Skip to main content

Hugging Face Model Trainer

by Hugging Face

Train and fine-tune language models using TRL on Hugging Face Jobs infrastructure with SFT, DPO, and GRPO.

About This Skill

Specialized skill for training and fine-tuning language models using the Transformer Reinforcement Learning (TRL) library on Hugging Face's Jobs infrastructure. Supports Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), Group Relative Policy Optimization (GRPO), and reward model training. Includes dataset preparation, hyperparameter tuning, and model evaluation workflows.

How to Install

# Clone or download the skill to your skills directory git clone https://github.com/alirezarezvani/claude-skills ~/.claude/skills/hugging-face-model-trainer

Or download the SKILL.md file directly and place it in your project's .claude/skills/ directory.

Tags

hugging-facetrainingfine-tuningtrlllm