# 커뮤니티

이 페이지는 커뮤니티에서 개발한 🤗 Transformers 관련 리소스를 모아 제공합니다.

## 커뮤니티 리소스

| 리소스     |      설명      |      저자      |
|:----------|:-------------|------:|
| [Hugging Face Transformers 용어집 플래시카드](https://www.darigovresearch.com/huggingface-transformers-glossary-flashcards) | [Transformers Docs Glossary](glossary)를 기반으로 한 플래시카드 세트입니다. 장기적인 지식 유지에 특화된 오픈 소스 크로스 플랫폼 앱인 [Anki](https://apps.ankiweb.net/)를 사용하여 쉽게 학습하고 복습할 수 있는 형태로 구성되었습니다. 플래시카드 사용법에 대한 [소개 영상](https://www.youtube.com/watch?v=Dji_h7PILrw)을 참고하세요. | [Darigov Research](https://www.darigovresearch.com/) |

## 커뮤니티 노트북

| 노트북     |      설명      |      저자      |      |
|:----------|:-------------|:-------------|------:|
| [학습된 Transformer를 미세 조정하여 가사 생성](https://github.com/AlekseyKorshuk/huggingartists) | 좋아하는 아티스트의 스타일로 가사를 생성하는 방법: GPT-2 모델 파인튜닝 |  [Aleksey Korshuk](https://github.com/AlekseyKorshuk) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/AlekseyKorshuk/huggingartists/blob/master/huggingartists-demo.ipynb) |
| [TPU에서 T5 학습](https://github.com/patil-suraj/exploring-T5/blob/master/T5_on_TPU.ipynb)  | Transformers와 Nlp를 사용하여 SQUAD에서 T5를 학습하는 방법 | [Suraj Patil](https://github.com/patil-suraj) |[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/patil-suraj/exploring-T5/blob/master/T5_on_TPU.ipynb#scrollTo=QLGiFCDqvuil) |
| [분류 및 다중 선택을 위한 T5 파인튜닝](https://github.com/patil-suraj/exploring-T5/blob/master/t5_fine_tuning.ipynb)  | PyTorch Lightning을 사용하여 텍스트-텍스트 형식으로 T5를 분류 및 다중 선택 작업에 대해 미세 조정하는 방법 |  [Suraj Patil](https://github.com/patil-suraj) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/patil-suraj/exploring-T5/blob/master/t5_fine_tuning.ipynb) |
| [새로운 데이터셋과 언어로 DialoGPT 파인튜닝](https://github.com/ncoop57/i-am-a-nerd/blob/master/_notebooks/2020-05-12-chatbot-part-1.ipynb)  | 새로운 데이터셋에서 오픈 다이얼로그 대화형 챗봇을 위해 DialoGPT 모델을 파인튜닝하는 방법 |  [네이던 쿠퍼](https://github.com/ncoop57) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/ncoop57/i-am-a-nerd/blob/master/_notebooks/2020-05-12-chatbot-part-1.ipynb) |
| [Reformer를 활용한 긴 시퀀스 모델링](https://github.com/patrickvonplaten/notebooks/blob/master/PyTorch_Reformer.ipynb)  | Reformer를 사용하여 500,000 토큰까지 긴 시퀀스로 학습하는 방법 |  [Patrick von Platen](https://github.com/patrickvonplaten) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/patrickvonplaten/notebooks/blob/master/PyTorch_Reformer.ipynb)  |
| [요약 작업을 위한 BART 파인튜닝](https://github.com/ohmeow/ohmeow_website/blob/master/posts/2021-05-25-mbart-sequence-classification-with-blurr.ipynb) | blurr를 사용하여 fastai로 BART를 요약 작업에 대해 미세 조정하는 방법 | [Wayde Gilliam](https://ohmeow.com/) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/ohmeow/ohmeow_website/blob/master/posts/2021-05-25-mbart-sequence-classification-with-blurr.ipynb) |
| [누군가의 트윗으로 사전 학습된 Transformer를 미세 조정하기](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb) | 좋아하는 Twitter 계정의 스타일로 트윗을 생성하는 방법: GPT-2 모델 파인튜닝 |  [Boris Dayma](https://github.com/borisdayma) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb) |
| [Weights & Biases로 🤗 Hugging Face 모델 최적화](https://colab.research.google.com/github/wandb/examples/blob/master/colabs/huggingface/Optimize_Hugging_Face_models_with_Weights_%26_Biases.ipynb) | Hugging Face와 W&B 통합을 보여주는 완전한 튜토리얼 | [Boris Dayma](https://github.com/borisdayma) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/wandb/examples/blob/master/colabs/huggingface/Optimize_Hugging_Face_models_with_Weights_%26_Biases.ipynb) |
