajpal │ ├── bert-base-codemixed-uncased-sentiment │ │ └── README.md │ ├── bert-base-en-es-codemix-cased │ │ └── README.md │ ├── bert-base-en-hi-codemix-cased │ │ └── README.md │ └── bert-base-multilingual-codemixed-cased-sentiment │ │ └── README.md ├── sagorsarker │ ├── bangla-bert-base │ │ └── README.md │ ├── codeswitch-hineng-lid-lince │ │ └── README.md │ ├── codeswitch-hineng-ner-lince │ │ └── README.md │ ├── codeswitch-hineng-pos-lince │ │ └── README.md │ ├── codeswitch-nepeng-lid-lince │ │ └── README.md │ ├── codeswitch-spaeng-lid-lince │ │ └── README.md │ ├── codeswitch-spaeng-ner-lince │ │ └── README.md │ ├── codeswitch-spaeng-pos-lince │ │ └── README.md │ └── codeswitch-spaeng-sentiment-analysis-lince │ │ └── README.md ├── savasy │ ├── bert-base-turkish-ner-cased │ │ └── README.md │ ├── bert-base-turkish-sentiment-cased │ │ └── README.md │ ├── bert-base-turkish-squad │ │ └── README.md │ └── bert-turkish-text-classification │ │ └── README.md ├── schmidek │ └── electra-small-cased │ │ └── README.md ├── seiya │ └── oubiobert-base-uncased │ │ └── README.md ├── sentence-transformers │ ├── bert-base-nli-cls-token │ │ └── README.md │ ├── bert-base-nli-max-tokens │ │ └── README.md │ └── bert-base-nli-mean-tokens │ │ └── README.md ├── severinsimmler │ └── literary-german-bert │ │ ├── README.md │ │ ├── kfold.png │ │ └── prosa-jahre.png ├── seyonec │ └── ChemBERTa-zinc-base-v1 │ │ └── README.md ├── shoarora │ ├── alectra-small-owt │ │ └── README.md │ └── electra-small-owt │ │ └── README.md ├── shrugging-grace │ └── tweetclassifier │ │ └── README.md ├── spentaur │ └── yelp │ │ └── README.md ├── stas │ └── tiny-wmt19-en-de │ │ └── README.md ├── stevhliu │ └── astroGPT │ │ └── README.md ├── surajp │ ├── RoBERTa-hindi-guj-san │ │ └── README.md │ ├── SanBERTa │ │ └── README.md │ └── albert-base-sanskrit │ │ └── README.md ├── t5-11b-README.md ├── t5-3b-README.md ├── t5-base-README.md ├── t5-large-README.md ├── t5-small-README.md ├── tblard │ └── tf-allocine │ │ └── README.md ├── tuner007 │ ├── pegasus_paraphrase │ │ └── README.md │ ├── pegasus_qa │ │ └── README.md │ └── t5_abs_qa │ │ └── README.md ├── twmkn9 │ ├── albert-base-v2-squad2 │ │ └── README.md │ ├── bert-base-uncased-squad2 │ │ └── README.md │ ├── distilbert-base-uncased-squad2 │ │ └── README.md │ └── distilroberta-base-squad2 │ │ └── README.md ├── uncnlp │ └── lxmert-base-uncased │ │ ├── LICENSE │ │ ├── README.md │ │ └── lxmert_model-1.jpg ├── unideeplearning │ └── polibert_sa │ │ └── README.md ├── urduhack │ └── roberta-urdu-small │ │ └── README.md ├── valhalla │ ├── bart-large-finetuned-squadv1 │ │ └── README.md │ ├── distilbart-mnli-12-1 │ │ └── README.md │ ├── distilbart-mnli-12-3 │ │ └── README.md │ ├── distilbart-mnli-12-6 │ │ └── README.md │ ├── distilbart-mnli-12-9 │ │ └── README.md │ ├── electra-base-discriminator-finetuned_squadv1 │ │ └── README.md │ ├── longformer-base-4096-finetuned-squadv1 │ │ └── README.md │ ├── t5-base-e2e-qg │ │ └── README.md │ ├── t5-base-qa-qg-hl │ │ └── README.md │ ├── t5-base-qg-hl │ │ └── README.md │ ├── t5-base-squad │ │ └── README.md │ ├── t5-samll-qg-prepend │ │ └── README.md │ ├── t5-small-e2e-qg │ │ └── README.md │ ├── t5-small-qa-qg-hl │ │ └── README.md │ └── t5-small-qg-hl │ │ └── README.md ├── vinai │ ├── bertweet-base │ │ └── README.md │ ├── bertweet-covid19-base-cased │ │ └── README.md │ ├── bertweet-covid19-base-uncased │ │ └── README.md │ ├── phobert-base │ │ └── README.md │ └── phobert-large │ │ └── README.md ├── voidful │ ├── albert_chinese_base │ │ └── README.md │ ├── albert_chinese_large │ │ └── README.md │ ├── albert_chinese_small │ │ └── README.md │ ├── albert_chinese_tiny │ │ └── README.md │ ├── albert_chinese_xlarge │ │ └── README.md │ └── albert_chinese_xxlarge │ │ └── README.md ├── wptoux │ └── albert-chinese-large-qa │ │ └── README.md ├── xlm-mlm-en-2048-README.md ├── xlm-roberta-base-README.md ├── xlm-roberta-large-finetuned-conll03-german-README.md ├── yjernite │ └── bart_eli5 │ │ └── README.md ├── youscan │ └── ukr-roberta-base │ │ └── README.md ├── yuvraj │ ├── summarizer-cnndm │ │ └── README.md │ └── xSumm │ │ └── README.md └── zanelim │ ├── singbert-large-sg │ └── README.md │ ├── singbert-lite-sg │ └── README.md │ └── singbert │ └── README.md ├── notebooks ├── 01-training-tokenizers.ipynb ├── 02-transformers.ipynb ├── 03-pipelines.ipynb ├── 04-onnx-export.ipynb ├── 05-benchmark.ipynb └── README.md ├── pyproject.toml ├── scripts └── fsmt │ ├── convert-allenai-wmt16.sh │ ├── convert-allenai-wmt19.sh │ ├── convert-facebook-wmt19.sh │ ├── eval-allenai-wmt16.sh │ ├── eval-allenai-wmt19.sh │ ├── eval-facebook-wmt19.sh │ ├── fsmt-make-tiny-model.py │ ├── gen-card-allenai-wmt16.py │ ├── gen-card-allenai-wmt19.py │ ├── gen-card-facebook-wmt19.py │ ├── s3-move.sh │ └── tests-to-run.sh ├── setup.cfg ├── setup.py ├── src ├── transformers.egg-info │ ├── PKG-INFO │ ├── SOURCES.txt │ ├── dependency_links.txt │ ├── entry_points.txt │ ├── requires.txt │ └── top_level.txt └── transformers │ ├── .ipynb_checkpoints │ ├── modeling_bart-checkpoint.py │ ├── modeling_utils-checkpoint.py │ └── testing_utils-checkpoint.py │ ├── __init__.py │ ├── __pycache__ │ ├── __init__.cpython-37.pyc │ ├── __init__.cpython-38.pyc │ ├── activations.cpython-37.pyc │ ├── activations.cpython-38.pyc │ ├── activations_tf.cpython-37.pyc │ ├── configuration_albert.cpython-37.pyc │ ├── configuration_albert.cpython-38.pyc │ ├── configuration_auto.cpython-37.pyc │ ├── configuration_auto.cpython-38.pyc │ ├── configuration_bart.cpython-37.pyc │ ├── configuration_bart.cpython-38.pyc │ ├── configuration_bert.cpython-37.pyc │ ├── configuration_bert.cpython-38.pyc │ ├── configuration_bert_generation.cpython-37.pyc │ ├── configuration_bert_generation.cpython-38.pyc │ ├── configuration_camembert.cpython-37.pyc │ ├── configuration_camembert.cpython-38.pyc │ ├── configuration_ctrl.cpython-37.pyc │ ├── configuration_ctrl.cpython-38.pyc │ ├── configuration_distilbert.cpython-37.pyc │ ├── configuration_distilbert.cpython-38.pyc │ ├── configuration_dpr.cpython-37.pyc │ ├── configuration_dpr.cpython-38.pyc │ ├── configuration_electra.cpython-37.pyc │ ├── configuration_electra.cpython-38.pyc │ ├── configuration_encoder_decoder.cpython-37.pyc │ ├── configuration_encoder_decoder.cpython-38.pyc │ ├── configuration_flaubert.cpython-37.pyc │ ├── configuration_flaubert.cpython-38.pyc │ ├── configuration_fsmt.cpython-37.pyc │ ├── configuration_fsmt.cpython-38.pyc │ ├── configuration_funnel.cpython-37.pyc │ ├── configuration_funnel.cpython-38.pyc │ ├── configuration_gpt2.cpython-37.pyc │ ├── configuration_gpt2.cpython-38.pyc │ ├── configuration_layoutlm.cpython-37.pyc │ ├── configuration_layoutlm.cpython-38.pyc │ ├── configuration_longformer.cpython-37.pyc │ ├── configuration_longformer.cpython-38.pyc │ ├── configuration_lxmert.cpython-37.pyc │ ├── configuration_lxmert.cpython-38.pyc │ ├── configuration_marian.cpython-37.pyc │ ├── configuration_marian.cpython-38.pyc │ ├── configuration_mbart.cpython-37.pyc │ ├── configuration_mbart.cpython-38.pyc │ ├── configuration_mmbt.cpython-37.pyc │ ├── configuration_mmbt.cpython-38.pyc │ ├── configuration_mobilebert.cpython-37.pyc │ ├── configuration_mobilebert.cpython-38.pyc │ ├── configuration_openai.cpython-37.pyc │ ├── configuration_openai.cpython-38.pyc │ ├── configuration_pegasus.cpython-37.pyc │ ├── configuration_pegasus.cpython-38.pyc │ ├── configuration_rag.cpython-37.pyc │ ├── configuration_rag.cpython-38.pyc │ ├── configuration_reformer.cpython-37.pyc │ ├── configuration_reformer.cpython-38.pyc │ ├── configuration_retribert.cpython-37.pyc │ ├── configuration_retribert.cpython-38.pyc │ ├── configuration_roberta.cpython-37.pyc │ ├── configuration_roberta.cpython-38.pyc │ ├── configuration_t5.cpython-37.pyc │ ├── configuration_t5.cpython-38.pyc │ ├── configuration_transfo_xl.cpython-37.pyc │ ├── configuration_transfo_xl.cpython-38.pyc │ ├── configuration_utils.cpython-37.pyc │ ├── configuration_utils.cpython-38.pyc │ ├── configuration_xlm.cpython-37.pyc │ ├── configuration_xlm.cpython-38.pyc │ ├── configuration_xlm_roberta.cpython-37.pyc │ ├── configuration_xlm_roberta.cpython-38.pyc │ ├── configuration_xlnet.cpython-37.pyc │ ├── configuration_xlnet.cpython-38.pyc │ ├── file_utils.cpython-37.pyc │ ├── file_utils.cpython-38.pyc │ ├── generation_tf_utils.cpython-37.pyc │ ├── generation_utils.cpython-37.pyc │ ├── generation_utils.cpython-38.pyc │ ├── hf_argparser.cpython-37.pyc │ ├── hf_argparser.cpython-38.pyc │ ├── integrations.cpython-37.pyc │ ├── integrations.cpython-38.pyc │ ├── modelcard.cpython-37.pyc │ ├── modelcard.cpython-38.pyc │ ├── modeling_albert.cpython-37.pyc │ ├── modeling_albert.cpython-38.pyc │ ├── modeling_auto.cpython-37.pyc │ ├── modeling_auto.cpython-38.pyc │ ├── modeling_bart.cpython-37.pyc │ ├── modeling_bart.cpython-38.pyc │ ├── modeling_bert.cpython-37.pyc │ ├── modeling_bert.cpython-38.pyc │ ├── modeling_bert_generation.cpython-37.pyc │ ├── modeling_bert_generation.cpython-38.pyc │ ├── modeling_camembert.cpython-37.pyc │ ├── modeling_camembert.cpython-38.pyc │ ├── modeling_ctrl.cpython-37.pyc │ ├── modeling_ctrl.cpython-38.pyc │ ├── modeling_distilbert.cpython-37.pyc │ ├── modeling_distilbert.cpython-38.pyc │ ├── modeling_dpr.cpython-37.pyc │ ├── modeling_dpr.cpython-38.pyc │ ├── modeling_electra.cpython-37.pyc │ ├── modeling_electra.cpython-38.pyc │ ├── modeling_encoder_decoder.cpython-37.pyc │ ├── modeling_encoder_decoder.cpython-38.pyc │ ├── modeling_flaubert.cpython-37.pyc │ ├── modeling_flaubert.cpython-38.pyc │ ├── modeling_fsmt.cpython-37.pyc │ ├── modeling_fsmt.cpython-38.pyc │ ├── modeling_funnel.cpython-37.pyc │ ├── modeling_funnel.cpython-38.pyc │ ├── modeling_gpt2.cpython-37.pyc │ ├── modeling_gpt2.cpython-38.pyc │ ├── modeling_layoutlm.cpython-37.pyc │ ├── modeling_layoutlm.cpython-38.pyc │ ├── modeling_longformer.cpython-37.pyc │ ├── modeling_longformer.cpython-38.pyc │ ├── modeling_lxmert.cpython-37.pyc │ ├── modeling_lxmert.cpython-38.pyc │ ├── modeling_marian.cpython-37.pyc │ ├── modeling_marian.cpython-38.pyc │ ├── modeling_mbart.cpython-37.pyc │ ├── modeling_mbart.cpython-38.pyc │ ├── modeling_mmbt.cpython-37.pyc │ ├── modeling_mmbt.cpython-38.pyc │ ├── modeling_mobilebert.cpython-37.pyc │ ├── modeling_mobilebert.cpython-38.pyc │ ├── modeling_openai.cpython-37.pyc │ ├── modeling_openai.cpython-38.pyc │ ├── modeling_outputs.cpython-37.pyc │ ├── modeling_outputs.cpython-38.pyc │ ├── modeling_pegasus.cpython-37.pyc │ ├── modeling_pegasus.cpython-38.pyc │ ├── modeling_rag.cpython-37.pyc │ ├── modeling_rag.cpython-38.pyc │ ├── modeling_reformer.cpython-37.pyc │ ├── modeling_reformer.cpython-38.pyc │ ├── modeling_retribert.cpython-37.pyc │ ├── modeling_retribert.cpython-38.pyc │ ├── modeling_roberta.cpython-37.pyc │ ├── modeling_roberta.cpython-38.pyc │ ├── modeling_t5.cpython-37.pyc │ ├── modeling_t5.cpython-38.pyc │ ├── modeling_tf_albert.cpython-37.pyc │ ├── modeling_tf_auto.cpython-37.pyc │ ├── modeling_tf_bert.cpython-37.pyc │ ├── modeling_tf_camembert.cpython-37.pyc │ ├── modeling_tf_ctrl.cpython-37.pyc │ ├── modeling_tf_distilbert.cpython-37.pyc │ ├── modeling_tf_electra.cpython-37.pyc │ ├── modeling_tf_flaubert.cpython-37.pyc │ ├── modeling_tf_funnel.cpython-37.pyc │ ├── modeling_tf_gpt2.cpython-37.pyc │ ├── modeling_tf_longformer.cpython-37.pyc │ ├── modeling_tf_lxmert.cpython-37.pyc │ ├── modeling_tf_mobilebert.cpython-37.pyc │ ├── modeling_tf_openai.cpython-37.pyc │ ├── modeling_tf_outputs.cpython-37.pyc │ ├── modeling_tf_pytorch_utils.cpython-37.pyc │ ├── modeling_tf_pytorch_utils.cpython-38.pyc │ ├── modeling_tf_roberta.cpython-37.pyc │ ├── modeling_tf_t5.cpython-37.pyc │ ├── modeling_tf_transfo_xl.cpython-37.pyc │ ├── modeling_tf_transfo_xl_utilities.cpython-37.pyc │ ├── modeling_tf_utils.cpython-37.pyc │ ├── modeling_tf_xlm.cpython-37.pyc │ ├── modeling_tf_xlm_roberta.cpython-37.pyc │ ├── modeling_tf_xlnet.cpython-37.pyc │ ├── modeling_transfo_xl.cpython-37.pyc │ ├── modeling_transfo_xl.cpython-38.pyc │ ├── modeling_transfo_xl_utilities.cpython-37.pyc │ ├── modeling_transfo_xl_utilities.cpython-38.pyc │ ├── modeling_utils.cpython-37.pyc │ ├── modeling_utils.cpython-38.pyc │ ├── modeling_xlm.cpython-37.pyc │ ├── modeling_xlm.cpython-38.pyc │ ├── modeling_xlm_roberta.cpython-37.pyc │ ├── modeling_xlm_roberta.cpython-38.pyc │ ├── modeling_xlnet.cpython-37.pyc │ ├── modeling_xlnet.cpython-38.pyc │ ├── optimization.cpython-37.pyc │ ├── optimization.cpython-38.pyc │ ├── optimization_tf.cpython-37.pyc │ ├── pipelines.cpython-37.pyc │ ├── pipelines.cpython-38.pyc │ ├── retrieval_rag.cpython-37.pyc │ ├── retrieval_rag.cpython-38.pyc │ ├── tokenization_albert.cpython-37.pyc │ ├── tokenization_albert.cpython-38.pyc │ ├── tokenization_auto.cpython-37.pyc │ ├── tokenization_auto.cpython-38.pyc │ ├── tokenization_bart.cpython-37.pyc │ ├── tokenization_bart.cpython-38.pyc │ ├── tokenization_bert.cpython-37.pyc │ ├── tokenization_bert.cpython-38.pyc │ ├── tokenization_bert_generation.cpython-37.pyc │ ├── tokenization_bert_generation.cpython-38.pyc │ ├── tokenization_bert_japanese.cpython-37.pyc │ ├── tokenization_bert_japanese.cpython-38.pyc │ ├── tokenization_bertweet.cpython-37.pyc │ ├── tokenization_bertweet.cpython-38.pyc │ ├── tokenization_camembert.cpython-37.pyc │ ├── tokenization_camembert.cpython-38.pyc │ ├── tokenization_ctrl.cpython-37.pyc │ ├── tokenization_ctrl.cpython-38.pyc │ ├── tokenization_distilbert.cpython-37.pyc │ ├── tokenization_distilbert.cpython-38.pyc │ ├── tokenization_dpr.cpython-37.pyc │ ├── tokenization_dpr.cpython-38.pyc │ ├── tokenization_electra.cpython-37.pyc │ ├── tokenization_electra.cpython-38.pyc │ ├── tokenization_flaubert.cpython-37.pyc │ ├── tokenization_flaubert.cpython-38.pyc │ ├── tokenization_fsmt.cpython-37.pyc │ ├── tokenization_fsmt.cpython-38.pyc │ ├── tokenization_funnel.cpython-37.pyc │ ├── tokenization_funnel.cpython-38.pyc │ ├── tokenization_gpt2.cpython-37.pyc │ ├── tokenization_gpt2.cpython-38.pyc │ ├── tokenization_layoutlm.cpython-37.pyc │ ├── tokenization_layoutlm.cpython-38.pyc │ ├── tokenization_longformer.cpython-37.pyc │ ├── tokenization_longformer.cpython-38.pyc │ ├── tokenization_lxmert.cpython-37.pyc │ ├── tokenization_lxmert.cpython-38.pyc │ ├── tokenization_marian.cpython-37.pyc │ ├── tokenization_marian.cpython-38.pyc │ ├── tokenization_mbart.cpython-37.pyc │ ├── tokenization_mbart.cpython-38.pyc │ ├── tokenization_mobilebert.cpython-37.pyc │ ├── tokenization_mobilebert.cpython-38.pyc │ ├── tokenization_openai.cpython-37.pyc │ ├── tokenization_openai.cpython-38.pyc │ ├── tokenization_pegasus.cpython-37.pyc │ ├── tokenization_pegasus.cpython-38.pyc │ ├── tokenization_phobert.cpython-37.pyc │ ├── tokenization_phobert.cpython-38.pyc │ ├── tokenization_rag.cpython-37.pyc │ ├── tokenization_rag.cpython-38.pyc │ ├── tokenization_reformer.cpython-37.pyc │ ├── tokenization_reformer.cpython-38.pyc │ ├── tokenization_retribert.cpython-37.pyc │ ├── tokenization_retribert.cpython-38.pyc │ ├── tokenization_roberta.cpython-37.pyc │ ├── tokenization_roberta.cpython-38.pyc │ ├── tokenization_t5.cpython-37.pyc │ ├── tokenization_t5.cpython-38.pyc │ ├── tokenization_transfo_xl.cpython-37.pyc │ ├── tokenization_transfo_xl.cpython-38.pyc │ ├── tokenization_utils.cpython-37.pyc │ ├── tokenization_utils.cpython-38.pyc │ ├── tokenization_utils_base.cpython-37.pyc │ ├── tokenization_utils_base.cpython-38.pyc │ ├── tokenization_utils_fast.cpython-37.pyc │ ├── tokenization_utils_fast.cpython-38.pyc │ ├── tokenization_xlm.cpython-37.pyc │ ├── tokenization_xlm.cpython-38.pyc │ ├── tokenization_xlm_roberta.cpython-37.pyc │ ├── tokenization_xlm_roberta.cpython-38.pyc │ ├── tokenization_xlnet.cpython-37.pyc │ ├── tokenization_xlnet.cpython-38.pyc │ ├── trainer.cpython-37.pyc │ ├── trainer.cpython-38.pyc │ ├── trainer_tf.cpython-37.pyc │ ├── trainer_utils.cpython-37.pyc │ ├── trainer_utils.cpython-38.pyc │ ├── training_args.cpython-37.pyc │ ├── training_args.cpython-38.pyc │ ├── training_args_tf.cpython-37.pyc │ └── training_args_tf.cpython-38.pyc │ ├── activations.py │ ├── activations_tf.py │ ├── benchmark │ ├── __init__.py │ ├── __pycache__ │ │ ├── __init__.cpython-37.pyc │ │ ├── __init__.cpython-38.pyc │ │ ├── benchmark.cpython-37.pyc │ │ ├── benchmark.cpython-38.pyc │ │ ├── benchmark_args.cpython-37.pyc │ │ ├── benchmark_args.cpython-38.pyc │ │ ├── benchmark_args_tf.cpython-37.pyc │ │ ├── benchmark_args_utils.cpython-37.pyc │ │ ├── benchmark_args_utils.cpython-38.pyc │ │ ├── benchmark_tf.cpython-37.pyc │ │ ├── benchmark_utils.cpython-37.pyc │ │ └── benchmark_utils.cpython-38.pyc │ ├── benchmark.py │ ├── benchmark_args.py │ ├── benchmark_args_tf.py │ ├── benchmark_args_utils.py │ ├── benchmark_tf.py │ └── benchmark_utils.py │ ├── commands │ ├── __init__.py │ ├── convert.py │ ├── download.py │ ├── env.py │ ├── run.py │ ├── serving.py │ ├── train.py │ ├── transformers_cli.py │ └── user.py │ ├── configuration_albert.py │ ├── configuration_auto.py │ ├── configuration_bart.py │ ├── configuration_bert.py │ ├── configuration_bert_generation.py │ ├── configuration_camembert.py │ ├── configuration_ctrl.py │ ├── configuration_distilbert.py │ ├── configuration_dpr.py │ ├── configuration_electra.py │ ├── configuration_encoder_decoder.py │ ├── configuration_flaubert.py │ ├── configuration_fsmt.py │ ├── configuration_funnel.py │ ├── configuration_gpt2.py │ ├── configuration_layoutlm.py │ ├── configuration_longformer.py │ ├── configuration_lxmert.py │ ├── configuration_marian.py │ ├── configuration_mbart.py │ ├── configuration_mmbt.py │ ├── configuration_mobilebert.py │ ├── configuration_openai.py │ ├── configuration_pegasus.py │ ├── configuration_rag.py │ ├── configuration_reformer.py │ ├── configuration_retribert.py │ ├── configuration_roberta.py │ ├── configuration_t5.py │ ├── configuration_transfo_xl.py │ ├── configuration_utils.py │ ├── configuration_xlm.py │ ├── configuration_xlm_roberta.py │ ├── configuration_xlnet.py │ ├── convert_albert_original_tf_checkpoint_to_pytorch.py │ ├── convert_bart_original_pytorch_checkpoint_to_pytorch.py │ ├── convert_bert_original_tf2_checkpoint_to_pytorch.py │ ├── convert_bert_original_tf_checkpoint_to_pytorch.py │ ├── convert_bert_pytorch_checkpoint_to_original_tf.py │ ├── convert_dialogpt_original_pytorch_checkpoint_to_pytorch.py │ ├── convert_dpr_original_checkpoint_to_pytorch.py │ ├── convert_electra_original_tf_checkpoint_to_pytorch.py │ ├── convert_fsmt_original_pytorch_checkpoint_to_pytorch.py │ ├── convert_funnel_original_tf_checkpoint_to_pytorch.py │ ├── convert_gpt2_original_tf_checkpoint_to_pytorch.py │ ├── convert_graph_to_onnx.py │ ├── convert_longformer_original_pytorch_lightning_to_pytorch.py │ ├── convert_lxmert_original_tf_checkpoint_to_pytorch.py │ ├── convert_marian_to_pytorch.py │ ├── convert_mbart_original_checkpoint_to_pytorch.py │ ├── convert_mobilebert_original_tf_checkpoint_to_pytorch.py │ ├── convert_openai_original_tf_checkpoint_to_pytorch.py │ ├── convert_pegasus_tf_to_pytorch.py │ ├── convert_pytorch_checkpoint_to_tf2.py │ ├── convert_reformer_trax_checkpoint_to_pytorch.py │ ├── convert_roberta_original_pytorch_checkpoint_to_pytorch.py │ ├── convert_t5_original_tf_checkpoint_to_pytorch.py │ ├── convert_tf_hub_seq_to_seq_bert_to_pytorch.py │ ├── convert_transfo_xl_original_tf_checkpoint_to_pytorch.py │ ├── convert_xlm_original_pytorch_checkpoint_to_pytorch.py │ ├── convert_xlnet_original_tf_checkpoint_to_pytorch.py │ ├── data │ ├── __init__.py │ ├── __pycache__ │ │ ├── __init__.cpython-37.pyc │ │ ├── __init__.cpython-38.pyc │ │ ├── data_collator.cpython-37.pyc │ │ └── data_collator.cpython-38.pyc │ ├── data_collator.py │ ├── datasets │ │ ├── __init__.py │ │ ├── __pycache__ │ │ │ ├── __init__.cpython-37.pyc │ │ │ ├── __init__.cpython-38.pyc │ │ │ ├── glue.cpython-37.pyc │ │ │ ├── glue.cpython-38.pyc │ │ │ ├── language_modeling.cpython-37.pyc │ │ │ ├── language_modeling.cpython-38.pyc │ │ │ ├── squad.cpython-37.pyc │ │ │ └── squad.cpython-38.pyc │ │ ├── glue.py │ │ ├── language_modeling.py │ │ └── squad.py │ ├── metrics │ │ ├── __init__.py │ │ ├── __pycache__ │ │ │ ├── __init__.cpython-37.pyc │ │ │ └── __init__.cpython-38.pyc │ │ └── squad_metrics.py │ ├── processors │ │ ├── __init__.py │ │ ├── __pycache__ │ │ │ ├── __init__.cpython-37.pyc │ │ │ ├── __init__.cpython-38.pyc │ │ │ ├── glue.cpython-37.pyc │ │ │ ├── glue.cpython-38.pyc │ │ │ ├── squad.cpython-37.pyc │ │ │ ├── squad.cpython-38.pyc │ │ │ ├── utils.cpython-37.pyc │ │ │ ├── utils.cpython-38.pyc │ │ │ ├── xnli.cpython-37.pyc │ │ │ └── xnli.cpython-38.pyc │ │ ├── glue.py │ │ ├── squad.py │ │ ├── utils.py │ │ └── xnli.py │ └── test_generation_utils.py │ ├── file_utils.py │ ├── generation_tf_utils.py │ ├── generation_utils.py │ ├── hf_api.py │ ├── hf_argparser.py │ ├── integrations.py │ ├── modelcard.py │ ├── modeling_albert.py │ ├── modeling_auto.py │ ├── modeling_bart.py │ ├── modeling_bert.py │ ├── modeling_bert_generation.py │ ├── modeling_camembert.py │ ├── modeling_ctrl.py │ ├── modeling_distilbert.py │ ├── modeling_dpr.py │ ├── modeling_electra.py │ ├── modeling_encoder_decoder.py │ ├── modeling_flaubert.py │ ├── modeling_fsmt.py │ ├── modeling_funnel.py │ ├── modeling_gpt2.py │ ├── modeling_layoutlm.py │ ├── modeling_longformer.py │ ├── modeling_lxmert.py │ ├── modeling_marian.py │ ├── modeling_mbart.py │ ├── modeling_mmbt.py │ ├── modeling_mobilebert.py │ ├── modeling_openai.py │ ├── modeling_outputs.py │ ├── modeling_pegasus.py │ ├── modeling_rag.py │ ├── modeling_reformer.py │ ├── modeling_retribert.py │ ├── modeling_roberta.py │ ├── modeling_t5.py │ ├── modeling_tf_albert.py │ ├── modeling_tf_auto.py │ ├── modeling_tf_bert.py │ ├── modeling_tf_camembert.py │ ├── modeling_tf_ctrl.py │ ├── modeling_tf_distilbert.py │ ├── modeling_tf_electra.py │ ├── modeling_tf_flaubert.py │ ├── modeling_tf_funnel.py │ ├── modeling_tf_gpt2.py │ ├── modeling_tf_longformer.py │ ├── modeling_tf_lxmert.py │ ├── modeling_tf_mobilebert.py │ ├── modeling_tf_openai.py │ ├── modeling_tf_outputs.py │ ├── modeling_tf_pytorch_utils.py │ ├── modeling_tf_roberta.py │ ├── modeling_tf_t5.py │ ├── modeling_tf_transfo_xl.py │ ├── modeling_tf_transfo_xl_utilities.py │ ├── modeling_tf_utils.py │ ├── modeling_tf_xlm.py │ ├── modeling_tf_xlm_roberta.py │ ├── modeling_tf_xlnet.py │ ├── modeling_transfo_xl.py │ ├── modeling_transfo_xl_utilities.py │ ├── modeling_utils.py │ ├── modeling_xlm.py │ ├── modeling_xlm_roberta.py │ ├── modeling_xlnet.py │ ├── optimization.py │ ├── optimization_tf.py │ ├── pipelines.py │ ├── retrieval_rag.py │ ├── testing_utils.py │ ├── tokenization_albert.py │ ├── tokenization_auto.py │ ├── tokenization_bart.py │ ├── tokenization_bert.py │ ├── tokenization_bert_generation.py │ ├── tokenization_bert_japanese.py │ ├── tokenization_bertweet.py │ ├── tokenization_camembert.py │ ├── tokenization_ctrl.py │ ├── tokenization_distilbert.py │ ├── tokenization_dpr.py │ ├── tokenization_electra.py │ ├── tokenization_flaubert.py │ ├── tokenization_fsmt.py │ ├── tokenization_funnel.py │ ├── tokenization_gpt2.py │ ├── tokenization_layoutlm.py │ ├── tokenization_longformer.py │ ├── tokenization_lxmert.py │ ├── tokenization_marian.py │ ├── tokenization_mbart.py │ ├── tokenization_mobilebert.py │ ├── tokenization_openai.py │ ├── tokenization_pegasus.py │ ├── tokenization_phobert.py │ ├── tokenization_rag.py │ ├── tokenization_reformer.py │ ├── tokenization_retribert.py │ ├── tokenization_roberta.py │ ├── tokenization_t5.py │ ├── tokenization_transfo_xl.py │ ├── tokenization_utils.py │ ├── tokenization_utils_base.py │ ├── tokenization_utils_fast.py │ ├── tokenization_xlm.py │ ├── tokenization_xlm_roberta.py │ ├── tokenization_xlnet.py │ ├── trainer.py │ ├── trainer_tf.py │ ├── trainer_utils.py │ ├── training_args.py │ ├── training_args_tf.py │ └── utils │ ├── __init__.py │ ├── __pycache__ │ ├── __init__.cpython-37.pyc │ ├── __init__.cpython-38.pyc │ ├── logging.cpython-37.pyc │ └── logging.cpython-38.pyc │ └── logging.py ├── templates ├── adding_a_new_example_script │ ├── README.md │ ├── run_xxx.py │ └── utils_xxx.py └── adding_a_new_model │ ├── README.md │ ├── configuration_xxx.py │ ├── convert_xxx_original_tf_checkpoint_to_pytorch.py │ ├── modeling_tf_xxx.py │ ├── modeling_xxx.py │ ├── tests │ ├── test_modeling_tf_xxx.py │ ├── test_modeling_xxx.py │ └── test_tokenization_xxx.py │ └── tokenization_xxx.py ├── tests ├── __init__.py ├── conftest.py ├── fixtures │ ├── dummy-config.json │ ├── empty.txt │ ├── input.txt │ ├── sample_text.txt │ ├── spiece.model │ ├── test_sentencepiece.model │ └── tests_samples │ │ ├── .gitignore │ │ ├── GermEval │ │ ├── dev.txt │ │ ├── labels.txt │ │ └── train.txt │ │ ├── MRPC │ │ ├── dev.tsv │ │ └── train.tsv │ │ ├── SQUAD │ │ ├── dev-v2.0.json │ │ └── train-v2.0.json │ │ ├── STS-B │ │ ├── dev.tsv │ │ └── train.tsv │ │ └── wiki_text │ │ └── wiki_00 ├── test_activations.py ├── test_activations_tf.py ├── test_benchmark.py ├── test_benchmark_tf.py ├── test_cli.py ├── test_configuration_auto.py ├── test_configuration_common.py ├── test_data_collator.py ├── test_doc_samples.py ├── test_hf_api.py ├── test_hf_argparser.py ├── test_logging.py ├── test_model_card.py ├── test_model_output.py ├── test_modeling_albert.py ├── test_modeling_auto.py ├── test_modeling_bart.py ├── test_modeling_bert.py ├── test_modeling_bert_generation.py ├── test_modeling_camembert.py ├── test_modeling_common.py ├── test_modeling_ctrl.py ├── test_modeling_distilbert.py ├── test_modeling_dpr.py ├── test_modeling_electra.py ├── test_modeling_encoder_decoder.py ├── test_modeling_flaubert.py ├── test_modeling_fsmt.py ├── test_modeling_funnel.py ├── test_modeling_gpt2.py ├── test_modeling_layoutlm.py ├── test_modeling_longformer.py ├── test_modeling_lxmert.py ├── test_modeling_marian.py ├── test_modeling_mbart.py ├── test_modeling_mobilebert.py ├── test_modeling_openai.py ├── test_modeling_pegasus.py ├── test_modeling_rag.py ├── test_modeling_reformer.py ├── test_modeling_roberta.py ├── test_modeling_t5.py ├── test_modeling_tf_albert.py ├── test_modeling_tf_auto.py ├── test_modeling_tf_bert.py ├── test_modeling_tf_camembert.py ├── test_modeling_tf_common.py ├── test_modeling_tf_ctrl.py ├── test_modeling_tf_distilbert.py ├── test_modeling_tf_electra.py ├── test_modeling_tf_flaubert.py ├── test_modeling_tf_funnel.py ├── test_modeling_tf_gpt2.py ├── test_modeling_tf_longformer.py ├── test_modeling_tf_lxmert.py ├── test_modeling_tf_mobilebert.py ├── test_modeling_tf_openai.py ├── test_modeling_tf_roberta.py ├── test_modeling_tf_t5.py ├── test_modeling_tf_transfo_xl.py ├── test_modeling_tf_xlm.py ├── test_modeling_tf_xlm_roberta.py ├── test_modeling_tf_xlnet.py ├── test_modeling_transfo_xl.py ├── test_modeling_xlm.py ├── test_modeling_xlm_roberta.py ├── test_modeling_xlnet.py ├── test_onnx.py ├── test_optimization.py ├── test_optimization_tf.py ├── test_pipelines.py ├── test_retrieval_rag.py ├── test_skip_decorators.py ├── test_tokenization_albert.py ├── test_tokenization_auto.py ├── test_tokenization_bart.py ├── test_tokenization_bert.py ├── test_tokenization_bert_generation.py ├── test_tokenization_bert_japanese.py ├── test_tokenization_bertweet.py ├── test_tokenization_common.py ├── test_tokenization_ctrl.py ├── test_tokenization_distilbert.py ├── test_tokenization_dpr.py ├── test_tokenization_fast.py ├── test_tokenization_fsmt.py ├── test_tokenization_funnel.py ├── test_tokenization_gpt2.py ├── test_tokenization_layoutlm.py ├── test_tokenization_lxmert.py ├── test_tokenization_marian.py ├── test_tokenization_mbart.py ├── test_tokenization_openai.py ├── test_tokenization_pegasus.py ├── test_tokenization_phobert.py ├── test_tokenization_rag.py ├── test_tokenization_reformer.py ├── test_tokenization_roberta.py ├── test_tokenization_t5.py ├── test_tokenization_transfo_xl.py ├── test_tokenization_utils.py ├── test_tokenization_xlm.py ├── test_tokenization_xlm_roberta.py ├── test_tokenization_xlnet.py ├── test_trainer.py ├── test_trainer_distributed.py └── test_utils_check_copies.py ├── utils ├── check_copies.py ├── check_repo.py ├── download_glue_data.py └── link_tester.py └── valohai.yaml /src/Weights & Biases.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/src/Weights & Biases.pdf -------------------------------------------------------------------------------- /src/composit/.ipynb_checkpoints/test_results-checkpoint.txt: -------------------------------------------------------------------------------- 1 | bs: 3.000000 2 | loss: 167.933685 3 | src_pad_frac: 0.025157 4 | src_pad_tok: 12.000000 5 | step_count: 13.000000 6 | test_avg_gen_len: 31.329268 7 | test_avg_gen_time: 0.312038 8 | test_avg_loss: 156.182098 9 | test_avg_rouge-1: 46.712563 10 | test_avg_rouge-2: 22.947288 11 | test_avg_rouge-l: 45.301813 12 | test_loss: 156.182098 13 | tpb: 545.000000 14 | val_avg_gen_len: 31.995110 15 | val_avg_gen_time: 0.287093 16 | val_avg_loss: 160.214417 17 | val_avg_rouge-1: 47.042550 18 | val_avg_rouge-2: 24.202754 19 | val_avg_rouge-l: 46.366539 20 | val_loss: 160.214417 21 | -------------------------------------------------------------------------------- /src/composit/hparams.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/src/composit/hparams.pkl -------------------------------------------------------------------------------- /src/composit/test_results.txt: -------------------------------------------------------------------------------- 1 | bs: 3.000000 2 | loss: 167.933685 3 | src_pad_frac: 0.025157 4 | src_pad_tok: 12.000000 5 | step_count: 13.000000 6 | test_avg_gen_len: 31.329268 7 | test_avg_gen_time: 0.312038 8 | test_avg_loss: 156.182098 9 | test_avg_rouge-1: 46.712563 10 | test_avg_rouge-2: 22.947288 11 | test_avg_rouge-l: 45.301813 12 | test_loss: 156.182098 13 | tpb: 545.000000 14 | val_avg_gen_len: 31.995110 15 | val_avg_gen_time: 0.287093 16 | val_avg_loss: 160.214417 17 | val_avg_rouge-1: 47.042550 18 | val_avg_rouge-2: 24.202754 19 | val_avg_rouge-l: 46.366539 20 | val_loss: 160.214417 21 | -------------------------------------------------------------------------------- /src/train_base.sh: -------------------------------------------------------------------------------- 1 | CUDA_VISIBLE_DEVICES=0 python train.py \ 2 | --data_dir ./data \ 3 | --learning_rate=3e-5 \ 4 | --gpus 1 \ 5 | --do_train \ 6 | --do_predict \ 7 | --check_val_every_n_epoch 1 \ 8 | --early_stopping_patience 5 \ 9 | --max_source_length 800 \ 10 | --task summarization \ 11 | --label_smoothing 0.1 \ 12 | --model_name_or_path facebook/bart-base \ 13 | --config_name bart_config_10_7.json \ 14 | --cache_dir ./cache \ 15 | --output_dir ./baseline \ 16 | --lr_scheduler polynomial \ 17 | --weight_decay 0.01 --warmup_steps 120 --num_train_epochs 20 \ 18 | --max_grad_norm 0.1 \ 19 | --dropout 0.1 --attention_dropout 0.1 \ 20 | --train_batch_size 1 \ 21 | --eval_batch_size 2 \ 22 | --gradient_accumulation_steps 32 \ 23 | --sortish_sampler \ 24 | --seed 42 \ 25 | --val_metric loss \ 26 | --logger_name wandb \ 27 | "$@" -------------------------------------------------------------------------------- /transformers/.coveragerc: -------------------------------------------------------------------------------- 1 | [run] 2 | source=transformers 3 | omit = 4 | # skip convertion scripts from testing for now 5 | */convert_* 6 | */__main__.py 7 | [report] 8 | exclude_lines = 9 | pragma: no cover 10 | raise 11 | except 12 | register_parameter -------------------------------------------------------------------------------- /transformers/MANIFEST.in: -------------------------------------------------------------------------------- 1 | include LICENSE 2 | -------------------------------------------------------------------------------- /transformers/docker/transformers-cpu/Dockerfile: -------------------------------------------------------------------------------- 1 | FROM ubuntu:18.04 2 | LABEL maintainer="Hugging Face" 3 | LABEL repository="transformers" 4 | 5 | RUN apt update && \ 6 | apt install -y bash \ 7 | build-essential \ 8 | git \ 9 | curl \ 10 | ca-certificates \ 11 | python3 \ 12 | python3-pip && \ 13 | rm -rf /var/lib/apt/lists 14 | 15 | RUN python3 -m pip install --no-cache-dir --upgrade pip && \ 16 | python3 -m pip install --no-cache-dir \ 17 | jupyter \ 18 | tensorflow-cpu \ 19 | torch 20 | 21 | WORKDIR /workspace 22 | COPY . transformers/ 23 | RUN cd transformers/ && \ 24 | python3 -m pip install --no-cache-dir . 25 | 26 | CMD ["/bin/bash"] -------------------------------------------------------------------------------- /transformers/docker/transformers-gpu/Dockerfile: -------------------------------------------------------------------------------- 1 | FROM nvidia/cuda:10.1-cudnn7-runtime-ubuntu18.04 2 | LABEL maintainer="Hugging Face" 3 | LABEL repository="transformers" 4 | 5 | RUN apt update && \ 6 | apt install -y bash \ 7 | build-essential \ 8 | git \ 9 | curl \ 10 | ca-certificates \ 11 | python3 \ 12 | python3-pip && \ 13 | rm -rf /var/lib/apt/lists 14 | 15 | RUN python3 -m pip install --no-cache-dir --upgrade pip && \ 16 | python3 -m pip install --no-cache-dir \ 17 | jupyter \ 18 | tensorflow \ 19 | torch 20 | 21 | WORKDIR /workspace 22 | COPY . transformers/ 23 | RUN cd transformers/ && \ 24 | python3 -m pip install --no-cache-dir . 25 | 26 | CMD ["/bin/bash"] -------------------------------------------------------------------------------- /transformers/docker/transformers-pytorch-cpu/Dockerfile: -------------------------------------------------------------------------------- 1 | FROM ubuntu:18.04 2 | LABEL maintainer="Hugging Face" 3 | LABEL repository="transformers" 4 | 5 | RUN apt update && \ 6 | apt install -y bash \ 7 | build-essential \ 8 | git \ 9 | curl \ 10 | ca-certificates \ 11 | python3 \ 12 | python3-pip && \ 13 | rm -rf /var/lib/apt/lists 14 | 15 | RUN python3 -m pip install --no-cache-dir --upgrade pip && \ 16 | python3 -m pip install --no-cache-dir \ 17 | jupyter \ 18 | torch 19 | 20 | WORKDIR /workspace 21 | COPY . transformers/ 22 | RUN cd transformers/ && \ 23 | python3 -m pip install --no-cache-dir . 24 | 25 | CMD ["/bin/bash"] -------------------------------------------------------------------------------- /transformers/docker/transformers-pytorch-gpu/Dockerfile: -------------------------------------------------------------------------------- 1 | FROM nvidia/cuda:10.1-cudnn7-runtime-ubuntu18.04 2 | LABEL maintainer="Hugging Face" 3 | LABEL repository="transformers" 4 | 5 | RUN apt update && \ 6 | apt install -y bash \ 7 | build-essential \ 8 | git \ 9 | curl \ 10 | ca-certificates \ 11 | python3 \ 12 | python3-pip && \ 13 | rm -rf /var/lib/apt/lists 14 | 15 | RUN python3 -m pip install --no-cache-dir --upgrade pip && \ 16 | python3 -m pip install --no-cache-dir \ 17 | mkl \ 18 | torch 19 | 20 | WORKDIR /workspace 21 | COPY . transformers/ 22 | RUN cd transformers/ && \ 23 | python3 -m pip install --no-cache-dir . 24 | 25 | CMD ["/bin/bash"] -------------------------------------------------------------------------------- /transformers/docker/transformers-pytorch-tpu/dataset.yaml: -------------------------------------------------------------------------------- 1 | apiVersion: v1 2 | kind: PersistentVolume 3 | metadata: 4 | name: huggingface-cluster-disk 5 | spec: 6 | storageClassName: "" 7 | capacity: 8 | storage: 500Gi 9 | accessModes: 10 | - ReadOnlyMany 11 | claimRef: 12 | namespace: default 13 | name: huggingface-cluster-disk-claim 14 | gcePersistentDisk: 15 | pdName: huggingface-cluster-disk 16 | fsType: ext4 17 | readOnly: true 18 | --- 19 | apiVersion: v1 20 | kind: PersistentVolumeClaim 21 | metadata: 22 | name: huggingface-cluster-disk-claim 23 | spec: 24 | # Specify "" as the storageClassName so it matches the PersistentVolume's StorageClass. 25 | # A nil storageClassName value uses the default StorageClass. For details, see 26 | # https://kubernetes.io/docs/concepts/storage/persistent-volumes/#class-1 27 | storageClassName: "" 28 | accessModes: 29 | - ReadOnlyMany 30 | resources: 31 | requests: 32 | storage: 1Ki 33 | -------------------------------------------------------------------------------- /transformers/docker/transformers-pytorch-tpu/docker-entrypoint.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | source ~/.bashrc 3 | echo "running docker-entrypoint.sh" 4 | conda activate container 5 | echo $KUBE_GOOGLE_CLOUD_TPU_ENDPOINTS 6 | echo "printed TPU info" 7 | export XRT_TPU_CONFIG="tpu_worker;0;${KUBE_GOOGLE_CLOUD_TPU_ENDPOINTS:7}" 8 | exec "$@"#!/bin/bash 9 | -------------------------------------------------------------------------------- /transformers/docker/transformers-tensorflow-cpu/Dockerfile: -------------------------------------------------------------------------------- 1 | FROM ubuntu:18.04 2 | LABEL maintainer="Hugging Face" 3 | LABEL repository="transformers" 4 | 5 | RUN apt update && \ 6 | apt install -y bash \ 7 | build-essential \ 8 | git \ 9 | curl \ 10 | ca-certificates \ 11 | python3 \ 12 | python3-pip && \ 13 | rm -rf /var/lib/apt/lists 14 | 15 | RUN python3 -m pip install --no-cache-dir --upgrade pip && \ 16 | python3 -m pip install --no-cache-dir \ 17 | mkl \ 18 | tensorflow-cpu 19 | 20 | WORKDIR /workspace 21 | COPY . transformers/ 22 | RUN cd transformers/ && \ 23 | python3 -m pip install --no-cache-dir . 24 | 25 | CMD ["/bin/bash"] -------------------------------------------------------------------------------- /transformers/docker/transformers-tensorflow-gpu/Dockerfile: -------------------------------------------------------------------------------- 1 | FROM nvidia/cuda:10.1-cudnn7-runtime-ubuntu18.04 2 | LABEL maintainer="Hugging Face" 3 | LABEL repository="transformers" 4 | 5 | RUN apt update && \ 6 | apt install -y bash \ 7 | build-essential \ 8 | git \ 9 | curl \ 10 | ca-certificates \ 11 | python3 \ 12 | python3-pip && \ 13 | rm -rf /var/lib/apt/lists 14 | 15 | RUN python3 -m pip install --no-cache-dir --upgrade pip && \ 16 | python3 -m pip install --no-cache-dir \ 17 | mkl \ 18 | tensorflow 19 | 20 | WORKDIR /workspace 21 | COPY . transformers/ 22 | RUN cd transformers/ && \ 23 | python3 -m pip install --no-cache-dir . 24 | 25 | CMD ["/bin/bash"] -------------------------------------------------------------------------------- /transformers/docs/Makefile: -------------------------------------------------------------------------------- 1 | # Minimal makefile for Sphinx documentation 2 | # 3 | 4 | # You can set these variables from the command line. 5 | SPHINXOPTS = 6 | SPHINXBUILD = sphinx-build 7 | SOURCEDIR = source 8 | BUILDDIR = _build 9 | 10 | # Put it first so that "make" without argument is like "make help". 11 | help: 12 | @$(SPHINXBUILD) -M help "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O) 13 | 14 | .PHONY: help Makefile 15 | 16 | # Catch-all target: route all unknown targets to Sphinx using the new 17 | # "make mode" option. $(O) is meant as a shortcut for $(SPHINXOPTS). 18 | %: Makefile 19 | @$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O) -------------------------------------------------------------------------------- /transformers/docs/source/_static/css/Calibre-Light.ttf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/docs/source/_static/css/Calibre-Light.ttf -------------------------------------------------------------------------------- /transformers/docs/source/_static/css/Calibre-Medium.otf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/docs/source/_static/css/Calibre-Medium.otf -------------------------------------------------------------------------------- /transformers/docs/source/_static/css/Calibre-Regular.otf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/docs/source/_static/css/Calibre-Regular.otf -------------------------------------------------------------------------------- /transformers/docs/source/_static/css/Calibre-Thin.otf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/docs/source/_static/css/Calibre-Thin.otf -------------------------------------------------------------------------------- /transformers/docs/source/_static/css/code-snippets.css: -------------------------------------------------------------------------------- 1 | 2 | .highlight .c1, .highlight .sd{ 3 | color: #999 4 | } 5 | 6 | .highlight .nn, .highlight .k, .highlight .s1, .highlight .nb, .highlight .bp, .highlight .kc { 7 | color: #FB8D68; 8 | } 9 | 10 | .highlight .kn, .highlight .nv, .highlight .s2, .highlight .ow { 11 | color: #6670FF; 12 | } 13 | 14 | .highlight .gp { 15 | color: #FB8D68; 16 | } -------------------------------------------------------------------------------- /transformers/docs/source/favicon.ico: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/docs/source/favicon.ico -------------------------------------------------------------------------------- /transformers/docs/source/imgs/local_attention_mask.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/docs/source/imgs/local_attention_mask.png -------------------------------------------------------------------------------- /transformers/docs/source/imgs/ppl_chunked.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/docs/source/imgs/ppl_chunked.gif -------------------------------------------------------------------------------- /transformers/docs/source/imgs/ppl_full.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/docs/source/imgs/ppl_full.gif -------------------------------------------------------------------------------- /transformers/docs/source/imgs/ppl_sliding.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/docs/source/imgs/ppl_sliding.gif -------------------------------------------------------------------------------- /transformers/docs/source/imgs/transformers_logo_name.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/docs/source/imgs/transformers_logo_name.png -------------------------------------------------------------------------------- /transformers/docs/source/imgs/warmup_constant_schedule.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/docs/source/imgs/warmup_constant_schedule.png -------------------------------------------------------------------------------- /transformers/docs/source/imgs/warmup_cosine_hard_restarts_schedule.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/docs/source/imgs/warmup_cosine_hard_restarts_schedule.png -------------------------------------------------------------------------------- /transformers/docs/source/imgs/warmup_cosine_schedule.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/docs/source/imgs/warmup_cosine_schedule.png -------------------------------------------------------------------------------- /transformers/docs/source/imgs/warmup_cosine_warm_restarts_schedule.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/docs/source/imgs/warmup_cosine_warm_restarts_schedule.png -------------------------------------------------------------------------------- /transformers/docs/source/imgs/warmup_linear_schedule.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/docs/source/imgs/warmup_linear_schedule.png -------------------------------------------------------------------------------- /transformers/docs/source/main_classes/configuration.rst: -------------------------------------------------------------------------------- 1 | Configuration 2 | ----------------------------------------------------------------------------------------------------------------------- 3 | 4 | The base class :class:`~transformers.PretrainedConfig` implements the common methods for loading/saving a configuration 5 | either from a local file or directory, or from a pretrained model configuration provided by the library (downloaded 6 | from HuggingFace's AWS S3 repository). 