읽을거리&정보공유
다른 사람과 나누고 싶은 싶은 뉴스와 정보 등을 공유합니다.
🤗허깅페이스가 허깅챗(HuggingChat)을 공개했습니다!
일전에 소개드렸던 OpenAssistant 모델을 기반으로 서비스를 시작했습니다. 데이터가 많이 모여서 지속적인 개선이 이뤄질지 기대해봅니다. +_+
9bow
HuggingChat
The first open source alternative to ChatGPT. 💪
BZCF | 비즈까페 : 네이버 블로그
Building Systems with the ChatGPT API
Level up your use of LLMs. Learn to break down complex tasks, automate workflows, chain LLM calls, and get better outputs.
Improving mathematical reasoning with process supervision
We’ve trained a model to achieve a new state-of-the-art in mathematical problem solving by rewarding each correct step of reasoning (“process supervision”) instead of simply rewarding the correct final answer (“outcome supervision”). In addition to boosting performance relative to outcome supervisio…
GitHub - openai/prm800k: 800,000 step-level correctness labels on LLM solutions to MATH problems
800,000 step-level correctness labels on LLM solutions to MATH problems - GitHub - openai/prm800k: 800,000 step-level correctness labels on LLM solutions to MATH problems
openai