daje0601 / CoT-Reasoning_without_PromptingLinks
구글에서 발표한 Chain-of-Thought Reasoning without Prompting을 코드로 구현한 레포입니다.
☆67Updated last year
Alternatives and similar repositories for CoT-Reasoning_without_Prompting
Users that are interested in CoT-Reasoning_without_Prompting are comparing it to the libraries listed below
Sorting:
- ☆108Updated 2 months ago
- [KO-Platy🥮] Korean-Open-platypus를 활용하여 llama-2-ko를 fine-tuning한 KO-platypus model☆75Updated 2 months ago
- The most modern LLM evaluation toolkit☆70Updated last month
- huggingface에 있는 한국어 데이터 세트☆30Updated last year
- AutoRAG example about benchmarking Korean embeddings.☆41Updated last year
- Forked repo from https://github.com/EleutherAI/lm-evaluation-harness/commit/1f66adc☆80Updated last year
- ☆68Updated last year
- Reward Model을 이용하여 언어모델의 답변을 평가하기☆29Updated last year
- Official repository for KoMT-Bench built by LG AI Research☆69Updated last year
- Liner LLM Meetup archive☆71Updated last year
- OpenOrca-KO dataset을 활용하여 llama2를 fine-tuning한 Korean-OpenOrca☆19Updated last year
- 한국어 심리 상담 데이터셋☆78Updated 2 years ago
- This repository aims to develop CoT Steering based on CoT without Prompting. It focuses on enhancing the model’s latent reasoning capabil…☆113Updated 4 months ago
- Kor-IR: Korean Information Retrieval Benchmark☆88Updated last year
- [Google Meet] MLLM Arxiv Casual Talk☆52Updated 2 years ago
- LLM 모델의 외국어 토큰 생성을 막는 코드 구현☆80Updated 2 months ago
- bpe based korean t5 model for text-to-text unified framework☆63Updated last year
- Benchmark in Korean Context☆136Updated 2 years ago
- CLIcK: A Benchmark Dataset of Cultural and Linguistic Intelligence in Korean☆47Updated 10 months ago
- 한국어 언어모델 다분야 사고력 벤치마크☆198Updated last year
- For the rlhf learning environment of Koreans☆25Updated 2 years ago
- ☆64Updated 3 months ago
- 자체 구축한 한국어 평가 데이터셋을 이용한 한국어 모델 평가☆31Updated last year
- IA3방식으로 KoAlpaca를 fine tuning한 한국어 LLM모델☆69Updated 2 years ago
- ☆36Updated 2 years ago
- Korean Sentence Embedding Model Performance Benchmark for RAG☆48Updated 9 months ago
- Train GEMMA on TPU/GPU! (Codebase for training Gemma-Ko Series)☆48Updated last year
- Performs benchmarking on two Korean datasets with minimal time and effort.☆43Updated last week
- StrategyQA 데이터 세트 번역☆22Updated last year
- KURE: 고려대학교에서 개발한, 한국어 검색에 특화된 임베딩 모델☆189Updated last month