7 | 8 | 9 | PretrainedConfig 10 | ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 11 | 12 | .. autoclass:: transformers.PretrainedConfig 13 | :members: 14 | -------------------------------------------------------------------------------- /transformers/examples/bert-loses-patience/pabee/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/examples/bert-loses-patience/pabee/__init__.py -------------------------------------------------------------------------------- /transformers/examples/conftest.py: -------------------------------------------------------------------------------- 1 | # tests directory-specific settings - this file is run automatically 2 | # by pytest before any tests are run 3 | 4 | import sys 5 | from os.path import abspath, dirname, join 6 | 7 | 8 | # allow having multiple repository checkouts and not needing to remember to rerun 9 | # 'pip install -e .[dev]' when switching between checkouts and running tests. 10 | git_repo_path = abspath(join(dirname(dirname(__file__)), "src")) 11 | sys.path.insert(1, git_repo_path) 12 | -------------------------------------------------------------------------------- /transformers/examples/contrib/README.md: -------------------------------------------------------------------------------- 1 | # Community contributed examples 2 | 3 | This folder contains examples which are not actively maintained (mostly contributed by the community). 4 | 5 | Using these examples together with a recent version of the library usually requires to make small (sometimes big) adaptations to get the scripts working. 6 | -------------------------------------------------------------------------------- /transformers/examples/contrib/mm-imdb/README.md: -------------------------------------------------------------------------------- 1 | ## MM-IMDb 2 | 3 | Based on the script [`run_mmimdb.py`](https://github.com/huggingface/transformers/blob/master/examples/contrib/mm-imdb/run_mmimdb.py). 4 | 5 | [MM-IMDb](http://lisi1.unal.edu.co/mmimdb/) is a Multimodal dataset with around 26,000 movies including images, plots and other metadata. 6 | 7 | ### Training on MM-IMDb 8 | 9 | ``` 10 | python run_mmimdb.py \ 11 | --data_dir /path/to/mmimdb/dataset/ \ 12 | --model_type bert \ 13 | --model_name_or_path bert-base-uncased \ 14 | --output_dir /path/to/save/dir/ \ 15 | --do_train \ 16 | --do_eval \ 17 | --max_seq_len 512 \ 18 | --gradient_accumulation_steps 20 \ 19 | --num_image_embeds 3 \ 20 | --num_train_epochs 100 \ 21 | --patience 5 22 | ``` 23 | 24 | -------------------------------------------------------------------------------- /transformers/examples/deebert/entropy_eval.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | export CUDA_VISIBLE_DEVICES=0 3 | 4 | PATH_TO_DATA=/h/xinji/projects/GLUE 5 | 6 | MODEL_TYPE=bert # bert or roberta 7 | MODEL_SIZE=base # base or large 8 | DATASET=MRPC # SST-2, MRPC, RTE, QNLI, QQP, or MNLI 9 | 10 | MODEL_NAME=${MODEL_TYPE}-${MODEL_SIZE} 11 | if [ $MODEL_TYPE = 'bert' ] 12 | then 13 | MODEL_NAME=${MODEL_NAME}-uncased 14 | fi 15 | 16 | ENTROPIES="0 0.1 0.2 0.3 0.4 0.5 0.6 0.7" 17 | 18 | for ENTROPY in $ENTROPIES; do 19 | python -u run_glue_deebert.py \ 20 | --model_type $MODEL_TYPE \ 21 | --model_name_or_path ./saved_models/${MODEL_TYPE}-${MODEL_SIZE}/$DATASET/two_stage \ 22 | --task_name $DATASET \ 23 | --do_eval \ 24 | --do_lower_case \ 25 | --data_dir $PATH_TO_DATA/$DATASET \ 26 | --output_dir ./saved_models/${MODEL_TYPE}-${MODEL_SIZE}/$DATASET/two_stage \ 27 | --plot_data_dir ./results/ \ 28 | --max_seq_length 128 \ 29 | --early_exit_entropy $ENTROPY \ 30 | --eval_highway \ 31 | --overwrite_cache \ 32 | --per_gpu_eval_batch_size=1 33 | done 34 | -------------------------------------------------------------------------------- /transformers/examples/deebert/eval_deebert.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | export CUDA_VISIBLE_DEVICES=0 3 | 4 | PATH_TO_DATA=/h/xinji/projects/GLUE 5 | 6 | MODEL_TYPE=bert # bert or roberta 7 | MODEL_SIZE=base # base or large 8 | DATASET=MRPC # SST-2, MRPC, RTE, QNLI, QQP, or MNLI 9 | 10 | MODEL_NAME=${MODEL_TYPE}-${MODEL_SIZE} 11 | if [ $MODEL_TYPE = 'bert' ] 12 | then 13 | MODEL_NAME=${MODEL_NAME}-uncased 14 | fi 15 | 16 | 17 | python -u run_glue_deebert.py \ 18 | --model_type $MODEL_TYPE \ 19 | --model_name_or_path ./saved_models/${MODEL_TYPE}-${MODEL_SIZE}/$DATASET/two_stage \ 20 | --task_name $DATASET \ 21 | --do_eval \ 22 | --do_lower_case \ 23 | --data_dir $PATH_TO_DATA/$DATASET \ 24 | --output_dir ./saved_models/${MODEL_TYPE}-${MODEL_SIZE}/$DATASET/two_stage \ 25 | --plot_data_dir ./results/ \ 26 | --max_seq_length 128 \ 27 | --eval_each_highway \ 28 | --eval_highway \ 29 | --overwrite_cache \ 30 | --per_gpu_eval_batch_size=1 31 | -------------------------------------------------------------------------------- /transformers/examples/deebert/src/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/examples/deebert/src/__init__.py -------------------------------------------------------------------------------- /transformers/examples/distillation/requirements.txt: -------------------------------------------------------------------------------- 1 | transformers 2 | 3 | gitpython==3.0.2 4 | tensorboard>=1.14.0 5 | tensorboardX==1.8 6 | psutil==5.6.6 7 | scipy==1.3.1 8 | -------------------------------------------------------------------------------- /transformers/examples/distillation/training_configs/distilbert-base-cased.json: -------------------------------------------------------------------------------- 1 | { 2 | "activation": "gelu", 3 | "attention_dropout": 0.1, 4 | "dim": 768, 5 | "dropout": 0.1, 6 | "hidden_dim": 3072, 7 | "initializer_range": 0.02, 8 | "max_position_embeddings": 512, 9 | "n_heads": 12, 10 | "n_layers": 6, 11 | "sinusoidal_pos_embds": true, 12 | "tie_weights_": true, 13 | "vocab_size": 28996 14 | } 15 | -------------------------------------------------------------------------------- /transformers/examples/distillation/training_configs/distilbert-base-multilingual-cased.json: -------------------------------------------------------------------------------- 1 | { 2 | "activation": "gelu", 3 | "attention_dropout": 0.1, 4 | "dim": 768, 5 | "dropout": 0.1, 6 | "hidden_dim": 3072, 7 | "initializer_range": 0.02, 8 | "max_position_embeddings": 512, 9 | "n_heads": 12, 10 | "n_layers": 6, 11 | "sinusoidal_pos_embds": true, 12 | "tie_weights_": true, 13 | "vocab_size": 119547 14 | } 15 | -------------------------------------------------------------------------------- /transformers/examples/distillation/training_configs/distilbert-base-uncased.json: -------------------------------------------------------------------------------- 1 | { 2 | "activation": "gelu", 3 | "attention_dropout": 0.1, 4 | "dim": 768, 5 | "dropout": 0.1, 6 | "hidden_dim": 3072, 7 | "initializer_range": 0.02, 8 | "max_position_embeddings": 512, 9 | "n_heads": 12, 10 | "n_layers": 6, 11 | "sinusoidal_pos_embds": true, 12 | "tie_weights_": true, 13 | "vocab_size": 30522 14 | } 15 | -------------------------------------------------------------------------------- /transformers/examples/distillation/training_configs/distilgpt2.json: -------------------------------------------------------------------------------- 1 | { 2 | "initializer_range": 0.02, 3 | "layer_norm_epsilon": 0.00001, 4 | "n_ctx": 1024, 5 | "n_embd": 768, 6 | "n_head": 12, 7 | "n_layer": 6, 8 | "n_positions": 1024, 9 | "vocab_size": 50257 10 | } -------------------------------------------------------------------------------- /transformers/examples/distillation/training_configs/distilroberta-base.json: -------------------------------------------------------------------------------- 1 | { 2 | "vocab_size": 50265, 3 | "hidden_size": 768, 4 | "num_hidden_layers": 6, 5 | "num_attention_heads": 12, 6 | "intermediate_size": 3072, 7 | "hidden_act": "gelu", 8 | "hidden_dropout_prob": 0.1, 9 | "attention_probs_dropout_prob": 0.1, 10 | "max_position_embeddings": 514, 11 | "type_vocab_size": 1, 12 | "initializer_range": 0.02, 13 | "layer_norm_eps": 0.00001 14 | } -------------------------------------------------------------------------------- /transformers/examples/longform-qa/README.md: -------------------------------------------------------------------------------- 1 | # Long Form Question Answering 2 | 3 | This folder contains the code for the Long Form Question answering [demo](http://35.226.96.115:8080/) as well as methods to train and use a fully end-to-end Long Form Question Answering system using the [🤗transformers](https://github.com/huggingface/transformers) and [🤗datasets](https://github.com/huggingface/datasets) libraries. 4 | 5 | You can use these methods to train your own system by following along the associate [notebook](https://github.com/huggingface/notebooks/blob/master/longform-qa/Long_Form_Question_Answering_with_ELI5_and_Wikipedia.ipynb) or [blog post](https://yjernite.github.io/lfqa.html). 6 | -------------------------------------------------------------------------------- /transformers/examples/lxmert/README.md: -------------------------------------------------------------------------------- 1 | # LXMERT DEMO 2 | 3 | 1. make a virtualenv: ``virtualenv venv`` and activate ``source venv/bin/activate`` 4 | 2. install reqs: ``pip install -r ./requirements.txt`` 5 | 3. usage is as shown in demo.ipynb 6 | -------------------------------------------------------------------------------- /transformers/examples/movement-pruning/emmental/__init__.py: -------------------------------------------------------------------------------- 1 | # flake8: noqa 2 | from .configuration_bert_masked import MaskedBertConfig 3 | from .modeling_bert_masked import ( 4 | MaskedBertForMultipleChoice, 5 | MaskedBertForQuestionAnswering, 6 | MaskedBertForSequenceClassification, 7 | MaskedBertForTokenClassification, 8 | MaskedBertModel, 9 | ) 10 | from .modules import * 11 | -------------------------------------------------------------------------------- /transformers/examples/movement-pruning/emmental/modules/__init__.py: -------------------------------------------------------------------------------- 1 | # flake8: noqa 2 | from .binarizer import MagnitudeBinarizer, ThresholdBinarizer, TopKBinarizer 3 | from .masked_nn import MaskedLinear 4 | -------------------------------------------------------------------------------- /transformers/examples/movement-pruning/requirements.txt: -------------------------------------------------------------------------------- 1 | torch>=1.4.0 2 | -e git+https://github.com/huggingface/transformers.git@352d5472b0c1dec0f420d606d16747d851b4bda8#egg=transformers 3 | knockknock>=0.1.8.1 4 | h5py>=2.10.0 5 | numpy>=1.18.2 6 | scipy>=1.4.1 7 | -------------------------------------------------------------------------------- /transformers/examples/rag/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/examples/rag/__init__.py -------------------------------------------------------------------------------- /transformers/examples/rag/requirements.txt: -------------------------------------------------------------------------------- 1 | faiss-cpu >= 1.6.3 2 | datasets >= 1.0.1 3 | psutil >= 5.7.0 4 | torch >= 1.4.0 -------------------------------------------------------------------------------- /transformers/examples/requirements.txt: -------------------------------------------------------------------------------- 1 | tensorboard 2 | scikit-learn 3 | seqeval 4 | psutil 5 | sacrebleu 6 | rouge-score 7 | tensorflow_datasets 8 | pytorch-lightning==0.8.5 9 | matplotlib 10 | git-python==1.0.3 11 | faiss-cpu 12 | streamlit 13 | elasticsearch 14 | pandas 15 | datasets 16 | fire 17 | pytest 18 | conllu 19 | -------------------------------------------------------------------------------- /transformers/examples/seq2seq/__init__.py: -------------------------------------------------------------------------------- 1 | import os 2 | import sys 3 | 4 | 5 | sys.path.insert(1, os.path.dirname(os.path.realpath(__file__))) 6 | -------------------------------------------------------------------------------- /transformers/examples/seq2seq/bertabs/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/examples/seq2seq/bertabs/__init__.py -------------------------------------------------------------------------------- /transformers/examples/seq2seq/bertabs/requirements.txt: -------------------------------------------------------------------------------- 1 | transformers 2 | 3 | # For ROUGE 4 | nltk 5 | py-rouge 6 | -------------------------------------------------------------------------------- /transformers/examples/seq2seq/builtin_trainer/finetune.sh: -------------------------------------------------------------------------------- 1 | # the proper usage is documented in the README, you need to specify data_dir, output_dir and model_name_or_path 2 | # run ./builtin_trainer/finetune.sh --help to see all the possible options 3 | python finetune_trainer.py \ 4 | --learning_rate=3e-5 \ 5 | --fp16 \ 6 | --do_train --do_eval --do_predict --evaluate_during_training \ 7 | --predict_with_generate \ 8 | --n_val 1000 \ 9 | "$@" 10 | -------------------------------------------------------------------------------- /transformers/examples/seq2seq/builtin_trainer/finetune_tpu.sh: -------------------------------------------------------------------------------- 1 | export TPU_NUM_CORES=8 2 | 3 | # the proper usage is documented in the README, you need to specify data_dir, output_dir and model_name_or_path 4 | # run ./builtin_trainer/finetune_tpu.sh --help to see all the possible options 5 | python xla_spawn.py --num_cores $TPU_NUM_CORES \ 6 | finetune_trainer.py \ 7 | --learning_rate=3e-5 \ 8 | --do_train --do_eval --evaluate_during_training \ 9 | --prediction_loss_only \ 10 | --n_val 1000 \ 11 | "$@" 12 | -------------------------------------------------------------------------------- /transformers/examples/seq2seq/builtin_trainer/train_mbart_cc25_enro.sh: -------------------------------------------------------------------------------- 1 | python finetune_trainer.py \ 2 | --model_name_or_path=facebook/mbart-large-cc25 \ 3 | --data_dir $ENRO_DIR \ 4 | --output_dir mbart_cc25_enro --overwrite_output_dir \ 5 | --learning_rate=3e-5 \ 6 | --warmup_steps 500 \ 7 | --fp16 \ 8 | --label_smoothing 0.1 \ 9 | --adam_eps 1e-06 \ 10 | --src_lang en_XX --tgt_lang ro_RO \ 11 | --freeze_embeds \ 12 | --per_device_train_batch_size=4 --per_device_eval_batch_size=4 \ 13 | --max_source_length 128 --max_target_length 128 \ 14 | --val_max_target_length 128 --test_max_target_length 128 \ 15 | --sortish_sampler \ 16 | --num_train_epochs 6 \ 17 | --save_steps 25000 --eval_steps 25000 --logging_steps 1000 \ 18 | --do_train --do_eval --do_predict --evaluate_during_training \ 19 | --predict_with_generate --logging_first_step 20 | --task translation \ 21 | --run_name mbart_en_ro \ 22 | "$@" 23 | -------------------------------------------------------------------------------- /transformers/examples/seq2seq/convert_model_to_fp16.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | 3 | from typing import Union 4 | 5 | import fire 6 | import torch 7 | from tqdm import tqdm 8 | 9 | 10 | def convert(src_path: str, map_location: str = "cpu", save_path: Union[str, None] = None) -> None: 11 | """Convert a pytorch_model.bin or model.pt file to torch.float16 for faster downloads, less disk space.""" 12 | state_dict = torch.load(src_path, map_location=map_location) 13 | for k, v in tqdm(state_dict.items()): 14 | if not isinstance(v, torch.Tensor): 15 | raise TypeError("FP16 conversion only works on paths that are saved state dics, like pytorch_model.bin") 16 | state_dict[k] = v.half() 17 | if save_path is None: # overwrite src_path 18 | save_path = src_path 19 | torch.save(state_dict, save_path) 20 | 21 | 22 | if __name__ == "__main__": 23 | fire.Fire(convert) 24 | -------------------------------------------------------------------------------- /transformers/examples/seq2seq/distil_marian_enro_teacher.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env bash 2 | export PYTHONPATH="../":"${PYTHONPATH}" 3 | export WANDB_PROJECT=dmar 4 | # export MAX_LEN=128 5 | python distillation.py \ 6 | --learning_rate=3e-4 \ 7 | --do_train \ 8 | --fp16 \ 9 | --val_check_interval 0.25 \ 10 | --teacher Helsinki-NLP/opus-mt-en-ro \ 11 | --max_source_length $MAX_LEN --max_target_length $MAX_LEN --val_max_target_length $MAX_LEN --test_max_target_length $MAX_LEN \ 12 | --student_decoder_layers 3 --student_encoder_layers 6 \ 13 | --freeze_encoder --freeze_embeds \ 14 | --model_name_or_path IGNORED \ 15 | --alpha_hid=3. \ 16 | --train_batch_size=$BS --eval_batch_size=$BS \ 17 | --tokenizer_name Helsinki-NLP/opus-mt-en-ro \ 18 | --warmup_steps 500 --logger_name wandb \ 19 | --fp16_opt_level O1 --task translation --normalize_hidden --num_sanity_val_steps=0 \ 20 | "$@" 21 | -------------------------------------------------------------------------------- /transformers/examples/seq2seq/distil_marian_no_teacher.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env bash 2 | export PYTHONPATH="../":"${PYTHONPATH}" 3 | export WANDB_PROJECT=dmar 4 | python distillation.py \ 5 | --learning_rate=3e-4 \ 6 | --do_train \ 7 | --do_predict \ 8 | --fp16 --no_teacher \ 9 | --val_check_interval 0.25 \ 10 | --data_dir $ENRO_DIR \ 11 | --max_source_length $MAX_LEN --max_target_length $MAX_LEN --val_max_target_length $MAX_LEN --test_max_target_length $MAX_LEN \ 12 | --freeze_encoder --freeze_embeds \ 13 | --train_batch_size=$BS --eval_batch_size=$BS \ 14 | --tokenizer_name $m --model_name_or_path $m \ 15 | --warmup_steps 500 --sortish_sampler --logger_name wandb \ 16 | --gpus 1 --fp16_opt_level=O1 --task translation --num_sanity_val_steps=0 \ 17 | "$@" 18 | -------------------------------------------------------------------------------- /transformers/examples/seq2seq/dynamic_bs_example.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env bash 2 | export PYTHONPATH="../":"${PYTHONPATH}" 3 | export WANDB_PROJECT=dmar 4 | export MAX_LEN=128 5 | export m=sshleifer/student_marian_en_ro_6_1 6 | python finetune.py \ 7 | --learning_rate=3e-4 \ 8 | --do_train \ 9 | --fp16 \ 10 | --data_dir wmt_en_ro \ 11 | --max_source_length $MAX_LEN --max_target_length $MAX_LEN --val_max_target_length $MAX_LEN --test_max_target_length $MAX_LEN \ 12 | --freeze_encoder --freeze_embeds \ 13 | --train_batch_size=48 --eval_batch_size=64 \ 14 | --tokenizer_name $m --model_name_or_path $m --num_train_epochs=1 \ 15 | --warmup_steps 500 --logger_name wandb --gpus 1 \ 16 | --fp16_opt_level=O1 --task translation \ 17 | "$@" 18 | -------------------------------------------------------------------------------- /transformers/examples/seq2seq/finetune.sh: -------------------------------------------------------------------------------- 1 | # the proper usage is documented in the README, you need to specify data_dir, output_dir and model_name_or_path 2 | # run ./finetune.sh --help to see all the possible options 3 | python finetune.py \ 4 | --learning_rate=3e-5 \ 5 | --fp16 \ 6 | --gpus 1 \ 7 | --do_train \ 8 | --do_predict \ 9 | --n_val 1000 \ 10 | --val_check_interval 0.1 \ 11 | "$@" 12 | -------------------------------------------------------------------------------- /transformers/examples/seq2seq/finetune_bart_tiny.sh: -------------------------------------------------------------------------------- 1 | # Script for verifying that run_bart_sum can be invoked from its directory 2 | 3 | # Get tiny dataset with cnn_dm format (4 examples for train, val, test) 4 | wget https://s3.amazonaws.com/datasets.huggingface.co/summarization/cnn_tiny.tgz 5 | tar -xzvf cnn_tiny.tgz 6 | rm cnn_tiny.tgz 7 | 8 | export OUTPUT_DIR_NAME=bart_utest_output 9 | export CURRENT_DIR=${PWD} 10 | export OUTPUT_DIR=${CURRENT_DIR}/${OUTPUT_DIR_NAME} 11 | 12 | # Make output directory if it doesn't exist 13 | mkdir -p $OUTPUT_DIR 14 | 15 | # Add parent directory to python path to access lightning_base.py and testing_utils.py 16 | export PYTHONPATH="../":"${PYTHONPATH}" 17 | python finetune.py \ 18 | --data_dir=cnn_tiny/ \ 19 | --model_name_or_path=sshleifer/bart-tiny-random \ 20 | --learning_rate=3e-5 \ 21 | --train_batch_size=2 \ 22 | --eval_batch_size=2 \ 23 | --output_dir=$OUTPUT_DIR \ 24 | --num_train_epochs=1 \ 25 | --gpus=0 \ 26 | --do_train "$@" 27 | 28 | rm -rf cnn_tiny 29 | rm -rf $OUTPUT_DIR 30 | 31 | 32 | 33 | -------------------------------------------------------------------------------- /transformers/examples/seq2seq/finetune_pegasus_xsum.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env bash 2 | export PYTHONPATH="../":"${PYTHONPATH}" 3 | 4 | # From appendix C of paper https://arxiv.org/abs/1912.08777 5 | # Set --gradient_accumulation_steps so that effective batch size is 256 (2*128, 4*64, 8*32, 16*16) 6 | python finetune.py \ 7 | --learning_rate=1e-4 \ 8 | --do_train \ 9 | --do_predict \ 10 | --n_val 1000 \ 11 | --val_check_interval 0.25 \ 12 | --max_source_length 512 --max_target_length 56 \ 13 | --freeze_embeds --label_smoothing 0.1 --adafactor --task summarization_xsum \ 14 | "$@" 15 | -------------------------------------------------------------------------------- /transformers/examples/seq2seq/finetune_t5.sh: -------------------------------------------------------------------------------- 1 | # Add parent directory to python path to access lightning_base.py 2 | export PYTHONPATH="../":"${PYTHONPATH}" 3 | 4 | python finetune.py \ 5 | --data_dir=$CNN_DIR \ 6 | --learning_rate=3e-5 \ 7 | --train_batch_size=$BS \ 8 | --eval_batch_size=$BS \ 9 | --output_dir=$OUTPUT_DIR \ 10 | --max_source_length=512 \ 11 | --max_target_length=56 \ 12 | --val_check_interval=0.1 --n_val=200 \ 13 | --do_train --do_predict \ 14 | "$@" 15 | -------------------------------------------------------------------------------- /transformers/examples/seq2seq/initialization_utils.py: -------------------------------------------------------------------------------- 1 | from typing import List 2 | 3 | from torch import nn 4 | 5 | 6 | def init_student(student, teacher): 7 | teacher_state_dict = teacher.state_dict() 8 | info = student.load_state_dict(teacher_state_dict, strict=False) 9 | assert info.missing_keys == [], info.missing_keys 10 | return student, info 11 | 12 | 13 | def copy_decoder_layers(teacher, student, l2copy=[0, 2, 4, 7, 9, 11]): 14 | copy_layers(teacher.model.decoder.layers, student.model.decoder.layers, l2copy) 15 | 16 | 17 | def copy_layers(teacher_layers: nn.ModuleList, student_layers: nn.ModuleList, layers_to_copy: List) -> None: 18 | layers_to_copy = nn.ModuleList([l for i, l in enumerate(teacher_layers) if i in layers_to_copy]) 19 | assert len(student_layers) == len(layers_to_copy), f"{len(student_layers)} != {len(layers_to_copy)}" 20 | student_layers.load_state_dict(layers_to_copy.state_dict()) 21 | -------------------------------------------------------------------------------- /transformers/examples/seq2seq/minify_dataset.