Skip to content

Hugging Face LLM Trainer

Fine-tune language and vision models on Hugging Face Jobs from a conversation.

Official vendorby Hugging FaceChecked October 18, 2026

Hugging Face's official skill for training models with TRL or Unsloth on its cloud GPUs. Claude prepares the dataset, picks hardware, estimates cost, launches the job and pushes the trained model to the Hub.

Who it is for

  • ML engineers
  • AI researchers
  • Developers exploring fine-tuning

Prompts to try

Once the skill is installed, ask for the result in plain words. Claude picks the skill up on its own.

Prompt 1
Fine-tune a small open model on my customer support dataset
Prompt 2
Train a DPO model with this preference dataset and estimate the cost
Prompt 3
Convert my fine-tuned model to GGUF so I can run it locally

How to install it

In Claude Code

  1. /plugin marketplace add huggingface/skills
  2. /plugin install hf-cli@huggingface/skills

  3. hf skills add huggingface-llm-trainer

In Claude.ai

Not practical in Claude.ai because the skill drives local command-line tools, so use Claude Code.

Good to know

The marketplace registers as huggingface-skills; if the documented install name is not found, try hf-cli@huggingface-skills.

Unlock the install steps

Free. Leave your email once to open the install steps for all 149 skills, and get the best new skills each month.

No spam. One click to unsubscribe. We use your email to send you the course and AI tips.

How we checked it

Confirmed SKILL.md at skills/huggingface-llm-trainer/SKILL.md in huggingface/skills via the GitHub API; skill folder last changed 2026-07-06, repo has 11,178 stars and was pushed 2026-10-08.

Source: github.com/huggingface/skills/tree/main/skills/huggingface-llm-trainer

More ai agents skills