Tangerine Indexλ ChatGPT μ΄ν λμ¨ νλ‘λνΈμ μ¬λλ€μ λ°μμ μ£μ΅λλ€.
oat
github.com
πΎ OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.
λΌμ΄λΈλ¬λ¦¬μ€νμμ€
github.com λ°©λ¬ΈμΈλΆ μ¬μ΄νΈGitHub675 μ€νμΈλΆ μ¬μ΄νΈ
μ€μΉΒ·μ°κ²°
곡μ MCP Registry, Homebrew, npm, PyPI, crates.ioμμ μ μ₯μλ λλ©μΈμΌλ‘ λ§μΆ° ν루 ν λ² κ°μ Έμ΅λλ€.
λ°μ (1)
λΉμ·ν νλ‘λνΈ
μ€λͺ μ΄ λΉμ·ν μ
LlamaGym
fine-tune LLM agents with online reinforcement learning
safe-rlhf
Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback
alignment-handbook
Robust recipes to align language models with human and AI preferences
AgileRL
The complete post-training stack for LLMs, plus RL for any problem. SFT, DPO and multi-turn agentic RL, with evolutionary hyperparameter optimization built in.
openrl
Unified Reinforcement Learning Framework
