PKU-Alignment/safe-rlhf
▲ +3 ★ this week
Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback
BeaverTails is a collection of datasets designed to facilitate research on safety alignment in large language models (LLMs).
$ git clone https://github.com/PKU-Alignment/beavertails.git▲ +3 ★ this week
Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback
▲ +6 ★ this week
Build a modern LLM from scratch. Every line commented. Explained like we are five.
InternLM-XComposer2.5-OmniLive: A Comprehensive Multimodal System for Long-term Streaming Video and Audio Interactions
A complete guide to start and improve your LLM skills in 2026 with little background in the field and stay up-to-date with the latest news and state-of-the-art techniques!
[COLM 2024] OpenAgents: An Open Platform for Language Agents in the Wild
▲ +25 ★ this week
Harness LLMs with Multi-Agent Programming
Data from GitHub · snapshot Nov 16, 2026