huggingface-llm-trainer
Hugging Face's skill for fine-tuning language and vision-language models on Hugging Face Jobs, its managed cloud GPUs, using TRL or Unsloth.
What the skill teaches
Hugging Face's skill for fine-tuning language and vision-language models on Hugging Face Jobs, its managed cloud GPUs, using TRL or Unsloth. It walks the agent through choosing a method (supervised fine-tuning, DPO, GRPO or reward modelling), preparing and validating the dataset, writing a self-contained uv script, picking hardware and estimating cost, submitting and monitoring the job, and pushing the trained model to the Hub. It also covers converting results to GGUF for local use. Bundled scripts and reference notes support each step. A Hugging Face account with Jobs access and a write token are required, and jobs are billed.
Capabilities
- Fine-tune models with SFT, DPO, GRPO or reward modelling
- Submit and monitor training runs on Hugging Face Jobs
- Validate datasets and estimate hardware and cost
- Convert trained models to GGUF
About
- Publisher
- Hugging Face
- Tool
- Hugging Face
Install
- Run this to add it to Any client:
hf skills add huggingface-llm-trainer --global
What's inside
- references/gguf_conversion.md
- references/hardware_guide.md
- references/hub_saving.md
- references/local_training_macos.md
- references/reliability_principles.md
- references/trackio_guide.md
- references/training_methods.md
- references/training_patterns.md
- references/troubleshooting.md
- references/unsloth.md
- scripts/convert_to_gguf.py
- scripts/dataset_inspector.py
- scripts/estimate_cost.py
- scripts/hf_benchmarks.py
- scripts/train_dpo_example.py
- scripts/train_grpo_example.py
- scripts/train_sft_example.py
- scripts/unsloth_sft_example.py
MCP servers and skills can run code on your computer and act on your data. Review the source before installing.
This skill includes scripts that your agent may run.
Details
| Fact | Value | Source |
|---|---|---|
| Type | Skill | |
| Tool | Hugging Face | |
| Publisher | Hugging Face | source |
| Official status | OfficialHugging Face Hub docs link to the huggingface/skills repository | source |
| Needs an API key or sign-in | Not stated in its documentation | |
| Includes scripts | Yes | source |
| Platforms | Not stated in its documentation | |
| AI clients | Not stated in its documentation | |
| Licence | Apache-2.0 | source |
| Pricing | Not stated in its documentation | |
| Activity | Last commit Nov 11, 202611,334 GitHub starsDownload data not available (not on npm or PyPI) | source |
| Links | Repository Website |
More from Hugging Face
1 server · 26 skills
- hf-mcp (Skill)
- hf-cli (Skill)
- hf-mem (Skill)
- huggingface-best (Skill)
- huggingface-community-evals (Skill)
- huggingface-datasets (Skill)
Sources
- Skill file (SKILL.md)github.com/huggingface/skillsNov 10, 2026
- Web pagehuggingface.co · Backs: Official statusNov 12, 2026
- Licence file (LICENSE)github.com/huggingface/skills · Backs: LicenceNov 12, 2026
- GitHub repositorygithub.com/huggingface/skills · Backs: Publisher, Activity, LicenceNov 11, 2026
- Folder in the repository (huggingface-llm-trainer)github.com/huggingface/skills · Backs: Includes scriptsNov 10, 2026