| [Longformer 사전 학습](https://github.com/allenai/longformer/blob/master/scripts/convert_model_to_long.ipynb)  | 기존 사전 학습 모델의 "긴" 버전을 구축하는 방법 |  [Iz Beltagy](https://beltagy.net) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/allenai/longformer/blob/master/scripts/convert_model_to_long.ipynb) |
| [Longformer를 QA로 Fine-tune](https://github.com/patil-suraj/Notebooks/blob/master/longformer_qa_training.ipynb) | QA 작업용 longformer 모델 파인튜닝 방법 | [Suraj Patil](https://github.com/patil-suraj) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/patil-suraj/Notebooks/blob/master/longformer_qa_training.ipynb) |
| [🤗nlp로 모델 평가하기](https://github.com/patrickvonplaten/notebooks/blob/master/How_to_evaluate_Longformer_on_TriviaQA_using_NLP.ipynb) | `nlp`를 사용하여 TriviaQA에서 longformer를 평가하는 방법 | [Patrick von Platen](https://github.com/patrickvonplaten) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1m7eTGlPmLRgoPkkA7rkhQdZ9ydpmsdLE?usp=sharing) |
| [T5를 감정 스팬 추출을 위해 파인튜닝하기](https://github.com/enzoampil/t5-intro/blob/master/t5_qa_training_pytorch_span_extraction.ipynb)  | PyTorch Lightning을 사용하여 텍스트-텍스트 형식으로 T5를 감정 스팬 추출에 대해 미세 조정하는 방법 |  [로렌조 암필](https://github.com/enzoampil) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/enzoampil/t5-intro/blob/master/t5_qa_training_pytorch_span_extraction.ipynb) |
| [다중 클래스 분류를 위한 DistilBert 파인튜닝](https://github.com/abhimishra91/transformers-tutorials/blob/master/transformers_multiclass_classification.ipynb) | PyTorch로 DistilBert를 다중 클래스 분류에 맞게 미세 조정하는 방법 | [Abhishek Kumar Mishra](https://github.com/abhimishra91) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/abhimishra91/transformers-tutorials/blob/master/transformers_multiclass_classification.ipynb)|
|[멀티 라벨 분류를 위한 BERT 파인튜닝](https://github.com/abhimishra91/transformers-tutorials/blob/master/transformers_multi_label_classification.ipynb)|PyTorch를 사용하여 BERT를 다중 레이블 분류에 대해 미세 조정하는 방법|[Abhishek Kumar Mishra](https://github.com/abhimishra91) |[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/abhimishra91/transformers-tutorials/blob/master/transformers_multi_label_classification.ipynb)|
|[요약 작업을 위한 T5 파인튜닝](https://github.com/abhimishra91/transformers-tutorials/blob/master/transformers_summarization_wandb.ipynb)|PyTorch로 T5를 요약 작업에 fine-tune하고 WandB로 실험을 추적하는 방법|[Abhishek Kumar Mishra](https://github.com/abhimishra91) |[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/abhimishra91/transformers-tutorials/blob/master/transformers_summarization_wandb.ipynb)|
|[Transformers에서 Dynamic Padding / Bucketing으로 Fine-Tuning 속도 향상](https://github.com/ELS-RD/transformers-notebook/blob/master/Divide_Hugging_Face_Transformers_training_time_by_2_or_more.ipynb)|dynamic padding / bucketing를 사용하여 미세 조정을 2배로 가속하는 방법|[Michael Benesty](https://github.com/pommedeterresautee) |[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1CBfRU1zbfu7-ijiOqAAQUA-RJaxfcJoO?usp=sharing)|
|[Reformer를 Masked Language Modeling을 위해 사전 학습하기](https://github.com/patrickvonplaten/notebooks/blob/master/Reformer_For_Masked_LM.ipynb)| 양방향 셀프 어텐션 레이어를 사용하여 Reformer 모델을 학습하는 방법 | [Patrick von Platen](https://github.com/patrickvonplaten) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1tzzh0i8PgDQGV3SMFUGxM7_gGae3K-uW?usp=sharing)|
