grpo-rl-training
orchestra-research903 installs
Fine-tune language models with custom rewards.
About this skill
- Visibility
- Public
- Repository
- orchestra-research/ai-research-skills
- Language
- English
- License
- MIT (from SKILL.md)
- Created
- Oct 16, 2026
- Updated
- Oct 16, 2026
- Files
- 4