Marker-Inc-Korea / COT_steeringLinks
This repository aims to develop CoT Steering based on CoT without Prompting. It focuses on enhancing the model’s latent reasoning capability without additional training by leveraging Test-Time Scaling techniques.
☆112Updated 2 months ago
Alternatives and similar repositories for COT_steering
Users that are interested in COT_steering are comparing it to the libraries listed below
Sorting:
- LLM 모델의 외국어 토큰 생성을 막는 코드 구현☆79Updated 3 weeks ago
- ☆68Updated last year
- KURE: 고려대학교에서 개발한, 한국어 검색에 특화된 임베딩 모델☆177Updated last month
- 한국어 언어모델 다분야 사고력 벤치마크☆196Updated 10 months ago
- The most modern LLM evaluation toolkit☆70Updated this week
- ☆106Updated 3 weeks ago
- [KO-Platy🥮] Korean-Open-platypus를 활용하여 llama-2-ko를 fine-tuning한 KO-platypus model☆75Updated this week
- Kor-IR: Korean Information Retrieval Benchmark☆89Updated last year
- 구글에서 발표한 Chain-of-Thought Reasoning without Prompting을 코드로 구현한 레포입니다.☆67Updated 11 months ago
- SKT A.X LLM 4.0☆133Updated last month
- IA3방식으로 KoAlpaca를 fine tuning한 한국어 LLM모델☆69Updated 2 years ago
- Korean Sentence Embedding Model Performance Benchmark for RAG☆48Updated 7 months ago
- Benchmark in Korean Context☆135Updated last year
- 한글 텍스트 임베딩 모델 리더보드☆93Updated 10 months ago
- 한국어 의료 분야 특화 챗봇 프로젝트☆32Updated last year
- Forked repo from https://github.com/EleutherAI/lm-evaluation-harness/commit/1f66adc☆80Updated last year
- 한국어 심리 상담 데이터셋☆79Updated 2 years ago
- 42dot LLM consists of a pre-trained language model, 42dot LLM-PLM, and a fine-tuned model, 42dot LLM-SFT, which is trained to respond to …☆130Updated last year
- ☆62Updated last month
- ☆48Updated last year
- Official repository for EXAONE built by LG AI Research☆182Updated last year
- AutoRAG example about benchmarking Korean embeddings.☆38Updated 10 months ago
- Make running benchmark simple yet maintainable, again. Now only supports Korean-based cross-encoder.☆20Updated 2 months ago
- hwplib 패키지 python에서 쉽게 사용 할수 있게 만든 github repo 입니다.☆50Updated 5 months ago
- 사용자가 채팅웹을 통해 자신이 처한 법률적 상황을 제시하면, 입력에 대한 문맥을 모델이 이해하여 가이드라인을 제시하고, 유사한 상황의 판례를 제공하는 웹 서비스입니다. (2023.08.18 서비스 종료)☆49Updated last week
- Official repository for KoMT-Bench built by LG AI Research☆66Updated last year
- ☆41Updated last year
- ☆78Updated last year
- Gunmo-emo-classification: 한국어 감정 다중 분류 모델 제작법☆29Updated last year
- ☆123Updated 2 years ago