|[Sci-BERT 확장 및 세부 조정](https://github.com/lordtt13/word-embeddings/blob/master/COVID-19%20Research%20Data/COVID-SciBERT.ipynb)| AllenAI의 사전 학습된 SciBERT 모델의 어휘를 CORD 데이터셋으로 확장하고 파이프라인을 구성하는 방법 | [Tanmay Thakur](https://github.com/lordtt13) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1rqAR40goxbAfez1xvF3hBJphSCsvXmh8)|
|[Trainer API를 사용하여 BlenderBotSmall을 요약 작업에 대해 Fine Tune하기](https://github.com/lordtt13/transformers-experiments/blob/master/Custom%20Tasks/fine-tune-blenderbot_small-for-summarization.ipynb)| Trainer API를 사용하여 커스텀 데이터셋에서 요약 작업을 위해 BlenderBotSmall을 파인튜닝하는 방법 | [Tanmay Thakur](https://github.com/lordtt13) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/19Wmupuls7mykSGyRN_Qo6lPQhgp56ymq?usp=sharing)|
|[Electra를 Fine-tune하고 Integrated Gradients로 해석하기](https://github.com/elsanns/xai-nlp-notebooks/blob/master/electra_fine_tune_interpret_captum_ig.ipynb) | Electra를 감정 분석에 대해 미세 조정하고 Captum Integrated Gradients로 예측을 해석하는 방법 | [Eliza Szczechla](https://elsanns.github.io) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/elsanns/xai-nlp-notebooks/blob/master/electra_fine_tune_interpret_captum_ig.ipynb)|
|[Trainer 클래스로 비영어권 GPT-2 모델 파인튜닝](https://github.com/philschmid/fine-tune-GPT-2/blob/master/Fine_tune_a_non_English_GPT_2_Model_with_Huggingface.ipynb) | Trainer 클래스를 사용하여 비영어권 GPT-2 모델을 미세 조정하는 방법 | [필립 슈미트](https://www.philschmid.de) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/philschmid/fine-tune-GPT-2/blob/master/Fine_tune_a_non_English_GPT_2_Model_with_Huggingface.ipynb)|
|[멀티 라벨 분류 작업을 위한 DistilBERT 모델 파인튜닝](https://github.com/DhavalTaunk08/Transformers_scripts/blob/master/Transformers_multilabel_distilbert.ipynb) | 멀티 라벨 분류 작업을 위해 DistilBERT 모델을 파인튜닝하는 방법 | [Dhaval Taunk](https://github.com/DhavalTaunk08) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/DhavalTaunk08/Transformers_scripts/blob/master/Transformers_multilabel_distilbert.ipynb)|
|[ALBERT를 문장 쌍 분류를 위해 미세 조정하기](https://github.com/NadirEM/nlp-notebooks/blob/master/Fine_tune_ALBERT_sentence_pair_classification.ipynb) | ALBERT 모델 또는 다른 BERT 기반 모델을 문장 쌍 분류 작업에 대해 미세 조정하는 방법 | [나디르 엘 마누지](https://github.com/NadirEM) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/NadirEM/nlp-notebooks/blob/master/Fine_tune_ALBERT_sentence_pair_classification.ipynb)|
|[감정 분석을 위한 Roberta 파인튜닝](https://github.com/DhavalTaunk08/NLP_scripts/blob/master/sentiment_analysis_using_roberta.ipynb) | 감정 분석을 위한 Roberta 모델 파인튜닝 방법 | [Dhaval Taunk](https://github.com/DhavalTaunk08) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/DhavalTaunk08/NLP_scripts/blob/master/sentiment_analysis_using_roberta.ipynb)|
|[질문 생성 모델 평가](https://github.com/flexudy-pipe/qugeev) | seq2seq transformer 모델이 생성한 질문에 대한 답변의 정확도는 얼마나 될까요? | [파스칼 졸레코](https://github.com/zolekode) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1bpsSqCQU-iw_5nNoRm_crPq6FRuJthq_?usp=sharing)|
|[CNN/Dailymail에서 BERT를 활용한 인코더-디코더 요약](https://github.com/patrickvonplaten/notebooks/blob/master/BERT2BERT_for_CNN_Dailymail.ipynb) | CNN/Dailymail에서 요약 작업을 위해 *google-bert/bert-base-uncased* 체크포인트로 *EncoderDecoderModel*을 워밍 스타트하는 방법 | [Patrick von Platen](https://github.com/patrickvonplaten) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/patrickvonplaten/notebooks/blob/master/BERT2BERT_for_CNN_Dailymail.ipynb)|
