Linking pages
Linked pages
- Meet ChatLLaMA: The First Open-Source Implementation of LLaMA Based on Reinforcement Learning from Human Feedback (RLHF) - MarkTechPost https://www.marktechpost.com/2023/02/27/meet-chatllama-the-first-open-source-implementation-of-llama-based-on-reinforcement-learning-from-human-feedback-rlhf/ 1 comment
- [2102.12321] AGENT: A Benchmark for Core Psychological Reasoning https://arxiv.org/abs/2102.12321 0 comments