Running
8
AsyncGRPOTrainer: a stable async RL trainer
🏁
Train language models with async RL using GRPO
None defined yet.
Train language models with async RL using GRPO
Reproducible training recipes built with TRL
Qwen3.5-35B-A3B text-to-SQL episodes over RL training
Display an interactive tracking dashboard
Explore async reinforcement learning with AsyncGRPOTrainer
Estimate optimal max_length for SFT training with token analysis
Display side-by-side code differences
Show weekly PyPI download trends
Inspect and test chat templates for Hugging Face models
Track and visualize data streams in real-time
Estimate GPU memory usage for model training