DAPO: An Open-Source LLM Reinforcement Learning System at Scale
Paper
•
2503.14476
•
Published
•
141
Post-training
-
-
Training language models to follow instructions with human feedback
Paper • 2203.02155 • Published • 24 -
Llama 2: Open Foundation and Fine-Tuned Chat Models
Paper • 2307.09288 • Published • 247 -
The Llama 3 Herd of Models
Paper • 2407.21783 • Published • 116 -
Secrets of RLHF in Large Language Models Part I: PPO
Paper • 2307.04964 • Published • 29 -
Secrets of RLHF in Large Language Models Part II: Reward Modeling
Paper • 2401.06080 • Published • 28 -
Direct Preference Optimization: Your Language Model is Secretly a Reward Model
Paper • 2305.18290 • Published • 63 -
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
Paper • 2501.12948 • Published • 423 -
Understanding R1-Zero-Like Training: A Critical Perspective
Paper • 2503.20783 • Published • 56 -
The Art of Scaling Reinforcement Learning Compute for LLMs
Paper • 2510.13786 • Published • 30 -
Command A: An Enterprise-Ready Large Language Model
Paper • 2504.00698 • Published • 29 -
1.79k
The Smol Training Playbook: The Secrets to Building World-Class LLMs
📝Explore loss curves for training LLMs