teddysum / korean_evaluationLinks
☆10Updated last month
Alternatives and similar repositories for korean_evaluation
Users that are interested in korean_evaluation are comparing it to the libraries listed below
Sorting:
- ☆32Updated last year
- Google 공식 Rouge Implementation을 한국어에서 사용할 수 있도록 처리☆16Updated last year
- ☆35Updated last year
- For the rlhf learning environment of Koreans☆23Updated last year
- StrategyQA 데이터 세트 번역☆22Updated last year
- ☆10Updated 8 months ago
- 한국어 T5 모델☆54Updated 3 years ago
- KLUE Benchmark 1st place (2021.12) solutions. (RE, MRC, NLI, STS, TC)☆25Updated 3 years ago
- A utility for storing and reading files for Korean LM training 💾☆36Updated last year
- Beyond LM: How can language model go forward in the future?☆15Updated 2 years ago
- Hate speech detection corpus in Korean, shared with EMNLP 2023 paper☆15Updated last year
- #인권코퍼스☆32Updated last year
- ☆19Updated 2 years ago
- Korean Named Entity Corpus☆25Updated 2 years ago
- NSMC, KorSTS ... fine-tunings☆19Updated 3 years ago
- ☆28Updated 2 years ago
- ☆20Updated 3 years ago
- Adversarial Test Dataset for Korean Multi-turn Response Selection☆35Updated 3 years ago
- KoRean based ELECTRA pre-trained models (KR-ELECTRA) for Tensorflow and PyTorch☆15Updated 3 years ago
- kogpt를 oslo로 파인튜닝하는 예제.☆23Updated 2 years ago
- ☆36Updated last year
- bpe based korean t5 model for text-to-text unified framework☆63Updated last year
- Reward Model을 이용하여 언어모델의 답변을 평가하기☆29Updated last year
- 언어모델을 학습하기 위한 공개 한국어 instruction dataset들을 모아두었습니다.☆19Updated 2 years ago
- 문장단위로 분절된 한국어 위키피디아 코퍼스. Releases에서 다운로드 받거나 tfds-korean으로 사용해주세요.☆24Updated last year
- [Findings of NAACL2022] A Dog Is Passing Over The Jet? A Text-Generation Dataset for Korean Commonsense Reasoning and Evaluation☆27Updated 2 years ago
- Korean Commonsense Knowledge Graph☆14Updated 2 years ago
- 한국어 어휘 의미 분석 모델☆21Updated 3 years ago
- Difference-based Contrastive Learning for Korean Sentence Embeddings☆25Updated 2 years ago
- 한국어 생성 모델의 상식 추론을 위한 KommonGen 데이터셋입니다.☆19Updated 3 years ago