Agent Skills: model_finetuning

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.

auto-healedID: vuralserhat86/antigravity-agentic-skills/model_finetuning

Install this agent skill to your local

npx skills add vuralserhat86/antigravity-agentic-skills --skill model_finetuning

Skill Files

The files that make up model_finetuning.

Download Skill

More agent skills