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | 3 | from pathlib import Path 4 | 5 | import fire 6 | 7 | 8 | def minify(src_dir: str, dest_dir: str, n: int): 9 | """Write first n lines of each file f in src_dir to dest_dir/f """ 10 | src_dir = Path(src_dir) 11 | dest_dir = Path(dest_dir) 12 | dest_dir.mkdir(exist_ok=True) 13 | for path in src_dir.iterdir(): 14 | new = [x.rstrip() for x in list(path.open().readlines())][:n] 15 | dest_path = dest_dir.joinpath(path.name) 16 | print(dest_path) 17 | dest_path.open("w").write("\n".join(new)) 18 | 19 | 20 | if __name__ == "__main__": 21 | fire.Fire(minify) 22 | -------------------------------------------------------------------------------- /transformers/examples/seq2seq/run_distiller.sh: -------------------------------------------------------------------------------- 1 | # Add parent directory to python path to access lightning_base.py 2 | export PYTHONPATH="../":"${PYTHONPATH}" 3 | 4 | python distillation.py \ 5 | --learning_rate=3e-4 \ 6 | --do_train \ 7 | --do_predict \ 8 | --fp16 \ 9 | --val_check_interval 0.1 \ 10 | "$@" 11 | -------------------------------------------------------------------------------- /transformers/examples/seq2seq/test_data/fsmt/build-eval-data.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | 3 | import io 4 | import json 5 | import subprocess 6 | 7 | 8 | pairs = [ 9 | ["en", "ru"], 10 | ["ru", "en"], 11 | ["en", "de"], 12 | ["de", "en"], 13 | ] 14 | 15 | n_objs = 8 16 | 17 | 18 | def get_all_data(pairs, n_objs): 19 | text = {} 20 | for src, tgt in pairs: 21 | pair = f"{src}-{tgt}" 22 | cmd = f"sacrebleu -t wmt19 -l {pair} --echo src".split() 23 | src_lines = subprocess.run(cmd, stdout=subprocess.PIPE).stdout.decode("utf-8").splitlines() 24 | cmd = f"sacrebleu -t wmt19 -l {pair} --echo ref".split() 25 | tgt_lines = subprocess.run(cmd, stdout=subprocess.PIPE).stdout.decode("utf-8").splitlines() 26 | text[pair] = {"src": src_lines[:n_objs], "tgt": tgt_lines[:n_objs]} 27 | return text 28 | 29 | 30 | text = get_all_data(pairs, n_objs) 31 | filename = "./fsmt_val_data.json" 32 | with io.open(filename, "w", encoding="utf-8") as f: 33 | bleu_data = json.dump(text, f, indent=2, ensure_ascii=False) 34 | -------------------------------------------------------------------------------- /transformers/examples/seq2seq/test_data/wmt_en_ro/train.len: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/examples/seq2seq/test_data/wmt_en_ro/train.len -------------------------------------------------------------------------------- /transformers/examples/seq2seq/test_data/wmt_en_ro/val.len: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/examples/seq2seq/test_data/wmt_en_ro/val.len -------------------------------------------------------------------------------- /transformers/examples/seq2seq/train_distilbart_cnn.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env bash 2 | export PYTHONPATH="../":"${PYTHONPATH}" 3 | 4 | export BS=32 5 | export GAS=1 6 | 7 | python finetune.py \ 8 | --learning_rate=3e-5 \ 9 | --fp16 \ 10 | --gpus 1 \ 11 | --do_train \ 12 | --do_predict \ 13 | --val_check_interval 0.25 \ 14 | --n_val 500 \ 15 | --num_train_epochs 2 \ 16 | --freeze_encoder --freeze_embeds --data_dir $CNN_DIR \ 17 | --max_target_length 142 --val_max_target_length=142 \ 18 | --train_batch_size=$BS --eval_batch_size=$BS --gradient_accumulation_steps=$GAS \ 19 | --model_name_or_path sshleifer/student_cnn_12_6 \ 20 | --tokenizer_name facebook/bart-large \ 21 | --warmup_steps 500 \ 22 | --output_dir distilbart-cnn-12-6 \ 23 | "$@" 24 | 25 | -------------------------------------------------------------------------------- /transformers/examples/seq2seq/train_distilbart_xsum.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env bash 2 | export PYTHONPATH="../":"${PYTHONPATH}" 3 | export BS=16 4 | export GAS=2 5 | python distillation.py \ 6 | --learning_rate=3e-4 \ 7 | --do_train \ 8 | --do_predict \ 9 | --fp16 \ 10 | --val_check_interval 0.1 --n_val 1000 \ 11 | --teacher facebook/bart-large-xsum --data_dir $XSUM_DIR \ 12 | --max_target_length=60 --val_max_target_length=60 --test_max_target_length=100 \ 13 | --student_decoder_layers 6 --student_encoder_layers 12 \ 14 | --freeze_encoder --freeze_embeds \ 15 | --model_name_or_path IGNORED \ 16 | --alpha_hid=3. --length_penalty=0.5 \ 17 | --train_batch_size=$BS --eval_batch_size=$BS --gradient_accumulation_steps=$GAS --num_train_epochs=6 \ 18 | --tokenizer_name facebook/bart-large \ 19 | --warmup_steps 500 \ 20 | --output_dir distilbart_xsum_12_6 \ 21 | "$@" 22 | -------------------------------------------------------------------------------- /transformers/examples/seq2seq/train_mbart_cc25_enro.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env bash 2 | export PYTHONPATH="../":"${PYTHONPATH}" 3 | 4 | python finetune.py \ 5 | --learning_rate=3e-5 \ 6 | --fp16 \ 7 | --do_train \ 8 | --val_check_interval=0.25 \ 9 | --adam_eps 1e-06 \ 10 | --num_train_epochs 6 --src_lang en_XX --tgt_lang ro_RO \ 11 | --data_dir $ENRO_DIR \ 12 | --max_source_length $MAX_LEN --max_target_length $MAX_LEN --val_max_target_length $MAX_LEN --test_max_target_length $MAX_LEN \ 13 | --train_batch_size=$BS --eval_batch_size=$BS \ 14 | --task translation \ 15 | --warmup_steps 500 \ 16 | --freeze_embeds \ 17 | --model_name_or_path=facebook/mbart-large-cc25 \ 18 | "$@" 19 | -------------------------------------------------------------------------------- /transformers/examples/text-generation/README.md: -------------------------------------------------------------------------------- 1 | ## Language generation 2 | 3 | Based on the script [`run_generation.py`](https://github.com/huggingface/transformers/blob/master/examples/text-generation/run_generation.py). 4 | 5 | Conditional text generation using the auto-regressive models of the library: GPT, GPT-2, Transformer-XL, XLNet, CTRL. 6 | A similar script is used for our official demo [Write With Transfomer](https://transformer.huggingface.co), where you 7 | can try out the different models available in the library. 8 | 9 | Example usage: 10 | 11 | ```bash 12 | python run_generation.py \ 13 | --model_type=gpt2 \ 14 | --model_name_or_path=gpt2 15 | ``` 16 | -------------------------------------------------------------------------------- /transformers/examples/text-generation/pplm/imgs/headfigure.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/examples/text-generation/pplm/imgs/headfigure.png -------------------------------------------------------------------------------- /transformers/examples/text-generation/pplm/imgs/wooly.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/examples/text-generation/pplm/imgs/wooly.png -------------------------------------------------------------------------------- /transformers/examples/text-generation/pplm/pplm_classification_head.py: -------------------------------------------------------------------------------- 1 | import torch 2 | 3 | 4 | class ClassificationHead(torch.nn.Module): 5 | """Classification Head for transformer encoders""" 6 | 7 | def __init__(self, class_size, embed_size): 8 | super().__init__() 9 | self.class_size = class_size 10 | self.embed_size = embed_size 11 | # self.mlp1 = torch.nn.Linear(embed_size, embed_size) 12 | # self.mlp2 = (torch.nn.Linear(embed_size, class_size)) 13 | self.mlp = torch.nn.Linear(embed_size, class_size) 14 | 15 | def forward(self, hidden_state): 16 | # hidden_state = F.relu(self.mlp1(hidden_state)) 17 | # hidden_state = self.mlp2(hidden_state) 18 | logits = self.mlp(hidden_state) 19 | return logits 20 | -------------------------------------------------------------------------------- /transformers/model_cards/DeepPavlov/bert-base-bg-cs-pl-ru-cased/README.md: -------------------------------------------------------------------------------- 1 | --- 2 | language: 3 | - bg 4 | - cs 5 | - pl 6 | - ru 7 | --- 8 | 9 | # bert-base-bg-cs-pl-ru-cased 10 | 11 | SlavicBERT\[1\] \(Slavic \(bg, cs, pl, ru\), cased, 12‑layer, 768‑hidden, 12‑heads, 180M parameters\) was trained on Russian News and four Wikipedias: Bulgarian, Czech, Polish, and Russian. Subtoken vocabulary was built using this data. Multilingual BERT was used as an initialization for SlavicBERT. 12 | 13 | 14 | \[1\]: Arkhipov M., Trofimova M., Kuratov Y., Sorokin A. \(2019\). [Tuning Multilingual Transformers for Language-Specific Named Entity Recognition](https://www.aclweb.org/anthology/W19-3712/). ACL anthology W19-3712. 15 | -------------------------------------------------------------------------------- /transformers/model_cards/DeepPavlov/rubert-base-cased-conversational/README.md: -------------------------------------------------------------------------------- 1 | --- 2 | language: 3 | - ru 4 | --- 5 | 6 | # rubert-base-cased-conversational 7 | 8 | Conversational RuBERT \(Russian, cased, 12‑layer, 768‑hidden, 12‑heads, 180M parameters\) was trained on OpenSubtitles\[1\], [Dirty](https://d3.ru/), [Pikabu](https://pikabu.ru/), and a Social Media segment of Taiga corpus\[2\]. We assembled a new vocabulary for Conversational RuBERT model on this data and initialized the model with [RuBERT](../rubert-base-cased). 9 | 10 | 11 | \[1\]: P. Lison and J. Tiedemann, 2016, OpenSubtitles2016: Extracting Large Parallel Corpora from Movie and TV Subtitles. In Proceedings of the 10th International Conference on Language Resources and Evaluation \(LREC 2016\) 12 | 13 | \[2\]: Shavrina T., Shapovalova O. \(2017\) TO THE METHODOLOGY OF CORPUS CONSTRUCTION FOR MACHINE LEARNING: «TAIGA» SYNTAX TREE CORPUS AND PARSER. in proc. of “CORPORA2017”, international conference , Saint-Petersbourg, 2017. 14 | -------------------------------------------------------------------------------- /transformers/model_cards/DeepPavlov/rubert-base-cased-sentence/README.md: -------------------------------------------------------------------------------- 1 | --- 2 | language: 3 | - ru 4 | --- 5 | 6 | # rubert-base-cased-sentence 7 | 8 | Sentence RuBERT \(Russian, cased, 12-layer, 768-hidden, 12-heads, 180M parameters\) is a representation‑based sentence encoder for Russian. It is initialized with RuBERT and fine‑tuned on SNLI\[1\] google-translated to russian and on russian part of XNLI dev set\[2\]. Sentence representations are mean pooled token embeddings in the same manner as in Sentence‑BERT\[3\]. 9 | 10 | 11 | \[1\]: S. R. Bowman, G. Angeli, C. Potts, and C. D. Manning. \(2015\) A large annotated corpus for learning natural language inference. arXiv preprint [arXiv:1508.05326](https://arxiv.org/abs/1508.05326) 12 | 13 | \[2\]: Williams A., Bowman S. \(2018\) XNLI: Evaluating Cross-lingual Sentence Representations. arXiv preprint [arXiv:1809.05053](https://arxiv.org/abs/1809.05053) 14 | 15 | \[3\]: N. Reimers, I. Gurevych \(2019\) Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. arXiv preprint [arXiv:1908.10084](https://arxiv.org/abs/1908.10084) 16 | -------------------------------------------------------------------------------- /transformers/model_cards/DeepPavlov/rubert-base-cased/README.md: -------------------------------------------------------------------------------- 1 | --- 2 | language: 3 | - ru 4 | --- 5 | 6 | # rubert-base-cased 7 | 8 | RuBERT \(Russian, cased, 12‑layer, 768‑hidden, 12‑heads, 180M parameters\) was trained on the Russian part of Wikipedia and news data. We used this training data to build a vocabulary of Russian subtokens and took a multilingual version of BERT‑base as an initialization for RuBERT\[1\]. 9 | 10 | 11 | \[1\]: Kuratov, Y., Arkhipov, M. \(2019\). Adaptation of Deep Bidirectional Multilingual Transformers for Russian Language. arXiv preprint [arXiv:1905.07213](https://arxiv.org/abs/1905.07213). 12 | -------------------------------------------------------------------------------- /transformers/model_cards/NeuML/bert-small-cord19-squad2/README.md: -------------------------------------------------------------------------------- 1 | # BERT-Small CORD-19 fine-tuned on SQuAD 2.0 2 | 3 | [bert-small-cord19 model](https://huggingface.co/NeuML/bert-small-cord19) fine-tuned on SQuAD 2.0 4 | 5 | ## Building the model 6 | 7 | ```bash 8 | python run_squad.py 9 | --model_type bert 10 | --model_name_or_path bert-small-cord19 11 | --do_train 12 | --do_eval 13 | --do_lower_case 14 | --version_2_with_negative 15 | --train_file train-v2.0.json 16 | --predict_file dev-v2.0.json 17 | --per_gpu_train_batch_size 8 18 | --learning_rate 3e-5 19 | --num_train_epochs 3.0 20 | --max_seq_length 384 21 | --doc_stride 128 22 | --output_dir bert-small-cord19-squad2 23 | --save_steps 0 24 | --threads 8 25 | --overwrite_cache 26 | --overwrite_output_dir 27 | -------------------------------------------------------------------------------- /transformers/model_cards/NeuML/bert-small-cord19/README.md: -------------------------------------------------------------------------------- 1 | # BERT-Small fine-tuned on CORD-19 dataset 2 | 3 | [BERT L6_H-512_A-8 model](https://huggingface.co/google/bert_uncased_L-6_H-512_A-8) fine-tuned on the [CORD-19 dataset](https://www.semanticscholar.org/cord19). 4 | 5 | ## CORD-19 data subset 6 | The training data for this dataset is stored as a [Kaggle dataset](https://www.kaggle.com/davidmezzetti/cord19-qa?select=cord19.txt). The training 7 | data is a subset of the full corpus, focusing on high-quality, study-design detected articles. 8 | 9 | ## Building the model 10 | 11 | ```bash 12 | python run_language_modeling.py 13 | --model_type bert 14 | --model_name_or_path google/bert_uncased_L-6_H-512_A-8 15 | --do_train 16 | --mlm 17 | --line_by_line 18 | --block_size 512 19 | --train_data_file cord19.txt 20 | --per_gpu_train_batch_size 4 21 | --learning_rate 3e-5 22 | --num_train_epochs 3.0 23 | --output_dir bert-small-cord19 24 | --save_steps 0 25 | --overwrite_output_dir 26 | -------------------------------------------------------------------------------- /transformers/model_cards/VictorSanh/roberta-base-finetuned-yelp-polarity/README.md: -------------------------------------------------------------------------------- 1 | --- 2 | language: en 3 | datasets: 4 | - yelp_polarity 5 | --- 6 | 7 | # RoBERTa-base-finetuned-yelp-polarity 8 | 9 | This is a [RoBERTa-base](https://huggingface.co/roberta-base) checkpoint fine-tuned on binary sentiment classifcation from [Yelp polarity](https://huggingface.co/nlp/viewer/?dataset=yelp_polarity). 10 | It gets **98.08%** accuracy on the test set. 11 | 12 | ## Hyper-parameters 13 | 14 | We used the following hyper-parameters to train the model on one GPU: 15 | ```python 16 | num_train_epochs = 2.0 17 | learning_rate = 1e-05 18 | weight_decay = 0.0 19 | adam_epsilon = 1e-08 20 | max_grad_norm = 1.0 21 | per_device_train_batch_size = 32 22 | gradient_accumulation_steps = 1 23 | warmup_steps = 3500 24 | seed = 42 25 | ``` 26 | -------------------------------------------------------------------------------- /transformers/model_cards/akhooli/mbart-large-cc25-ar-en/README.md: -------------------------------------------------------------------------------- 1 | --- 2 | tags: 3 | - translation 4 | 5 | language: 6 | - ar 7 | - en 8 | 9 | license: mit 10 | --- 11 | ### mbart-large-ar-en 12 | This is mbart-large-cc25, finetuned on a subset of the OPUS corpus for ar_en. 13 | Usage: see [example notebook](https://colab.research.google.com/drive/1I6RFOWMaTpPBX7saJYjnSTddW0TD6H1t?usp=sharing) 14 | Note: model has limited training set, not fully trained (do not use for production). 15 | Other models by me: [Abed Khooli](https://huggingface.co/akhooli) 16 | -------------------------------------------------------------------------------- /transformers/model_cards/akhooli/mbart-large-cc25-en-ar/README.md: -------------------------------------------------------------------------------- 1 | --- 2 | tags: 3 | - translation 4 | 5 | language: 6 | - en 7 | - ar 8 | 9 | license: mit 10 | --- 11 | ### mbart-large-en-ar 12 | This is mbart-large-cc25, finetuned on a subset of the UN corpus for en_ar. 13 | Usage: see [example notebook](https://colab.research.google.com/drive/1I6RFOWMaTpPBX7saJYjnSTddW0TD6H1t?usp=sharing) 14 | Note: model has limited training set, not fully trained (do not use for production). 15 | -------------------------------------------------------------------------------- /transformers/model_cards/akhooli/xlm-r-large-arabic-sent/README.md: -------------------------------------------------------------------------------- 1 | --- 2 | 3 | language: 4 | - ar 5 | - en 6 | 7 | license: mit 8 | --- 9 | ### xlm-r-large-arabic-sent 10 | Multilingual sentiment classification (Label_0: mixed, Label_1: negative, Label_2: positive) of Arabic reviews by fine-tuning XLM-Roberta-Large. 11 | Zero shot classification of other languages (also works in mixed languages - ex. Arabic & English). Mixed category is not accurate and may confuse other 12 | classes (was based on a rate of 3 out of 5 in reviews). 13 | Usage: see last section in this [Colab notebook](https://lnkd.in/d3bCFyZ) 14 | -------------------------------------------------------------------------------- /transformers/model_cards/albert-base-v1-README.md: -------------------------------------------------------------------------------- 1 | --- 2 | tags: 3 | - exbert 4 | 5 | license: apache-2.0 6 | --- 7 | 8 | 9 | 10 | 11 | -------------------------------------------------------------------------------- /transformers/model_cards/albert-xxlarge-v2-README.md: -------------------------------------------------------------------------------- 1 | --- 2 | tags: 3 | - exbert 4 | 5 | license: apache-2.0 6 | --- 7 | 8 | 9 | 10 | -------------------------------------------------------------------------------- /transformers/model_cards/allenai/longformer-base-4096-extra.pos.embd.only/README.md: -------------------------------------------------------------------------------- 1 | 2 | # longformer-base-4096-extra.pos.embd.only 3 | 4 | This model is similar to `longformer-base-4096` but it was pretrained to preserve RoBERTa weights by freezing all RoBERTa weights and only train the additional position embeddings. 5 | 6 | 7 | ### Citing 8 | 9 | If you use `Longformer` in your research, please cite [Longformer: The Long-Document Transformer](https://arxiv.org/abs/2004.05150). 10 | ``` 11 | @article{Beltagy2020Longformer, 12 | title={Longformer: The Long-Document Transformer}, 13 | author={Iz Beltagy and Matthew E. Peters and Arman Cohan}, 14 | journal={arXiv:2004.05150}, 15 | year={2020}, 16 | } 17 | ``` 18 | 19 | `Longformer` is an open-source project developed by [the Allen Institute for Artificial Intelligence (AI2)](http://www.allenai.org). 20 | AI2 is a non-profit institute with the mission to contribute to humanity through high-impact AI research and engineering. 21 | -------------------------------------------------------------------------------- /transformers/model_cards/aodiniz/bert_uncased_L-10_H-512_A-8_cord19-200616/README.md: -------------------------------------------------------------------------------- 1 | # BERT L-10 H-512 fine-tuned on MLM (CORD-19 2020/06/16) 2 | 3 | BERT model with [10 Transformer layers and hidden embedding of size 512](https://huggingface.co/google/bert_uncased_L-10_H-512_A-8), referenced in [Well-Read Students Learn Better: On the Importance of Pre-training Compact Models](https://arxiv.org/abs/1908.08962), fine-tuned for MLM on CORD-19 dataset (as released on 2020/06/16). 4 | 5 | ## Training the model 6 | 7 | ```bash 8 | python run_language_modeling.py 9 | --model_type bert 10 | --model_name_or_path google/bert_uncased_L-10_H-512_A-8 11 | --do_train 12 | --train_data_file {cord19-200616-dataset} 13 | --mlm 14 | --mlm_probability 0.2 15 | --line_by_line 16 | --block_size 512 17 | --per_device_train_batch_size 10 18 | --learning_rate 3e-5 19 | --num_train_epochs 2 20 | --output_dir bert_uncased_L-10_H-512_A-8_cord19-200616 21 | -------------------------------------------------------------------------------- /transformers/model_cards/aodiniz/bert_uncased_L-2_H-512_A-8_cord19-200616/README.md: -------------------------------------------------------------------------------- 1 | # BERT L-2 H-512 fine-tuned on MLM (CORD-19 2020/06/16) 2 | 3 | BERT model with [2 Transformer layers and hidden embedding of size 512](https://huggingface.co/google/bert_uncased_L-2_H-512_A-8), referenced in [Well-Read Students Learn Better: On the Importance of Pre-training Compact Models](https://arxiv.org/abs/1908.08962), fine-tuned for MLM on CORD-19 dataset (as released on 2020/06/16). 4 | 5 | ## Training the model 6 | 7 | ```bash 8 | python run_language_modeling.py 9 | --model_type bert 10 | --model_name_or_path google/bert_uncased_L-2_H-512_A-8 11 | --do_train 12 | --train_data_file {cord19-200616-dataset} 13 | --mlm 14 | --mlm_probability 0.2 15 | --line_by_line 16 | --block_size 512 17 | --per_device_train_batch_size 20 18 | --learning_rate 3e-5 19 | --num_train_epochs 2 20 | --output_dir bert_uncased_L-2_H-512_A-8_cord19-200616 21 | -------------------------------------------------------------------------------- /transformers/model_cards/aodiniz/bert_uncased_L-4_H-256_A-4_cord19-200616/README.md: -------------------------------------------------------------------------------- 1 | # BERT L-4 H-256 fine-tuned on MLM (CORD-19 2020/06/16) 2 | 3 | BERT model with [4 Transformer layers and hidden embedding of size 256](https://huggingface.co/google/bert_uncased_L-4_H-256_A-4), referenced in [Well-Read Students Learn Better: On the Importance of Pre-training Compact Models](https://arxiv.org/abs/1908.08962), fine-tuned for MLM on CORD-19 dataset (as released on 2020/06/16). 