# Huggingface LLM Trainer

Train or fine-tune language and vision models using TRL (Transformer Reinforcement...

- Repository: https://github.com/huggingface/skills (11249 stars)
- Category: Data and ML
- License: Complete terms in LICENSE.txt
- Last updated: 2026-10-30
- Runs scripts: yes, review before use

## Install

Claude Code: `npx skills add huggingface/skills --skill huggingface-llm-trainer -g -a claude-code -y`
Codex: `npx skills add huggingface/skills --skill huggingface-llm-trainer -g -a codex -y`
Cursor: `npx skills add huggingface/skills --skill huggingface-llm-trainer -g -a cursor -y`
Gemini CLI: `npx skills add huggingface/skills --skill huggingface-llm-trainer -g -a gemini-cli -y`
Claude Code plugin marketplace: `/plugin marketplace add huggingface/skills`

## Description

Train or fine-tune language and vision models using TRL (Transformer Reinforcement Learning) or Unsloth with Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scripts with PEP 723 format, dataset preparation and validation, hardware selection, cost estimation, Trackio monitoring, Hub authentication, model selection/leaderboards and model persistence. Use for tasks involving cloud GPU training, GGUF conversion, or when users mention training on Hugging Face Jobs without local GPU setup.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# TRL Training on Hugging Face Jobs

## Overview

Train language models using TRL (Transformer Reinforcement Learning) on fully managed Hugging Face infrastructure. No local GPU setup required, models train on cloud GPUs and results are automatically saved to the Hugging Face Hub.

**TRL provides multiple training methods:**
- **SFT** (Supervised Fine-Tuning) - Standard instruction tuning
- **DPO** (Direct Preference Optimization) - Alignment from preference data
- **GRPO** (Group Relative Policy Optimization) - Online RL training
- **Reward Modeling** - Train reward models for RLHF

**For detailed TRL method documentation:**
```python
hf_doc_search("your query", product="trl")
hf_doc_fetch("https://huggingface.co/docs/trl/sft_trainer")  # SFT
hf_doc_fetch("https://huggingface.co/docs/trl/dpo_trainer")  # DPO
# etc.
```

**See also:** `references/training_methods.md` for method overviews and selection guidance

## When to Use This Skill

Use this skill when users want to:
- Fine-tune language models on cloud GPUs without local infrastructure
- Train with TRL methods (SFT, DPO, GRPO, etc.)
- Run training jobs on Hugging Face Jobs infrastructure
- Convert trained models to GGUF for local deployment (Ollama, LM Studio, llama.cpp)
- Ensure trained models are permanently saved to the Hub
- Use modern workflows with optimized defaults

### When to Use Unsloth

Use **Unsloth** (`references/unsloth.md`) instead of standard TRL when:
- **Limited GPU memory** - Unsloth uses ~60% less VRAM
- **Speed matters** - Unsloth is ~2x faster
- Training **large models (>13B)** - memory efficiency is critical
- Training **Vision-Language Models (VLMs)** - Unsloth has `FastVisionModel` support

See `references/unsloth.md` for complete Unsloth documentation and `scripts/unsloth_sft_example.py` for a production-ready training script.

## Key Directives

When assisting with training jobs:

The rest: https://github.com/huggingface/skills/blob/HEAD/skills/huggingface-llm-trainer/SKILL.md