Agent SkillsML · ModelsOfficial

huggingface-llm-trainer

skills/huggingface-llm-trainer · huggingface/skills · by Hugging Face

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.

Repo stars
11,351
huggingface/skills · 2026-11-15
Last commit
2026-07-06
to this skill folder
Files
19
8 scripts
License
Complete terms in LICENSE.txt
SKILL.md frontmatter

Source · GitHub API and the SKILL.md frontmatter, read 2026-11-15 · stars are for the whole huggingface/skills repository

Ready-to-paste · from the repository README and the skill folder

# Copy this skill folder into your personal Claude Code skills
git clone --depth 1 --filter=blob:none --sparse --branch main https://github.com/huggingface/skills.git /tmp/huggingface-llm-trainer-src
git -C /tmp/huggingface-llm-trainer-src sparse-checkout set skills/huggingface-llm-trainer
mkdir -p ~/.claude/skills
cp -R /tmp/huggingface-llm-trainer-src/skills/huggingface-llm-trainer ~/.claude/skills/huggingface-llm-trainer
Claude Code reads skills from ~/.claude/skills/<name>/SKILL.md.Claude Code docs
Ecosystem · Agent Skills

Skill repositories from other publishers in the open Agent Skills format (agentskills.io) · a folder with a SKILL.md plus optional scripts and resources, read by any client that supports the format.

Files · 19
SKILL.mdreferences/gguf_conversion.mdreferences/hardware_guide.mdreferences/hub_saving.mdreferences/local_training_macos.mdreferences/reliability_principles.mdreferences/trackio_guide.mdreferences/training_methods.mdreferences/training_patterns.mdreferences/troubleshooting.mdreferences/unsloth.mdscripts/convert_to_gguf.pyscripts/dataset_inspector.pyscripts/estimate_cost.pyscripts/hf_benchmarks.pyscripts/train_dpo_example.pyscripts/train_grpo_example.pyscripts/train_sft_example.pyscripts/unsloth_sft_example.py
Scripts · 8
scripts/convert_to_gguf.pyscripts/dataset_inspector.pyscripts/estimate_cost.pyscripts/hf_benchmarks.pyscripts/train_dpo_example.pyscripts/train_grpo_example.pyscripts/train_sft_example.pyscripts/unsloth_sft_example.py

Same repository · huggingface/skills · latest commit first

Drop into your README · links to this skill page

huggingface-llm-trainer · listed on BenchGecko
[![huggingface-llm-trainer · listed on BenchGecko](https://benchgecko.ai/badge/skill/huggingface-llm-trainer.svg)](https://benchgecko.ai/skills/huggingface-llm-trainer)
The badge shows the skill ecosystem label · BenchGecko does not rate skills.

Built from the GitHub data above

What is huggingface-llm-trainer?

huggingface-llm-trainer is a Agent Skills agent skill by Hugging Face, in the skills/huggingface-llm-trainer folder of the huggingface/skills repository (BenchGecko category: ML · Models). Its SKILL.md describes it as: 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.

Where does this data come from?

From GitHub, read 2026-11-15: the name and description from the SKILL.md frontmatter, 19 files from the repository tree, the last commit to the folder on 2026-07-06, and 11,351 stars for the whole huggingface/skills repository. BenchGecko does not rate skills.

How do I install huggingface-llm-trainer?

Copy the skills/huggingface-llm-trainer folder into ~/.claude/skills/ for Claude Code, use the command from the huggingface/skills README, or point any client that supports the Agent Skills format at the folder. Ready-to-paste snippets are above.

Is huggingface-llm-trainer official?

huggingface-llm-trainer is published in huggingface/skills, a repository owned by the Hugging Face organization on GitHub.

Keep exploring the BenchGecko graph