4 | 5 | ## Training the model 6 | 7 | ```bash 8 | python run_language_modeling.py 9 | --model_type bert 10 | --model_name_or_path google/bert_uncased_L-4_H-256_A-4 11 | --do_train 12 | --train_data_file {cord19-200616-dataset} 13 | --mlm 14 | --mlm_probability 0.2 15 | --line_by_line 16 | --block_size 256 17 | --per_device_train_batch_size 20 18 | --learning_rate 3e-5 19 | --num_train_epochs 2 20 | --output_dir bert_uncased_L-4_H-256_A-4_cord19-200616 21 | -------------------------------------------------------------------------------- /transformers/model_cards/bart-large-cnn/README.md: -------------------------------------------------------------------------------- 1 | --- 2 | tags: 3 | - summarization 4 | --- 5 | 6 | -------------------------------------------------------------------------------- /transformers/model_cards/bart-large-xsum/README.md: -------------------------------------------------------------------------------- 1 | --- 2 | tags: 3 | - summarization 4 | --- 5 | 6 | -------------------------------------------------------------------------------- /transformers/model_cards/bert-base-chinese-README.md: -------------------------------------------------------------------------------- 1 | --- 2 | language: zh 3 | --- 4 | -------------------------------------------------------------------------------- /transformers/model_cards/bert-base-german-dbmdz-cased-README.md: -------------------------------------------------------------------------------- 1 | --- 2 | language: de 3 | license: mit 4 | --- 5 | -------------------------------------------------------------------------------- /transformers/model_cards/bert-base-german-dbmdz-uncased-README.md: -------------------------------------------------------------------------------- 1 | --- 2 | language: de 3 | license: mit 4 | --- 5 | -------------------------------------------------------------------------------- /transformers/model_cards/bert-large-cased-README.md: -------------------------------------------------------------------------------- 1 | --- 2 | license: apache-2.0 3 | --- 4 | -------------------------------------------------------------------------------- /transformers/model_cards/binwang/xlnet-base-cased/README.md: -------------------------------------------------------------------------------- 1 | This model is pre-trained **XLNET** with 12 layers. 2 | 3 | It comes with paper: SBERT-WK: A Sentence Embedding Method By Dissecting BERT-based Word Models 4 | 5 | Project Page: [SBERT-WK](https://github.com/BinWang28/SBERT-WK-Sentence-Embedding) 6 | -------------------------------------------------------------------------------- /transformers/model_cards/daigo/bert-base-japanese-sentiment/README.md: -------------------------------------------------------------------------------- 1 | --- 2 | language: 3 | - ja 4 | --- 5 | 6 | binary classification 7 | 8 | # Usage 9 | ``` 10 | print(pipeline("sentiment-analysis",model="daigo/bert-base-japanese-sentiment",tokenizer="daigo/bert-base-japanese-sentiment")("私は幸福である。")) 11 | 12 | [{'label': 'ポジティブ', 'score': 0.98430425}] 13 | ``` 14 | -------------------------------------------------------------------------------- /transformers/model_cards/dccuchile/bert-base-spanish-wwm-cased/README.md: -------------------------------------------------------------------------------- 1 | --- 2 | language: es 3 | --- 4 | -------------------------------------------------------------------------------- /transformers/model_cards/dccuchile/bert-base-spanish-wwm-uncased/README.md: -------------------------------------------------------------------------------- 1 | --- 2 | language: es 3 | --- 4 | -------------------------------------------------------------------------------- /transformers/model_cards/deepset/sentence_bert/README.md: -------------------------------------------------------------------------------- 1 | This is an upload of the bert-base-nli-stsb-mean-tokens pretrained model from the Sentence Transformers Repo (https://github.com/UKPLab/sentence-transformers) 2 | -------------------------------------------------------------------------------- /transformers/model_cards/distilbert-base-cased-distilled-squad-README.md: -------------------------------------------------------------------------------- 1 | --- 2 | language: "en" 3 | datasets: 4 | - squad 5 | metrics: 6 | - squad 7 | --- 8 | -------------------------------------------------------------------------------- /transformers/model_cards/distilbert-base-multilingual-cased-README.md: -------------------------------------------------------------------------------- 1 | --- 2 | language: multilingual 3 | license: apache-2.0 4 | --- 5 | -------------------------------------------------------------------------------- /transformers/model_cards/distilgpt2-README.md: -------------------------------------------------------------------------------- 1 | --- 2 | tags: 3 | - exbert 4 | 5 | license: apache-2.0 6 | --- 7 | 8 | 9 | 10 | 11 | -------------------------------------------------------------------------------- /transformers/model_cards/distilroberta-base-README.md: -------------------------------------------------------------------------------- 1 | --- 2 | tags: 3 | - exbert 4 | 5 | license: apache-2.0 6 | --- 7 | 8 | 9 | 10 | 11 | -------------------------------------------------------------------------------- /transformers/model_cards/djstrong/bg_cs_pl_ru_cased_L-12_H-768_A-12/README.md: -------------------------------------------------------------------------------- 1 | Slavic BERT from https://github.com/deepmipt/Slavic-BERT-NER http://files.deeppavlov.ai/deeppavlov_data/bg_cs_pl_ru_cased_L-12_H-768_A-12.tar.gz 2 | -------------------------------------------------------------------------------- /transformers/model_cards/facebook/bart-large-cnn/README.md: -------------------------------------------------------------------------------- 1 | --- 2 | tags: 3 | - summarization 4 | 5 | license: mit 6 | --- 7 | -------------------------------------------------------------------------------- /transformers/model_cards/facebook/bart-large/README.md: -------------------------------------------------------------------------------- 1 | The Bart model was proposed by Mike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman Mohamed, Omer Levy, Ves Stoyanov and Luke Zettlemoyer on 29 Oct, 2019. According to the abstract, 2 | 3 | Bart uses a standard seq2seq/machine translation architecture with a bidirectional encoder (like BERT) and a left-to-right decoder (like GPT). 4 | 5 | The pretraining task involves randomly shuffling the order of the original sentences and a novel in-filling scheme, where spans of text are replaced with a single mask token. 6 | 7 | BART is particularly effective when fine tuned for text generation but also works well for comprehension tasks. It matches the performance of RoBERTa with comparable training resources on GLUE and SQuAD, achieves new state-of-the-art results on a range of abstractive dialogue, question answering, and summarization tasks, with gains of up to 6 ROUGE. 8 | 9 | The Authors’ code can be found here: 10 | https://github.com/pytorch/fairseq/tree/master/examples/bart 11 | -------------------------------------------------------------------------------- /transformers/model_cards/facebook/rag-token-nq_new/README.md: -------------------------------------------------------------------------------- 1 | The model can be loaded and used as follows on [this branch](https://github.com/huggingface/transformers/tree/finalize_rag) as follows. 2 | 3 | 4 | # Load model 5 | 6 | ```python 7 | from transformers import RagTokenizer, RagTokenForGeneration, RagRetriever 8 | 9 | # create Retriever augmented model 10 | retriever = RagRetriever.from_pretrained("facebook/rag-token-nq_new", use_dummy_dataset=True) 11 | model = RagTokenForGeneration.from_pretrained("facebook/rag-token-nq_new", retriever=retriever) 12 | 13 | tokenizer = RagTokenizer.from_pretrained("facebook/rag-token-nq_new") 14 | 15 | # create input ids and labels 16 | input_ids = tokenizer("who sings does he love me with reba", return_tensors="pt").input_ids 17 | 18 | # use labels 19 | labels = tokenizer.generator("Linda Davis", return_tensors="pt").input_ids 20 | 21 | 22 | # compute loss 23 | outputs = model(input_ids, labels=labels) 24 | ``` 25 | -------------------------------------------------------------------------------- /transformers/model_cards/flexudy/t5-base-multi-sentence-doctor/sent-banner.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/model_cards/flexudy/t5-base-multi-sentence-doctor/sent-banner.png -------------------------------------------------------------------------------- /transformers/model_cards/gpt2-large-README.md: -------------------------------------------------------------------------------- 1 | Test the full generation capabilities here: https://transformer.huggingface.co/doc/gpt2-large 2 | -------------------------------------------------------------------------------- /transformers/model_cards/gpt2-medium-README.md: -------------------------------------------------------------------------------- 1 | Test the full generation capabilities here: https://transformer.huggingface.co/doc/gpt2-large 2 | -------------------------------------------------------------------------------- /transformers/model_cards/gpt2-xl-README.md: -------------------------------------------------------------------------------- 1 | Test the whole generation capabilities here: https://transformer.huggingface.co/doc/gpt2-large 2 | -------------------------------------------------------------------------------- /transformers/model_cards/healx/gpt-2-pubmed-large/README.md: -------------------------------------------------------------------------------- 1 | GPT-2 (774M model) finetuned on 0.5m PubMed abstracts. Used in the [writemeanabstract.com](writemeanabstract.com) and the following preprint: 2 | 3 | [Papanikolaou, Yannis, and Andrea Pierleoni. "DARE: Data Augmented Relation Extraction with GPT-2." arXiv preprint arXiv:2004.13845 (2020).](https://arxiv.org/abs/2004.13845) 4 | -------------------------------------------------------------------------------- /transformers/model_cards/healx/gpt-2-pubmed-medium/README.md: -------------------------------------------------------------------------------- 1 | GPT-2 (355M model) finetuned on 0.5m PubMed abstracts. Used in the [writemeanabstract.com](writemeanabstract.com) and the following preprint: 2 | 3 | [Papanikolaou, Yannis, and Andrea Pierleoni. "DARE: Data Augmented Relation Extraction with GPT-2." arXiv preprint arXiv:2004.13845 (2020).](https://arxiv.org/abs/2004.13845) 4 | -------------------------------------------------------------------------------- /transformers/model_cards/illuin/lepetit/README.md: -------------------------------------------------------------------------------- 1 | --- 2 | language: fr 3 | thumbnail: https://miro.medium.com/max/700/1*MoPnD6vA9wTHjdLfW7POyw.png 4 | widget: 5 | - text: "Le camembert LePetit c'est le ." 6 | - text: "Salut les ça va ?" 7 | --- 8 | 9 | # LePetit: A pre-training efficient and lightning fast French Language Model 10 | 11 | See [blogpost](https://medium.com/illuin/lepetit-a-pre-training-efficient-and-lightning-fast-french-language-model-96495ad726b3) 12 | 13 | -------------------------------------------------------------------------------- /transformers/model_cards/ipuneetrathore/bert-base-cased-finetuned-finBERT/README.md: -------------------------------------------------------------------------------- 1 | ## FinBERT 2 | 3 | Code for importing and using this model is available [here](https://github.com/ipuneetrathore/BERT_models) 4 | -------------------------------------------------------------------------------- /transformers/model_cards/jannesg/bertsson/README.md: -------------------------------------------------------------------------------- 1 | --- 2 | language: sv 3 | --- 4 | 5 | # BERTSSON Models 6 | 7 | The models are trained on: 8 | - Government Text 9 | - Swedish Literature 10 | - Swedish News 11 | 12 | Corpus size: Roughly 6B tokens. 13 | 14 | The following models are currently available: 15 | 16 | - **bertsson** - A BERT base model trained with the same hyperparameters as first published by Google. 17 | 18 | All models are cased and trained with whole word masking. 19 | 20 | Stay tuned for evaluations. 21 | -------------------------------------------------------------------------------- /transformers/model_cards/jimregan/BERTreach/README.md: -------------------------------------------------------------------------------- 1 | --- 2 | language: ga 3 | tags: 4 | - irish 5 | --- 6 | 7 | ## BERTreach 8 | 9 | ([beirtreach](https://www.teanglann.ie/en/fgb/beirtreach) means 'oyster bed') 10 | 11 | **Model size:** 84M 12 | 13 | **Training data:** 14 | * [PARSEME 1.2](https://gitlab.com/parseme/parseme_corpus_ga/-/blob/master/README.md) 15 | * Newscrawl 300k portion of the [Leipzig Corpora](https://wortschatz.uni-leipzig.de/en/download/irish) 16 | * Private news corpus crawled with [Corpus Crawler](https://github.com/google/corpuscrawler) 17 | 18 | (2125804 sentences, 47419062 tokens, as reckoned by wc) 19 | 20 | ``` 21 | from transformers import pipeline 22 | fill_mask = pipeline("fill-mask", model="jimregan/BERTreach", tokenizer="jimregan/BERTreach") 23 | ``` 24 | -------------------------------------------------------------------------------- /transformers/model_cards/julien-c/bert-xsmall-dummy/README.md: -------------------------------------------------------------------------------- 1 | ## How to build a dummy model 2 | 3 | 4 | ```python 5 | from transformers.configuration_bert import BertConfig 6 | from transformers.modeling_bert import BertForMaskedLM 7 | from transformers.modeling_tf_bert import TFBertForMaskedLM 8 | from transformers.tokenization_bert import BertTokenizer 9 | 10 | 11 | SMALL_MODEL_IDENTIFIER = "julien-c/bert-xsmall-dummy" 12 | DIRNAME = "./bert-xsmall-dummy" 13 | 14 | config = BertConfig(10, 20, 1, 1, 40) 15 | 16 | model = BertForMaskedLM(config) 17 | model.save_pretrained(DIRNAME) 18 | 19 | tf_model = TFBertForMaskedLM.from_pretrained(DIRNAME, from_pt=True) 20 | tf_model.save_pretrained(DIRNAME) 21 | 22 | # Slightly different for tokenizer. 23 | # tokenizer = BertTokenizer.from_pretrained(DIRNAME) 24 | # tokenizer.save_pretrained() 25 | ``` 26 | -------------------------------------------------------------------------------- /transformers/model_cards/lvwerra/bert-imdb/README.md: -------------------------------------------------------------------------------- 1 | # BERT-IMDB 2 | 3 | ## What is it? 4 | BERT (`bert-large-cased`) trained for sentiment classification on the [IMDB dataset](https://www.kaggle.com/lakshmi25npathi/imdb-dataset-of-50k-movie-reviews). 5 | 6 | ## Training setting 7 | 8 | The model was trained on 80% of the IMDB dataset for sentiment classification for three epochs with a learning rate of `1e-5` with the `simpletransformers` library. The library uses a learning rate schedule. 9 | 10 | ## Result 11 | The model achieved 90% classification accuracy on the validation set. 12 | 13 | ## Reference 14 | The full experiment is available in the [tlr repo](https://lvwerra.github.io/trl/03-bert-imdb-training/). 15 | -------------------------------------------------------------------------------- /transformers/model_cards/lvwerra/gpt2-imdb/README.md: -------------------------------------------------------------------------------- 1 | # GPT2-IMDB 2 | 3 | ## What is it? 4 | A GPT2 (`gpt2`) language model fine-tuned on the [IMDB dataset](https://www.kaggle.com/lakshmi25npathi/imdb-dataset-of-50k-movie-reviews). 5 | 6 | ## Training setting 7 | 8 | The GPT2 language model was fine-tuned for 1 epoch on the IMDB dataset. All comments were joined into a single text file separated by the EOS token: 9 | 10 | ``` 11 | import pandas as pd 12 | df = pd.read_csv("imdb-dataset.csv") 13 | imdb_str = " <|endoftext|> ".join(df['review'].tolist()) 14 | 15 | with open ('imdb.txt', 'w') as f: 16 | f.write(imdb_str) 17 | ``` 18 | 19 | To train the model the `run_language_modeling.py` script in the `transformer` library was used: 20 | 21 | ``` 22 | python run_language_modeling.py 23 | --train_data_file imdb.txt 24 | --output_dir gpt2-imdb 25 | --model_type gpt2 26 | --model_name_or_path gpt2 27 | ``` 28 | -------------------------------------------------------------------------------- /transformers/model_cards/lvwerra/gpt2-medium-taboo/README.md: -------------------------------------------------------------------------------- 1 | # GPT-2 (medium) Taboo 2 | 3 | ## What is it? 4 | A fine-tuned GPT-2 version for Taboo cards generation. 5 | 6 | ## Training setting 7 | 8 | The model was trained on ~900 Taboo cards in the following format for 100 epochs: 9 | ``` 10 | Describe the word Glitch without using the words Problem, Unexpected, Technology, Minor, Outage. 11 | ```` 12 | 13 | -------------------------------------------------------------------------------- /transformers/model_cards/lysandre/arxiv-nlp/README.md: -------------------------------------------------------------------------------- 1 | # ArXiv-NLP GPT-2 checkpoint 2 | 3 | This is a GPT-2 small checkpoint for PyTorch. It is the official `gpt2-small` fine-tuned to ArXiv paper on the computational linguistics field. 4 | 5 | ## Training data 6 | 7 | This model was trained on a subset of ArXiv papers that were parsed from PDF to txt. The resulting data is made of 80MB of text from the computational linguistics (cs.CL) field. -------------------------------------------------------------------------------- /transformers/model_cards/lysandre/arxiv/README.md: -------------------------------------------------------------------------------- 1 | # ArXiv GPT-2 checkpoint 2 | 3 | This is a GPT-2 small checkpoint for PyTorch. It is the official `gpt2-small` finetuned to ArXiv paper on physics fields. 4 | 5 | ## Training data 6 | 7 | This model was trained on a subset of ArXiv papers that were parsed from PDF to txt. The resulting data is made of 130MB of text, mostly from quantum physics (quant-ph) and other physics sub-fields. 8 | -------------------------------------------------------------------------------- /transformers/model_cards/mrm8488/GuaPeTe-2-tiny/README.md: -------------------------------------------------------------------------------- 1 | --- 2 | language: es 3 | widget: 4 | - text: "Murcia es la huerta de Europa porque" 5 | --- 6 | 7 | #GuaPeTe-2-tiny: A proof of concept tiny GPT-2 like model trained on Spanish Wikipedia corpus 8 | -------------------------------------------------------------------------------- /transformers/model_cards/mrm8488/RoBERTinha/README.md: -------------------------------------------------------------------------------- 1 | --- 2 | language: gl 3 | widget: 4 | - text: "Galicia é unha autónoma española." 5 | - text: "A lingua oficial de Galicia é o ." 6 | --- 7 | 8 | # RoBERTinha: RoBERTa-like Language model trained on OSCAR Galician corpus 9 | -------------------------------------------------------------------------------- /transformers/model_cards/mrm8488/RoBasquERTa/README.md: -------------------------------------------------------------------------------- 1 | --- 2 | language: eu 3 | widget: 4 | - text: "Euskara da Euskal Herriko ofiziala" 5 | - text: "Gaur egun, Euskadik Espainia osoko ekonomia du" 6 | --- 7 | 8 | # RoBasquERTa: RoBERTa-like Language model trained on OSCAR Basque corpus 9 | -------------------------------------------------------------------------------- /transformers/model_cards/mrm8488/RuPERTa-base-finetuned-pawsx-es/README.md: -------------------------------------------------------------------------------- 1 | --- 2 | language: es 3 | datasets: 4 | - xtreme 5 | widget: 6 | - text: "En 2009 se mudó a Filadelfia y en la actualidad vive en Nueva York. Se mudó nuevamente a Filadelfia en 2009 y ahora vive en la ciudad de Nueva York." 7 | --- 8 | 9 | # RuPERTa-base fine-tuned on PAWS-X-es for Paraphrase Identification 10 | -------------------------------------------------------------------------------- /transformers/model_cards/mrm8488/RuPERTa-base-finetuned-squadv1/README.md: -------------------------------------------------------------------------------- 1 | --- 2 | language: es 3 | datasets: 4 | - squad 5 | --- 6 | -------------------------------------------------------------------------------- /transformers/model_cards/mrm8488/RuPERTa-base-finetuned-squadv2/README.md: -------------------------------------------------------------------------------- 1 | --- 2 | language: es 3 | datasets: 4 | - squad_v2 5 | --- 6 | -------------------------------------------------------------------------------- /transformers/model_cards/mrm8488/bert-base-german-dbmdz-cased-finetuned-pawsx-de/README.md: -------------------------------------------------------------------------------- 1 | --- 2 | language: de 3 | datasets: 4 | - xtreme 5 | widget: 6 | - text: "Winarsky ist Mitglied des IEEE, Phi Beta Kappa, des ACM und des Sigma Xi. Winarsky ist Mitglied des ACM, des IEEE, der Phi Beta Kappa und der Sigma Xi." 7 | --- 8 | 9 | # bert-base-german-dbmdz-cased fine-tuned on PAWS-X-de for Paraphrase Identification 10 | -------------------------------------------------------------------------------- /transformers/model_cards/mrm8488/camembert-base-finetuned-pawsx-fr/README.md: -------------------------------------------------------------------------------- 1 | --- 2 | language: fr 3 | datasets: 4 | - xtreme 5 | widget: 6 | - text: "La première série a été mieux reçue par la critique que la seconde. La seconde série a été bien accueillie par la critique, mieux que la première." 