# Huggingface LLM trainer

> Huggingface LLM trainer is an open-source agent skill for ai models and llm tooling. Train or fine-tune language and vision models using TRL (Transformer Reinforcement Learning) or Unsloth with Hugging Face Jobs infrastructur. It is available on Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf and Goose.

- **Kind:** Skill
- **Pricing:** Open source
- **Platforms:** Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf, Goose
- **Website:** https://github.com/huggingface/skills/tree/main/skills/huggingface-llm-trainer
- **Repository:** https://github.com/huggingface/skills
- **GitHub stars:** 11,356
- **License:** Apache-2.0
- **Skill name:** huggingface-llm-trainer
- **Collection:** https://github.com/huggingface/skills
- **Categories:** AI models and LLM tooling
- **Listing updated:** 2026-11-17

## About

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.

## When your agent uses it

> 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.

## What it can access

From a static check of the files on GitHub; nothing was run.

- [Runs Python scripts](https://github.com/huggingface/skills/tree/HEAD/skills/huggingface-llm-trainer)
- [Network calls found in its scripts](https://github.com/huggingface/skills/tree/HEAD/skills/huggingface-llm-trainer)
- [License: Apache-2.0](https://github.com/huggingface/skills/tree/HEAD/skills/huggingface-llm-trainer)

## Install

### Claude Code

Copy the skill folder to `~/.claude/skills/huggingface-llm-trainer` to use it in all your projects:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/huggingface/skills.git "$tmp" &&
mkdir -p ~/.claude/skills &&
rm -rf ~/.claude/skills/huggingface-llm-trainer &&
cp -R "$tmp/skills/huggingface-llm-trainer" ~/.claude/skills/huggingface-llm-trainer &&
rm -rf "$tmp"
```

For one project only, put the folder in `.claude/skills/huggingface-llm-trainer` inside it instead.

### Codex

Copy the skill folder to `~/.agents/skills/huggingface-llm-trainer` to use it in every repository:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/huggingface/skills.git "$tmp" &&
mkdir -p ~/.agents/skills &&
rm -rf ~/.agents/skills/huggingface-llm-trainer &&
cp -R "$tmp/skills/huggingface-llm-trainer" ~/.agents/skills/huggingface-llm-trainer &&
rm -rf "$tmp"
```

For one repository only, put the folder in `.agents/skills/huggingface-llm-trainer` inside it instead.

### Cursor

Copy the skill folder to `~/.cursor/skills/huggingface-llm-trainer` to use it in every project:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/huggingface/skills.git "$tmp" &&
mkdir -p ~/.cursor/skills &&
rm -rf ~/.cursor/skills/huggingface-llm-trainer &&
cp -R "$tmp/skills/huggingface-llm-trainer" ~/.cursor/skills/huggingface-llm-trainer &&
rm -rf "$tmp"
```

For one project only, put the folder in `.cursor/skills/huggingface-llm-trainer` inside it instead.

### Gemini CLI

Run in a terminal (add `--scope workspace` to install it for the current workspace only):

```sh
gemini skills install https://github.com/huggingface/skills.git --path skills/huggingface-llm-trainer
```

Or copy the folder to `~/.gemini/skills/huggingface-llm-trainer` yourself.

### VS Code

For GitHub Copilot in VS Code, copy the skill folder to `~/.copilot/skills/huggingface-llm-trainer`:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/huggingface/skills.git "$tmp" &&
mkdir -p ~/.copilot/skills &&
rm -rf ~/.copilot/skills/huggingface-llm-trainer &&
cp -R "$tmp/skills/huggingface-llm-trainer" ~/.copilot/skills/huggingface-llm-trainer &&
rm -rf "$tmp"
```

For one project only, put the folder in `.github/skills/huggingface-llm-trainer` inside it instead.

### Other agents

Get the folder:

```sh
git clone --depth 1 https://github.com/huggingface/skills.git
```

Then copy `skills/skills/huggingface-llm-trainer` into your agent's skills folder as `huggingface-llm-trainer`. Agents that support SKILL.md read one folder per skill.

## FAQ

### How do I install Huggingface LLM trainer in Claude Code?

Copy the skill folder from GitHub to ~/.claude/skills/huggingface-llm-trainer to use it in all your projects, or to .claude/skills/huggingface-llm-trainer in one project.

### Does Huggingface LLM trainer run scripts?

Yes. It runs Python scripts. Its scripts contain network calls. This comes from a static check of the files on GitHub; nothing was run. Read the files before you install it.

### Which AI agents can use Huggingface LLM trainer?

Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf and Goose. Each reads skills in the SKILL.md format from its own folder; the install steps on this page list them.

### What are the best alternatives to Huggingface LLM trainer?

The closest alternatives to Huggingface LLM trainer are MCP builder, Academy guide, Claude API, Nano banana pro openrouter and Generate image.

## Alternatives

- [MCP builder](https://ai-powered.com/skills/mcp-builder): MCP builder is an agent skill for ai models and llm tooling.
- [Academy guide](https://ai-powered.com/skills/academy-guide): Academy guide is an agent skill for ai models and llm tooling.
- [Claude API](https://ai-powered.com/skills/claude-api): Claude API is an agent skill for ai models and llm tooling.
- [Nano banana pro openrouter](https://ai-powered.com/skills/nano-banana-pro-openrouter): Nano banana pro openrouter is an open-source agent skill for design and media.
- [Generate image](https://ai-powered.com/skills/generate-image): Generate image is an open-source agent skill for design and media.
- [Phoenix evals](https://ai-powered.com/skills/phoenix-evals): Phoenix evals is an open-source agent skill for ai models and llm tooling.
- [Code exemplars blueprint generator](https://ai-powered.com/skills/code-exemplars-blueprint-generator): Code exemplars blueprint generator is an open-source agent skill for ai models and llm tooling.
- [Arize AI provider integration](https://ai-powered.com/skills/arize-ai-provider-integration): Arize AI provider integration is an open-source agent skill for ai models and llm tooling.

---
Source: https://ai-powered.com/skills/huggingface-llm-trainer