|[BBC XSum에서 Encoder-Decoder 요약에 RoBERTa 활용하기](https://github.com/patrickvonplaten/notebooks/blob/master/RoBERTaShared_for_BBC_XSum.ipynb) | BBC/XSum에서 요약 작업을 위해 *FacebookAI/roberta-base* 체크포인트로 공유 *EncoderDecoderModel*을 워밍 스타트하는 방법 | [Patrick von Platen](https://github.com/patrickvonplaten) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/patrickvonplaten/notebooks/blob/master/RoBERTaShared_for_BBC_XSum.ipynb)|
|[순차적 질의응답(SQA)에서 TAPAS 미세 조정](https://github.com/NielsRogge/Transformers-Tutorials/blob/master/TAPAS/Fine_tuning_TapasForQuestionAnswering_on_SQA.ipynb) | Sequential Question Answering(SQA) 데이터셋에서 *tapas-base* 체크포인트를 사용하여 *TapasForQuestionAnswering*를 파인튜닝하는 방법 | [Niels Rogge](https://github.com/nielsrogge) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/NielsRogge/Transformers-Tutorials/blob/master/TAPAS/Fine_tuning_TapasForQuestionAnswering_on_SQA.ipynb)|
|[TabFact(Table Fact Checking)에서 TAPAS 평가](https://github.com/NielsRogge/Transformers-Tutorials/blob/master/TAPAS/Evaluating_TAPAS_on_the_Tabfact_test_set.ipynb) | 🤗 datasets와 🤗 transformers 라이브러리를 조합하여 *tapas-base-finetuned-tabfact* 체크포인트로 파인튜닝된 *TapasForSequenceClassification*를 평가하는 방법 | [Niels Rogge](https://github.com/nielsrogge) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/NielsRogge/Transformers-Tutorials/blob/master/TAPAS/Evaluating_TAPAS_on_the_Tabfact_test_set.ipynb)|
|[번역을 위한 mBART 파인튜닝](https://colab.research.google.com/github/vasudevgupta7/huggingface-tutorials/blob/main/translation_training.ipynb) | Seq2SeqTrainer를 사용하여 힌디어에서 영어로 번역하는 mBART를 파인튜닝하는 방법 | [Vasudev Gupta](https://github.com/vasudevgupta7) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/vasudevgupta7/huggingface-tutorials/blob/main/translation_training.ipynb)|
|[FUNSD(양식 이해 데이터셋)에서 LayoutLM을 파인튜닝합니다](https://github.com/NielsRogge/Transformers-Tutorials/blob/master/LayoutLM/Fine_tuning_LayoutLMForTokenClassification_on_FUNSD.ipynb) | 스캔된 문서에서 정보 추출을 위해 FUNSD 데이터셋으로 *LayoutLMForTokenClassification*를 미세 조정하는 방법 | [Niels Rogge](https://github.com/nielsrogge) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/NielsRogge/Transformers-Tutorials/blob/master/LayoutLM/Fine_tuning_LayoutLMForTokenClassification_on_FUNSD.ipynb)|
|[DistilGPT2 파인튜닝 및 텍스트 생성](https://colab.research.google.com/github/tripathiaakash/DistilGPT2-Tutorial/blob/main/distilgpt2_fine_tuning.ipynb) | DistilGPT2를 파인튜닝하고 텍스트를 생성하는 방법 | [Aakash Tripathi](https://github.com/tripathiaakash) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/tripathiaakash/DistilGPT2-Tutorial/blob/main/distilgpt2_fine_tuning.ipynb)|
|[최대 8K 토큰으로 LED 파인튜닝](https://github.com/patrickvonplaten/notebooks/blob/master/Fine_tune_Longformer_Encoder_Decoder_(LED)_for_Summarization_on_pubmed.ipynb) | pubmed에서 LED를 장거리 요약(fine-tune)하는 방법 | [Patrick von Platen](https://github.com/patrickvonplaten) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/patrickvonplaten/notebooks/blob/master/Fine_tune_Longformer_Encoder_Decoder_(LED)_for_Summarization_on_pubmed.ipynb)|
|[Arxiv에서 LED 평가](https://github.com/patrickvonplaten/notebooks/blob/master/LED_on_Arxiv.ipynb) | 장거리 요약에서 LED를 효과적으로 평가하는 방법 | [Patrick von Platen](https://github.com/patrickvonplaten) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/patrickvonplaten/notebooks/blob/master/LED_on_Arxiv.ipynb)|