7 | --- 8 | 9 | # Camembert-base fine-tuned on PAWS-X-fr for Paraphrase Identification 10 | -------------------------------------------------------------------------------- /transformers/model_cards/mrm8488/electricidad-base-finetuned-pawsx-es/README.md: -------------------------------------------------------------------------------- 1 | --- 2 | language: es 3 | datasets: 4 | - xtreme 5 | widget: 6 | - text: "El río Tabaci es una vertiente del río Leurda en Rumania. El río Leurda es un afluente del río Tabaci en Rumania." 7 | --- 8 | 9 | # Electricidad-base fine-tuned on PAWS-X-es for Paraphrase Identification 10 | -------------------------------------------------------------------------------- /transformers/model_cards/mrm8488/gpt2-finetuned-recipes-cooking/README.md: -------------------------------------------------------------------------------- 1 | --- 2 | language: en 3 | thumbnail: 4 | widget: 5 | - text: "HuggingFace Cake:" 6 | --- 7 | -------------------------------------------------------------------------------- /transformers/model_cards/mrm8488/gpt2-finetuned-recipes-cooking_v2/README.md: -------------------------------------------------------------------------------- 1 | --- 2 | language: en 3 | thumbnail: 4 | widget: 5 | - text: "HuggingFace Cake:" 6 | --- 7 | -------------------------------------------------------------------------------- /transformers/model_cards/pradhyra/AWSBlogBert/README.md: -------------------------------------------------------------------------------- 1 | This model is pre-trained on blog articles from AWS Blogs. 2 | 3 | ## Pre-training corpora 4 | The input text contains around 3000 blog articles on [AWS Blogs website](https://aws.amazon.com/blogs/) technical subject matter including AWS products, tools and tutorials. 5 | 6 | ## Pre-training details 7 | I picked a Roberta architecture for masked language modeling (6-layer, 768-hidden, 12-heads, 82M parameters) and its corresponding ByteLevelBPE tokenization strategy. I then followed HuggingFace's Transformers [blog post](https://huggingface.co/blog/how-to-train) to train the model. 8 | I chose to follow the following training set-up: 28k training steps with batches of 64 sequences of length 512 with an initial learning rate 5e-5. The model acheived a training loss of 3.6 on the MLM task over 10 epochs. 9 | -------------------------------------------------------------------------------- /transformers/model_cards/pranavpsv/gpt2-genre-story-generator/README.md: -------------------------------------------------------------------------------- 1 | 2 | # GPT2 Genre Based Story Generator 3 | 4 | ## Model description 5 | 6 | GPT2 fine-tuned on genre-based story generation. 7 | 8 | ## Intended uses 9 | 10 | Used to generate stories based on user inputted genre and starting prompts. 11 | 12 | ## How to use 13 | 14 | #### Supported Genres 15 | superhero, action, drama, horror, thriller, sci_fi 16 | #### Input text format 17 | \ \ Some optional text... 18 | 19 | **Example**: \ \ After discovering time travel, 20 | 21 | ```python 22 | # Example of usage 23 | from transformers import pipeline 24 | 25 | story_gen = pipeline("text-generation", "pranavpsv/gpt2-genre-story-generator") 26 | print(story_gen(" Batman")) 27 | 28 | ``` 29 | 30 | ## Training data 31 | 32 | Initialized with pre-trained weights of "gpt2" checkpoint. Fine-tuned the model on stories of various genres. 33 | -------------------------------------------------------------------------------- /transformers/model_cards/rdenadai/BR_BERTo/README.md: -------------------------------------------------------------------------------- 1 | --- 2 | language: pt 3 | tags: 4 | - portuguese 5 | - brazil 6 | - pt_BR 7 | widget: 8 | - text: gostei muito dessa 9 | --- 10 | 11 | # BR_BERTo 12 | 13 | Portuguese (Brazil) model for text inference. 14 | 15 | ## Params 16 | 17 | Trained on a corpus of 6_993_330 sentences. 18 | 19 | - Vocab size: 150_000 20 | - RobertaForMaskedLM size : 512 21 | - Num train epochs: 3 22 | - Time to train: ~10days (on GCP with a Nvidia T4) 23 | 24 | I follow the great tutorial from HuggingFace team: 25 | 26 | [How to train a new language model from scratch using Transformers and Tokenizers](https://huggingface.co/blog/how-to-train) 27 | 28 | More infor here: 29 | 30 | [BR_BERTo](https://github.com/rdenadai/BR-BERTo) 31 | -------------------------------------------------------------------------------- /transformers/model_cards/roberta-large-mnli-README.md: -------------------------------------------------------------------------------- 1 | --- 2 | license: mit 3 | widget: 4 | - text: "I like you. I love you." 5 | --- 6 | 7 | 8 | ## roberta-large-mnli 9 | 10 | Trained by Facebook, [original source](https://github.com/pytorch/fairseq/tree/master/examples/roberta) 11 | 12 | ```bibtex 13 | @article{liu2019roberta, 14 | title = {RoBERTa: A Robustly Optimized BERT Pretraining Approach}, 15 | author = {Yinhan Liu and Myle Ott and Naman Goyal and Jingfei Du and 16 | Mandar Joshi and Danqi Chen and Omer Levy and Mike Lewis and 17 | Luke Zettlemoyer and Veselin Stoyanov}, 18 | journal={arXiv preprint arXiv:1907.11692}, 19 | year = {2019}, 20 | } 21 | ``` 22 | 23 | -------------------------------------------------------------------------------- /transformers/model_cards/schmidek/electra-small-cased/README.md: -------------------------------------------------------------------------------- 1 | --- 2 | language: en 3 | license: apache-2.0 4 | --- 5 | 6 | ## ELECTRA-small-cased 7 | 8 | This is a cased version of `google/electra-small-discriminator`, trained on the 9 | [OpenWebText corpus](https://skylion007.github.io/OpenWebTextCorpus/). 10 | 11 | Uses the same tokenizer and vocab from `bert-base-cased` 12 | -------------------------------------------------------------------------------- /transformers/model_cards/severinsimmler/literary-german-bert/kfold.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/model_cards/severinsimmler/literary-german-bert/kfold.png -------------------------------------------------------------------------------- /transformers/model_cards/severinsimmler/literary-german-bert/prosa-jahre.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/model_cards/severinsimmler/literary-german-bert/prosa-jahre.png -------------------------------------------------------------------------------- /transformers/model_cards/spentaur/yelp/README.md: -------------------------------------------------------------------------------- 1 | # DistilBERT Yelp Review Sentiment 2 | This model is used for sentiment analysis on english yelp reviews. 3 | It is a DistilBERT model trained on 1 million reviews from the yelp open dataset. 4 | It is a regression model, with outputs in the range of ~-2 to ~2. With -2 being 1 star and 2 being 5 stars. 5 | It was trained using the [ktrain](https://github.com/amaiya/ktrain) because of it's ease of use. 6 | 7 | Example use: 8 | 9 | ``` 10 | tokenizer = AutoTokenizer.from_pretrained( 11 | 'distilbert-base-uncased', use_fast=True) 12 | model = TFAutoModelForSequenceClassification.from_pretrained( 13 | "spentaur/yelp") 14 | 15 | review = "This place is great!" 16 | input_ids = tokenizer.encode(review, return_tensors='tf') 17 | pred = model(input_ids)[0][0][0].numpy() 18 | # pred should === 1.9562385 19 | ``` 20 | -------------------------------------------------------------------------------- /transformers/model_cards/stas/tiny-wmt19-en-de/README.md: -------------------------------------------------------------------------------- 1 | --- 2 | language: 3 | - en 4 | - de 5 | thumbnail: 6 | tags: 7 | - wmt19 8 | - testing 9 | license: apache-2.0 10 | datasets: 11 | - wmt19 12 | metrics: 13 | - bleu 14 | --- 15 | 16 | # Tiny FSMT 17 | 18 | This is a tiny model that is used in the `transformers` test suite. It doesn't do anything useful, other than testing that `FSMT` works. 19 | -------------------------------------------------------------------------------- /transformers/model_cards/uncnlp/lxmert-base-uncased/lxmert_model-1.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/model_cards/uncnlp/lxmert-base-uncased/lxmert_model-1.jpg -------------------------------------------------------------------------------- /transformers/model_cards/xlm-mlm-en-2048-README.md: -------------------------------------------------------------------------------- 1 | --- 2 | tags: 3 | - exbert 4 | 5 | license: cc-by-nc-4.0 6 | --- 7 | 8 | 9 | 10 | 11 | -------------------------------------------------------------------------------- /transformers/model_cards/xlm-roberta-base-README.md: -------------------------------------------------------------------------------- 1 | --- 2 | tags: 3 | - exbert 4 | 5 | license: mit 6 | --- 7 | 8 | 9 | 10 | 11 | -------------------------------------------------------------------------------- /transformers/model_cards/xlm-roberta-large-finetuned-conll03-german-README.md: -------------------------------------------------------------------------------- 1 | --- 2 | language: de 3 | --- 4 | 5 | ## xlm-roberta-large-finetuned-conll03-german 6 | -------------------------------------------------------------------------------- /transformers/model_cards/yjernite/bart_eli5/README.md: -------------------------------------------------------------------------------- 1 | --- 2 | language: en 3 | license: apache-2.0 4 | datasets: 5 | - eli5 6 | --- 7 | 8 | ## BART ELI5 9 | 10 | Read the article at https://yjernite.github.io/lfqa.html and try the demo at https://huggingface.co/qa/ 11 | -------------------------------------------------------------------------------- /transformers/model_cards/yuvraj/summarizer-cnndm/README.md: -------------------------------------------------------------------------------- 1 | --- 2 | language: "en" 3 | tags: 4 | - summarization 5 | --- 6 | ​ 7 | # Summarization 8 | ​ 9 | ## Model description 10 | ​ 11 | BartForConditionalGeneration model fine tuned for summarization on 10000 samples from the cnn-dailymail dataset 12 | ​ 13 | ## How to use 14 | ​ 15 | PyTorch model available 16 | ​ 17 | ```python 18 | from transformers import AutoTokenizer, AutoModelWithLMHead, pipeline 19 | ​ 20 | tokenizer = AutoTokenizer.from_pretrained("yuvraj/summarizer-cnndm") 21 | AutoModelWithLMHead.from_pretrained("yuvraj/summarizer-cnndm") 22 | ​ 23 | summarizer = pipeline('summarization', model=model, tokenizer=tokenizer) 24 | summarizer("") 25 | ​ 26 | ## Limitations and bias 27 | Trained on a small dataset 28 | -------------------------------------------------------------------------------- /transformers/model_cards/yuvraj/xSumm/README.md: -------------------------------------------------------------------------------- 1 | --- 2 | language: "en" 3 | tags: 4 | - summarization 5 | - extreme summarization 6 | --- 7 | ​ 8 | ## Model description 9 | ​ 10 | BartForConditionalGenerationModel for extreme summarization- creates a one line abstractive summary of a given article 11 | ​ 12 | ## How to use 13 | ​ 14 | PyTorch model available 15 | ​ 16 | ```python 17 | from transformers import AutoTokenizer, AutoModelWithLMHead, pipeline 18 | ​ 19 | tokenizer = AutoTokenizer.from_pretrained("yuvraj/xSumm") 20 | model = AutoModelWithLMHead.from_pretrained("yuvraj/xSumm") 21 | ​ 22 | xsumm = pipeline('summarization', model=model, tokenizer=tokenizer) 23 | xsumm("") 24 | ​ 25 | ## Limitations and bias 26 | Trained on a small fraction of the xsumm training dataset 27 | -------------------------------------------------------------------------------- /transformers/pyproject.toml: -------------------------------------------------------------------------------- 1 | [tool.black] 2 | line-length = 119 3 | target-version = ['py35'] 4 | -------------------------------------------------------------------------------- /transformers/scripts/fsmt/tests-to-run.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env bash 2 | 3 | # these scripts need to be run before any changes to FSMT-related code - it should cover all bases 4 | 5 | USE_CUDA=0 RUN_SLOW=1 pytest --disable-warnings tests/test_tokenization_fsmt.py tests/test_configuration_auto.py tests/test_modeling_fsmt.py examples/seq2seq/test_fsmt_bleu_score.py 6 | USE_CUDA=1 RUN_SLOW=1 pytest --disable-warnings tests/test_tokenization_fsmt.py tests/test_configuration_auto.py tests/test_modeling_fsmt.py examples/seq2seq/test_fsmt_bleu_score.py 7 | -------------------------------------------------------------------------------- /transformers/setup.cfg: -------------------------------------------------------------------------------- 1 | [isort] 2 | default_section = FIRSTPARTY 3 | ensure_newline_before_comments = True 4 | force_grid_wrap = 0 5 | include_trailing_comma = True 6 | known_first_party = transformers 7 | known_third_party = 8 | absl 9 | conllu 10 | datasets 11 | elasticsearch 12 | fairseq 13 | faiss-cpu 14 | fastprogress 15 | fire 16 | fugashi 17 | git 18 | h5py 19 | matplotlib 20 | nltk 21 | numpy 22 | packaging 23 | pandas 24 | PIL 25 | psutil 26 | pytest 27 | pytorch_lightning 28 | rouge_score 29 | sacrebleu 30 | seqeval 31 | sklearn 32 | streamlit 33 | tensorboardX 34 | tensorflow 35 | tensorflow_datasets 36 | timeout_decorator 37 | torch 38 | torchtext 39 | torchvision 40 | torch_xla 41 | tqdm 42 | 43 | line_length = 119 44 | lines_after_imports = 2 45 | multi_line_output = 3 46 | use_parentheses = True 47 | 48 | [flake8] 49 | ignore = E203, E501, E741, W503, W605 50 | max-line-length = 119 51 | -------------------------------------------------------------------------------- /transformers/src/transformers.egg-info/dependency_links.txt: -------------------------------------------------------------------------------- 1 | 2 | -------------------------------------------------------------------------------- /transformers/src/transformers.egg-info/entry_points.txt: -------------------------------------------------------------------------------- 1 | [console_scripts] 2 | transformers-cli = transformers.commands.transformers_cli:main 3 | 4 | -------------------------------------------------------------------------------- /transformers/src/transformers.egg-info/top_level.txt: -------------------------------------------------------------------------------- 1 | transformers 2 | -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/__init__.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/__init__.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/__init__.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/__init__.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/activations.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/activations.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/activations.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/activations.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/activations_tf.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/activations_tf.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/configuration_albert.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/configuration_albert.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/configuration_albert.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/configuration_albert.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/configuration_auto.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/configuration_auto.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/configuration_auto.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/configuration_auto.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/configuration_bart.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/configuration_bart.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/configuration_bart.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/configuration_bart.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/configuration_bert.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/configuration_bert.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/configuration_bert.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/configuration_bert.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/configuration_bert_generation.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/configuration_bert_generation.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/configuration_bert_generation.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/configuration_bert_generation.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/configuration_camembert.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/configuration_camembert.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/configuration_camembert.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/configuration_camembert.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/configuration_ctrl.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/configuration_ctrl.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/configuration_ctrl.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/configuration_ctrl.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/configuration_distilbert.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/configuration_distilbert.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/configuration_distilbert.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/configuration_distilbert.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/configuration_dpr.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/configuration_dpr.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/configuration_dpr.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/configuration_dpr.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/configuration_electra.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/configuration_electra.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/configuration_electra.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/configuration_electra.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/configuration_encoder_decoder.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/configuration_encoder_decoder.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/configuration_encoder_decoder.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/configuration_encoder_decoder.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/configuration_flaubert.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/configuration_flaubert.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/configuration_flaubert.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/configuration_flaubert.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/configuration_fsmt.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/configuration_fsmt.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/configuration_fsmt.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/configuration_fsmt.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/configuration_funnel.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/configuration_funnel.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/configuration_funnel.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/configuration_funnel.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/configuration_gpt2.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/configuration_gpt2.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/configuration_gpt2.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/configuration_gpt2.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/configuration_layoutlm.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/configuration_layoutlm.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/configuration_layoutlm.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/configuration_layoutlm.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/configuration_longformer.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/configuration_longformer.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/configuration_longformer.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/configuration_longformer.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/configuration_lxmert.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/configuration_lxmert.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/configuration_lxmert.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/configuration_lxmert.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/configuration_marian.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/configuration_marian.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/configuration_marian.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/configuration_marian.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/configuration_mbart.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/configuration_mbart.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/configuration_mbart.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/configuration_mbart.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/configuration_mmbt.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/configuration_mmbt.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/configuration_mmbt.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/configuration_mmbt.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/configuration_mobilebert.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/configuration_mobilebert.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/configuration_mobilebert.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/configuration_mobilebert.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/configuration_openai.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/configuration_openai.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/configuration_openai.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/configuration_openai.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/configuration_pegasus.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/configuration_pegasus.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/configuration_pegasus.