Post Training Rl: 5 curated resources
Curated material on post training rl within model training.
5 resources · page 1 of 1
TRL - Transformers Reinforcement Learning
by Hugging Face
Find training interfaces for supervised and preference-based adaptation.
Reinforcement Learning from Human Feedback (book)
A conceptual path through reward modeling and post-training methods.
Controlling Reasoning Effort in LLMs (Ahead of AI)
A free Ahead of AI article on training controllable reasoning effort.
DeepSeek-R1: Incentivizing Reasoning via RL (arXiv 2501.12948)
by DeepSeek
Study the reported reinforcement-learning recipe behind DeepSeek-R1.
verl (HybridFlow)
by verl project (originated at ByteDance Seed)
Explore how an RL training framework coordinates generation and optimization.