|[RVL-CDIP(문서 이미지 분류 데이터셋)에서 LayoutLM 파인튜닝](https://github.com/NielsRogge/Transformers-Tutorials/blob/master/LayoutLM/Fine_tuning_LayoutLMForSequenceClassification_on_RVL_CDIP.ipynb) | RVL-CDIP 데이터셋에서 스캔된 문서 분류를 위해 *LayoutLMForSequenceClassification*을 미세 조정하는 방법 | [Niels Rogge](https://github.com/nielsrogge) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/NielsRogge/Transformers-Tutorials/blob/master/LayoutLM/Fine_tuning_LayoutLMForSequenceClassification_on_RVL_CDIP.ipynb)|
|[GPT2 조정을 사용한 Wav2Vec2 CTC 디코딩](https://github.com/voidful/huggingface_notebook/blob/main/xlsr_gpt.ipynb) | CTC 시퀀스를 언어 모델 보정으로 디코딩하는 방법 | [Eric Lam](https://github.com/voidful) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1e_z5jQHYbO2YKEaUgzb1ww1WwiAyydAj?usp=sharing)|
|[Trainer 클래스를 사용하여 BART를 두 언어 요약에 대해 미세 조정하기](https://github.com/elsanns/xai-nlp-notebooks/blob/master/fine_tune_bart_summarization_two_langs.ipynb) | Trainer 클래스를 사용하여 BART를 두 언어로 요약하도록 미세 조정하는 방법 | [Eliza Szczechla](https://github.com/elsanns) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/elsanns/xai-nlp-notebooks/blob/master/fine_tune_bart_summarization_two_langs.ipynb)|
|[Trivia QA에서 Big Bird 평가](https://github.com/patrickvonplaten/notebooks/blob/master/Evaluating_Big_Bird_on_TriviaQA.ipynb) | Trivia QA에서 긴 문서 질의응답으로 BigBird를 평가하는 방법 | [Patrick von Platen](https://github.com/patrickvonplaten) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/patrickvonplaten/notebooks/blob/master/Evaluating_Big_Bird_on_TriviaQA.ipynb)|
| [Wav2Vec2를 사용하여 비디오 캡션 생성](https://github.com/Muennighoff/ytclipcc/blob/main/wav2vec_youtube_captions.ipynb) | Wav2Vec로 오디오를 전사하여 모든 비디오에서 YouTube 자막을 만드는 방법 | [Niklas Muennighoff](https://github.com/Muennighoff) |[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Muennighoff/ytclipcc/blob/main/wav2vec_youtube_captions.ipynb) |
| [PyTorch Lightning을 사용하여 CIFAR-10에서 Vision Transformer를 Fine-tune하기](https://github.com/NielsRogge/Transformers-Tutorials/blob/master/VisionTransformer/Fine_tuning_the_Vision_Transformer_on_CIFAR_10_with_PyTorch_Lightning.ipynb) | HuggingFace Transformers, Datasets 및 PyTorch Lightning을 사용하여 CIFAR-10에서 Vision Transformer(ViT)를 미세 조정하는 방법 | [Niels Rogge](https://github.com/nielsrogge) |[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/NielsRogge/Transformers-Tutorials/blob/master/VisionTransformer/Fine_tuning_the_Vision_Transformer_on_CIFAR_10_with_PyTorch_Lightning.ipynb) |
| [🤗 Trainer를 사용하여 CIFAR-10에서 Vision Transformer를 Fine-tune하기](https://github.com/NielsRogge/Transformers-Tutorials/blob/master/VisionTransformer/Fine_tuning_the_Vision_Transformer_on_CIFAR_10_with_the_%F0%9F%A4%97_Trainer.ipynb) | HuggingFace Transformers, Datasets 및 🤗 Trainer를 사용하여 CIFAR-10에서 Vision Transformer(ViT)를 fine-tune하는 방법 | [Niels Rogge](https://github.com/nielsrogge) |[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/NielsRogge/Transformers-Tutorials/blob/master/VisionTransformer/Fine_tuning_the_Vision_Transformer_on_CIFAR_10_with_the_%F0%9F%A4%97_Trainer.ipynb) |
| [엔티티 타이핑 데이터셋인 Open Entity에서 LUKE 평가](https://github.com/studio-ousia/luke/blob/master/notebooks/huggingface_open_entity.ipynb) | Open Entity 데이터셋에서 *LukeForEntityClassification*을 평가하는 방법 | [Ikuya Yamada](https://github.com/ikuyamada) |[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/studio-ousia/luke/blob/master/notebooks/huggingface_open_entity.ipynb) |