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/configuration_pegasus.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/configuration_rag.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/configuration_rag.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/configuration_rag.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/configuration_rag.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/configuration_reformer.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/configuration_reformer.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/configuration_reformer.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/configuration_reformer.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/configuration_retribert.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/configuration_retribert.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/configuration_retribert.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/configuration_retribert.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/configuration_roberta.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/configuration_roberta.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/configuration_roberta.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/configuration_roberta.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/configuration_t5.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/configuration_t5.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/configuration_t5.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/configuration_t5.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/configuration_transfo_xl.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/configuration_transfo_xl.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/configuration_transfo_xl.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/configuration_transfo_xl.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/configuration_utils.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/configuration_utils.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/configuration_utils.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/configuration_utils.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/configuration_xlm.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/configuration_xlm.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/configuration_xlm.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/configuration_xlm.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/configuration_xlm_roberta.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/configuration_xlm_roberta.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/configuration_xlm_roberta.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/configuration_xlm_roberta.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/configuration_xlnet.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/configuration_xlnet.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/configuration_xlnet.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/configuration_xlnet.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/file_utils.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/file_utils.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/file_utils.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/file_utils.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/generation_tf_utils.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/generation_tf_utils.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/generation_utils.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/generation_utils.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/generation_utils.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/generation_utils.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/hf_argparser.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/hf_argparser.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/hf_argparser.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/hf_argparser.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/integrations.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/integrations.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/integrations.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/integrations.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modelcard.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modelcard.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modelcard.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modelcard.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_albert.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_albert.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_albert.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_albert.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_auto.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_auto.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_auto.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_auto.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_bart.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_bart.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_bart.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_bart.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_bert.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_bert.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_bert.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_bert.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_bert_generation.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_bert_generation.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_bert_generation.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_bert_generation.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_camembert.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_camembert.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_camembert.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_camembert.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_ctrl.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_ctrl.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_ctrl.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_ctrl.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_distilbert.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_distilbert.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_distilbert.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_distilbert.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_dpr.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_dpr.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_dpr.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_dpr.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_electra.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_electra.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_electra.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_electra.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_encoder_decoder.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_encoder_decoder.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_encoder_decoder.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_encoder_decoder.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_flaubert.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_flaubert.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_flaubert.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_flaubert.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_fsmt.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_fsmt.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_fsmt.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_fsmt.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_funnel.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_funnel.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_funnel.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_funnel.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_gpt2.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_gpt2.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_gpt2.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_gpt2.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_layoutlm.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_layoutlm.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_layoutlm.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_layoutlm.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_longformer.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_longformer.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_longformer.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_longformer.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_lxmert.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_lxmert.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_lxmert.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_lxmert.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_marian.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_marian.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_marian.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_marian.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_mbart.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_mbart.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_mbart.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_mbart.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_mmbt.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_mmbt.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_mmbt.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_mmbt.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_mobilebert.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_mobilebert.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_mobilebert.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_mobilebert.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_openai.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_openai.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_openai.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_openai.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_outputs.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_outputs.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_outputs.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_outputs.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_pegasus.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_pegasus.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_pegasus.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_pegasus.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_rag.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_rag.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_rag.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_rag.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_reformer.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_reformer.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_reformer.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_reformer.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_retribert.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_retribert.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_retribert.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_retribert.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_roberta.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_roberta.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_roberta.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_roberta.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_t5.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_t5.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_t5.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_t5.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_tf_albert.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_tf_albert.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_tf_auto.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_tf_auto.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_tf_bert.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_tf_bert.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_tf_camembert.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_tf_camembert.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_tf_ctrl.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_tf_ctrl.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_tf_distilbert.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_tf_distilbert.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_tf_electra.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_tf_electra.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_tf_flaubert.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_tf_flaubert.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_tf_funnel.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_tf_funnel.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_tf_gpt2.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_tf_gpt2.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_tf_longformer.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_tf_longformer.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_tf_lxmert.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_tf_lxmert.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_tf_mobilebert.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_tf_mobilebert.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_tf_openai.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_tf_openai.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_tf_outputs.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_tf_outputs.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_tf_pytorch_utils.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_tf_pytorch_utils.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_tf_pytorch_utils.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_tf_pytorch_utils.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_tf_roberta.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_tf_roberta.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_tf_t5.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_tf_t5.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_tf_transfo_xl.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_tf_transfo_xl.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_tf_transfo_xl_utilities.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_tf_transfo_xl_utilities.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_tf_utils.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_tf_utils.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_tf_xlm.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_tf_xlm.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_tf_xlm_roberta.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_tf_xlm_roberta.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_tf_xlnet.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_tf_xlnet.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_transfo_xl.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_transfo_xl.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_transfo_xl.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_transfo_xl.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_transfo_xl_utilities.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_transfo_xl_utilities.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_transfo_xl_utilities.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_transfo_xl_utilities.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_utils.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_utils.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_utils.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_utils.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_xlm.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_xlm.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_xlm.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_xlm.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_xlm_roberta.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_xlm_roberta.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_xlm_roberta.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_xlm_roberta.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_xlnet.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_xlnet.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/modeling_xlnet.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/modeling_xlnet.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/optimization.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/optimization.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/optimization.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/optimization.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/optimization_tf.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/optimization_tf.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/pipelines.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/pipelines.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/pipelines.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/pipelines.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/retrieval_rag.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/retrieval_rag.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/retrieval_rag.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/retrieval_rag.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_albert.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_albert.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_albert.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_albert.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_auto.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_auto.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_auto.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_auto.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_bart.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_bart.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_bart.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_bart.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_bert.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_bert.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_bert.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_bert.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_bert_generation.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_bert_generation.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_bert_generation.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_bert_generation.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_bert_japanese.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_bert_japanese.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_bert_japanese.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_bert_japanese.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_bertweet.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_bertweet.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_bertweet.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_bertweet.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_camembert.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_camembert.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_camembert.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_camembert.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_ctrl.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_ctrl.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_ctrl.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_ctrl.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_distilbert.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_distilbert.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_distilbert.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_distilbert.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_dpr.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_dpr.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_dpr.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_dpr.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_electra.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_electra.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_electra.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_electra.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_flaubert.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_flaubert.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_flaubert.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_flaubert.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_fsmt.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_fsmt.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_fsmt.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_fsmt.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_funnel.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_funnel.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_funnel.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_funnel.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_gpt2.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_gpt2.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_gpt2.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_gpt2.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_layoutlm.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_layoutlm.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_layoutlm.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_layoutlm.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_longformer.