domains / research / post-training
| Skill | Kind | Repository |
|---|---|---|
| grpo-rl-training | separate | Orchestra-Research/AI-Research-SKILLs |
| miles | separate | Orchestra-Research/AI-Research-SKILLs |
| openrlhf | separate | Orchestra-Research/AI-Research-SKILLs |
| simpo | separate | Orchestra-Research/AI-Research-SKILLs |
| slime | separate | Orchestra-Research/AI-Research-SKILLs |
| torchforge | separate | Orchestra-Research/AI-Research-SKILLs |
| trl-fine-tuning | separate | Orchestra-Research/AI-Research-SKILLs |
| verl | separate | Orchestra-Research/AI-Research-SKILLs |