huggingface-llm-trainer
huggingface-llm-trainer is an agent skill published by huggingface, listed under training models. It lives in the huggingface/skills repository, which has 11,213 GitHub stars and is licensed under Apache-2.0; we last read it on 2026-09-16.
Trains or fine-tunes language and vision models using TRL or Unsloth methods with Hugging Face Jobs infrastructure, requiring Hub authentication. Covers SFT, DPO, GRPO, and reward modeling training methods, plus GGUF conversion for local deployment.
Install
skills is a generic installer for any repository of Claude agent skills -- it reads huggingface/skills’s own structure rather than assuming one, the same way this page reads the skill’s own SKILL.md rather than assuming a format.
npx skills add huggingface/skills
Maintenance
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.
huggingface-llm-trainer compared with similar skills
| Skill | Publisher | What it does | Repo stars | Last update |
|---|---|---|---|---|
| huggingface-llm-trainer (this page) | huggingface | Train or fine-tune language and vision models using TRL (Transformer Reinforcement Learning) or Unsloth with… | 11,213 | 2026-10-23 |
| hf-cloud-sagemaker-deployment-planner(same repository) | huggingface | Plan and coordinate the deployment of a model to Amazon SageMaker AI. Use this skill whenever the user wants… | 11,213 | 2026-10-23 |
| hf-cloud-serving-image-selection(same repository) | huggingface | Pick the right serving container for a SageMaker model deployment and find its current image URI. Use this sk… | 11,213 | 2026-10-23 |
| huggingface-lora-space-builder(same repository) | huggingface | Build and publish a Gradio demo on Hugging Face Spaces for a user-provided LoRA. Use when someone asks to cre… | 11,213 | 2026-10-23 |
| huggingface-vision-trainer(same repository) | huggingface | Trains and fine-tunes vision models for object detection (D-FINE, RT-DETR v2, DETR, YOLOS), image classificat… | 11,213 | 2026-10-23 |
| train-sentence-transformers(same repository) | huggingface | Train or fine-tune sentence-transformers models across `SentenceTransformer` (bi-encoder, dense or static emb… | 11,213 | 2026-10-23 |
| trl-training(same repository) | huggingface | Post-train LLMs with TRL (Transformers Reinforcement Learning) — SFT, DPO, GRPO, KTO, and reward-model traini… | 11,213 | 2026-10-23 |
Skills from the same repository first, then others for this job by repository stars. Figures are from each repository when we last read it.
Common questions about huggingface-llm-trainer
- What does huggingface-llm-trainer do?
- Trains or fine-tunes language and vision models using TRL or Unsloth methods with Hugging Face Jobs infrastructure, requiring Hub authentication. Covers SFT, DPO, GRPO, and reward modeling training methods, plus GGUF conversion for local deployment.
- How do I install huggingface-llm-trainer?
- Run npx skills add huggingface/skills. The skills installer reads the repository’s own structure, so it works for any repository of agent skills.
- Who publishes huggingface-llm-trainer?
- huggingface.
- Is huggingface-llm-trainer maintained, and what licence does it use?
- Its repository has 11,213 GitHub stars and its state in our directory is listed. Its last commit we recorded was on 2026-10-23. The repository declares the Apache-2.0 licence.
More agent skills for training models
- ai-image-generationby 101-skills
- flux-imageby 101-skills
- p-imageby 101-skills
- firecrawl-knowledge-baseby firecrawl
- agent-platform-eval-flywheelby google
- agent-platform-tuningby google