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_longformer.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_longformer.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_longformer.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_lxmert.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_lxmert.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_lxmert.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_lxmert.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_marian.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_marian.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_marian.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_marian.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_mbart.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_mbart.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_mbart.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_mbart.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_mobilebert.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_mobilebert.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_mobilebert.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_mobilebert.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_openai.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_openai.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_openai.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_openai.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_pegasus.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_pegasus.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_pegasus.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_pegasus.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_phobert.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_phobert.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_phobert.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_phobert.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_rag.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_rag.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_rag.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_rag.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_reformer.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_reformer.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_reformer.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_reformer.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_retribert.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_retribert.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_retribert.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_retribert.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_roberta.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_roberta.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_roberta.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_roberta.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_t5.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_t5.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_t5.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_t5.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_transfo_xl.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_transfo_xl.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_transfo_xl.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_transfo_xl.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_utils.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_utils.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_utils.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_utils.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_utils_base.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_utils_base.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_utils_base.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_utils_base.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_utils_fast.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_utils_fast.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_utils_fast.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_utils_fast.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_xlm.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_xlm.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_xlm.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_xlm.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_xlm_roberta.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_xlm_roberta.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_xlm_roberta.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_xlm_roberta.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_xlnet.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_xlnet.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/tokenization_xlnet.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/tokenization_xlnet.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/trainer.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/trainer.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/trainer.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/trainer.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/trainer_tf.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/trainer_tf.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/trainer_utils.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/trainer_utils.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/trainer_utils.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/trainer_utils.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/training_args.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/training_args.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/training_args.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/training_args.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/training_args_tf.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/training_args_tf.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/__pycache__/training_args_tf.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/__pycache__/training_args_tf.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/benchmark/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/benchmark/__init__.py -------------------------------------------------------------------------------- /transformers/src/transformers/benchmark/__pycache__/__init__.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/benchmark/__pycache__/__init__.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/benchmark/__pycache__/__init__.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/benchmark/__pycache__/__init__.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/benchmark/__pycache__/benchmark.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/benchmark/__pycache__/benchmark.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/benchmark/__pycache__/benchmark.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/benchmark/__pycache__/benchmark.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/benchmark/__pycache__/benchmark_args.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/benchmark/__pycache__/benchmark_args.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/benchmark/__pycache__/benchmark_args.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/benchmark/__pycache__/benchmark_args.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/benchmark/__pycache__/benchmark_args_tf.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/benchmark/__pycache__/benchmark_args_tf.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/benchmark/__pycache__/benchmark_args_utils.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/benchmark/__pycache__/benchmark_args_utils.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/benchmark/__pycache__/benchmark_args_utils.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/benchmark/__pycache__/benchmark_args_utils.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/benchmark/__pycache__/benchmark_tf.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/benchmark/__pycache__/benchmark_tf.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/benchmark/__pycache__/benchmark_utils.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/benchmark/__pycache__/benchmark_utils.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/benchmark/__pycache__/benchmark_utils.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/benchmark/__pycache__/benchmark_utils.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/commands/__init__.py: -------------------------------------------------------------------------------- 1 | from abc import ABC, abstractmethod 2 | from argparse import ArgumentParser 3 | 4 | 5 | class BaseTransformersCLICommand(ABC): 6 | @staticmethod 7 | @abstractmethod 8 | def register_subcommand(parser: ArgumentParser): 9 | raise NotImplementedError() 10 | 11 | @abstractmethod 12 | def run(self): 13 | raise NotImplementedError() 14 | -------------------------------------------------------------------------------- /transformers/src/transformers/data/__init__.py: -------------------------------------------------------------------------------- 1 | # flake8: noqa 2 | # There's no way to ignore "F401 '...' imported but unused" warnings in this 3 | # module, but to preserve other warnings. So, don't check this module at all. 4 | 5 | from .metrics import is_sklearn_available 6 | from .processors import ( 7 | DataProcessor, 8 | InputExample, 9 | InputFeatures, 10 | SingleSentenceClassificationProcessor, 11 | SquadExample, 12 | SquadFeatures, 13 | SquadV1Processor, 14 | SquadV2Processor, 15 | glue_convert_examples_to_features, 16 | glue_output_modes, 17 | glue_processors, 18 | glue_tasks_num_labels, 19 | squad_convert_examples_to_features, 20 | xnli_output_modes, 21 | xnli_processors, 22 | xnli_tasks_num_labels, 23 | ) 24 | 25 | 26 | if is_sklearn_available(): 27 | from .metrics import glue_compute_metrics, xnli_compute_metrics 28 | -------------------------------------------------------------------------------- /transformers/src/transformers/data/__pycache__/__init__.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/data/__pycache__/__init__.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/data/__pycache__/__init__.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/data/__pycache__/__init__.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/data/__pycache__/data_collator.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/data/__pycache__/data_collator.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/data/__pycache__/data_collator.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/data/__pycache__/data_collator.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/data/datasets/__init__.py: -------------------------------------------------------------------------------- 1 | # flake8: noqa 2 | # There's no way to ignore "F401 '...' imported but unused" warnings in this 3 | # module, but to preserve other warnings. So, don't check this module at all. 4 | 5 | from .glue import GlueDataset, GlueDataTrainingArguments 6 | from .language_modeling import ( 7 | LineByLineTextDataset, 8 | LineByLineWithSOPTextDataset, 9 | TextDataset, 10 | TextDatasetForNextSentencePrediction, 11 | ) 12 | from .squad import SquadDataset, SquadDataTrainingArguments 13 | -------------------------------------------------------------------------------- /transformers/src/transformers/data/datasets/__pycache__/__init__.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/data/datasets/__pycache__/__init__.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/data/datasets/__pycache__/__init__.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/data/datasets/__pycache__/__init__.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/data/datasets/__pycache__/glue.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/data/datasets/__pycache__/glue.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/data/datasets/__pycache__/glue.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/data/datasets/__pycache__/glue.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/data/datasets/__pycache__/language_modeling.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/data/datasets/__pycache__/language_modeling.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/data/datasets/__pycache__/language_modeling.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/data/datasets/__pycache__/language_modeling.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/data/datasets/__pycache__/squad.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/data/datasets/__pycache__/squad.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/data/datasets/__pycache__/squad.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/data/datasets/__pycache__/squad.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/data/metrics/__pycache__/__init__.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/data/metrics/__pycache__/__init__.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/data/metrics/__pycache__/__init__.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/data/metrics/__pycache__/__init__.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/data/processors/__init__.py: -------------------------------------------------------------------------------- 1 | # flake8: noqa 2 | # There's no way to ignore "F401 '...' imported but unused" warnings in this 3 | # module, but to preserve other warnings. So, don't check this module at all. 4 | 5 | from .glue import glue_convert_examples_to_features, glue_output_modes, glue_processors, glue_tasks_num_labels 6 | from .squad import SquadExample, SquadFeatures, SquadV1Processor, SquadV2Processor, squad_convert_examples_to_features 7 | from .utils import DataProcessor, InputExample, InputFeatures, SingleSentenceClassificationProcessor 8 | from .xnli import xnli_output_modes, xnli_processors, xnli_tasks_num_labels 9 | -------------------------------------------------------------------------------- /transformers/src/transformers/data/processors/__pycache__/__init__.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/data/processors/__pycache__/__init__.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/data/processors/__pycache__/__init__.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/data/processors/__pycache__/__init__.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/data/processors/__pycache__/glue.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/data/processors/__pycache__/glue.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/data/processors/__pycache__/glue.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/data/processors/__pycache__/glue.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/data/processors/__pycache__/squad.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/data/processors/__pycache__/squad.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/data/processors/__pycache__/squad.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/data/processors/__pycache__/squad.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/data/processors/__pycache__/utils.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/data/processors/__pycache__/utils.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/data/processors/__pycache__/utils.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/data/processors/__pycache__/utils.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/data/processors/__pycache__/xnli.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/data/processors/__pycache__/xnli.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/data/processors/__pycache__/xnli.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/data/processors/__pycache__/xnli.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/utils/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/utils/__init__.py -------------------------------------------------------------------------------- /transformers/src/transformers/utils/__pycache__/__init__.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/utils/__pycache__/__init__.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/utils/__pycache__/__init__.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/utils/__pycache__/__init__.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/utils/__pycache__/logging.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/utils/__pycache__/logging.cpython-37.pyc -------------------------------------------------------------------------------- /transformers/src/transformers/utils/__pycache__/logging.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/src/transformers/utils/__pycache__/logging.cpython-38.pyc -------------------------------------------------------------------------------- /transformers/templates/adding_a_new_example_script/README.md: -------------------------------------------------------------------------------- 1 | # How to add a new example script in 🤗Transformers 2 | 3 | This folder provide a template for adding a new example script implementing a training or inference task with the models in the 🤗Transformers library. 4 | Add tests! 5 | 6 | 7 | These folder can be put in a subdirectory under your example's name, like `examples/deebert`. 8 | 9 | 10 | Best Practices: 11 | - use `Trainer`/`TFTrainer` 12 | - write an @slow test that checks that your model can train on one batch and get a low loss. 13 | - this test should use cuda if it's available. (e.g. by checking `transformers.torch_device`) 14 | - adding an `eval_xxx.py` script that can evaluate a pretrained checkpoint. 15 | - tweet about your new example with a carbon screenshot of how to run it and tag @huggingface 16 | -------------------------------------------------------------------------------- /transformers/tests/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/tests/__init__.py -------------------------------------------------------------------------------- /transformers/tests/conftest.py: -------------------------------------------------------------------------------- 1 | # tests directory-specific settings - this file is run automatically 2 | # by pytest before any tests are run 3 | 4 | import sys 5 | import warnings 6 | from os.path import abspath, dirname, join 7 | 8 | 9 | # allow having multiple repository checkouts and not needing to remember to rerun 10 | # 'pip install -e .[dev]' when switching between checkouts and running tests. 11 | git_repo_path = abspath(join(dirname(dirname(__file__)), "src")) 12 | sys.path.insert(1, git_repo_path) 13 | 14 | 15 | # silence FutureWarning warnings in tests since often we can't act on them until 16 | # they become normal warnings - i.e. the tests still need to test the current functionality 17 | warnings.simplefilter(action="ignore", category=FutureWarning) 18 | -------------------------------------------------------------------------------- /transformers/tests/fixtures/dummy-config.json: -------------------------------------------------------------------------------- 1 | { 2 | "model_type": "roberta" 3 | } -------------------------------------------------------------------------------- /transformers/tests/fixtures/empty.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/tests/fixtures/empty.txt -------------------------------------------------------------------------------- /transformers/tests/fixtures/input.txt: -------------------------------------------------------------------------------- 1 | Who was Jim Henson ? ||| Jim Henson was a puppeteer 2 | -------------------------------------------------------------------------------- /transformers/tests/fixtures/spiece.model: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/tests/fixtures/spiece.model -------------------------------------------------------------------------------- /transformers/tests/fixtures/test_sentencepiece.model: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SALT-NLP/Structure-Aware-BART/90419667a9d1034bcb064312722aeadb0635ee20/transformers/tests/fixtures/test_sentencepiece.model -------------------------------------------------------------------------------- /transformers/tests/fixtures/tests_samples/.gitignore: -------------------------------------------------------------------------------- 1 | *.* 2 | cache* 3 | temp* 4 | !*.txt 5 | !*.tsv 6 | !*.json 7 | !.gitignore -------------------------------------------------------------------------------- /transformers/tests/fixtures/tests_samples/GermEval/labels.txt: -------------------------------------------------------------------------------- 1 | B-LOC 2 | B-LOCderiv 3 | B-LOCpart 4 | B-ORG 5 | B-ORGderiv 6 | B-ORGpart 7 | B-OTH 8 | B-OTHderiv 9 | B-OTHpart 10 | B-PER 11 | B-PERderiv 12 | B-PERpart 13 | I-LOC 14 | I-LOCderiv 15 | I-LOCpart 16 | I-ORG 17 | I-ORGderiv 18 | I-ORGpart 19 | I-OTH 20 | I-OTHderiv 21 | I-OTHpart 22 | I-PER 23 | I-PERderiv 24 | I-PERpart 25 | O 26 | -------------------------------------------------------------------------------- /transformers/tests/test_activations_tf.py: -------------------------------------------------------------------------------- 1 | import unittest 2 | 3 | from transformers import is_tf_available 4 | from transformers.testing_utils import require_tf 5 | 6 | 7 | if is_tf_available(): 8 | from transformers.activations_tf import get_tf_activation 9 | 10 | 11 | @require_tf 12 | class TestTFActivations(unittest.TestCase): 13 | def test_get_activation(self): 14 | get_tf_activation("swish") 15 | get_tf_activation("gelu") 16 | get_tf_activation("relu") 17 | get_tf_activation("tanh") 18 | get_tf_activation("gelu_new") 19 | get_tf_activation("gelu_fast") 20 | get_tf_activation("mish") 21 | with self.assertRaises(KeyError): 22 | get_tf_activation("bogus") 23 | with self.assertRaises(KeyError): 24 | get_tf_activation(None) 25 | --------------------------------------------------------------------------------