
ChaiML/gpt2_base_retry_and_continue_12m_reward_model
•
Updated
•
344
•
2
Large language models, Reward Modelling, Proximal Policy Optimization, AI Alignment, LLM Distillation
Welcome to Chai Research's HuggingFace page. We are a consumer-driven research lab, focused on delivering the best conversational AI to millions of users.
We package our latest research on our mobile app Chai. Our open source models and datasets are hosted here on HuggingFace.
We are running a $1 Million competition for fine-tuning and training chat models, join the fun! Competition Discord