| [관계 추출 데이터셋인 TACRED에서 LUKE 평가](https://github.com/studio-ousia/luke/blob/master/notebooks/huggingface_tacred.ipynb) | TACRED 데이터셋에서 *LukeForEntityPairClassification*를 평가하는 방법 | [Ikuya Yamada](https://github.com/ikuyamada) |[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/studio-ousia/luke/blob/master/notebooks/huggingface_tacred.ipynb) |
| [중요한 NER 벤치마크인 CoNLL-2003에서 LUKE 평가](https://github.com/studio-ousia/luke/blob/master/notebooks/huggingface_conll_2003.ipynb) | CoNLL-2003 데이터셋에서 *LukeForEntitySpanClassification*를 평가하는 방법 | [Ikuya Yamada](https://github.com/ikuyamada) |[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/studio-ousia/luke/blob/master/notebooks/huggingface_conll_2003.ipynb) |
| [PubMed 데이터셋에서 BigBird-Pegasus 평가](https://github.com/vasudevgupta7/bigbird/blob/main/notebooks/bigbird_pegasus_evaluation.ipynb) | PubMed 데이터셋에서 *BigBirdPegasusForConditionalGeneration*을 평가하는 방법 | [Vasudev Gupta](https://github.com/vasudevgupta7) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/vasudevgupta7/bigbird/blob/main/notebooks/bigbird_pegasus_evaluation.ipynb) |
| [Wav2Vec2를 활용한 음성 감정 분류](https://github.com/m3hrdadfi/soxan/blob/main/notebooks/Emotion_recognition_in_Greek_speech_using_Wav2Vec2.ipynb) | MEGA 데이터셋에서 감정 분류를 위해 사전 학습된 Wav2Vec2 모델을 활용하는 방법 | [Mehrdad Farahani](https://github.com/m3hrdadfi) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/m3hrdadfi/soxan/blob/main/notebooks/Emotion_recognition_in_Greek_speech_using_Wav2Vec2.ipynb) |
| [DETR를 사용하여 이미지에서 객체 감지](https://github.com/NielsRogge/Transformers-Tutorials/blob/master/DETR/DETR_minimal_example_(with_DetrFeatureExtractor).ipynb) | 학습된 *DetrForObjectDetection* 모델을 사용하여 이미지에서 객체를 감지하고 어텐션을 시각화하는 방법 | [Niels Rogge](https://github.com/NielsRogge) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/NielsRogge/Transformers-Tutorials/blob/master/DETR/DETR_minimal_example_(with_DetrFeatureExtractor).ipynb) |
| [커스텀 객체 감지 데이터셋에서 DETR 파인튜닝](https://github.com/NielsRogge/Transformers-Tutorials/blob/master/DETR/Fine_tuning_DetrForObjectDetection_on_custom_dataset_(balloon).ipynb) | 커스텀 객체 감지 데이터셋에서 *DetrForObjectDetection*을 파인튜닝하는 방법 | [Niels Rogge](https://github.com/NielsRogge) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/NielsRogge/Transformers-Tutorials/blob/master/DETR/Fine_tuning_DetrForObjectDetection_on_custom_dataset_(balloon).ipynb) |
| [명사 인식을 위한 T5 파인튜닝](https://github.com/ToluClassics/Notebooks/blob/main/T5_Ner_Finetuning.ipynb) | *T5*를 Named Entity Recognition 작업에 대해 fine-tune하는 방법 | [Ogundepo Odunayo](https://github.com/ToluClassics) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1obr78FY_cBmWY5ODViCmzdY6O1KB65Vc?usp=sharing) |
| [MLflow와 PEFT를 사용하여 QLoRA로 오픈소스 LLM 파인튜닝](https://github.com/mlflow/mlflow/blob/master/docs/source/llms/transformers/tutorials/fine-tuning/transformers-peft.ipynb) | [QLoRA](https://github.com/artidoro/qlora)와 [PEFT](https://huggingface.co/docs/peft/en/index)를 사용하여 메모리 효율적인 방식으로 LLM을 파인튜닝하고, [MLflow](https://mlflow.org/docs/latest/llms/transformers/index.html)를 사용하여 실험 추적을 관리하는 방법 | [Yuki Watanabe](https://github.com/B-Step62) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/mlflow/mlflow/blob/master/docs/source/llms/transformers/tutorials/fine-tuning/transformers-peft.ipynb) |