# Huggingface LLM Trainer

> Codex curated Hugging Face skill for training or fine-tuning language models with datasets, tokenizers, trainers, LoRA, metrics, and Hub checkpoints.

- Skill: `rycen7822/huggingface-llm-trainer` (Agent Skill)
- Install (CLI): `npx skillmds@latest add rycen7822/huggingface-llm-trainer`
- Raw SKILL.md: https://api.skillmd.com/api/skills/rycen7822/huggingface-llm-trainer/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: Rycen7822 (https://skillmd.com/u/rycen7822)
- Updated: 2026-09-22
- Page: https://skillmd.com/skills/rycen7822/huggingface-llm-trainer

---

# huggingface-llm-trainer
## When to Use
Use for LLM fine-tuning, tokenizer setup, training arguments, LoRA adapters, evaluation metrics, or Hub checkpoint publishing.
## Do Not Use When
Do not use for vision-only training or simple Gradio UI work.
## Required Inputs
Base model, dataset, tokenizer strategy, hardware budget, training configuration, and checkpoint destination.
## Workflow
1. Inspect model and dataset sizes.
2. Configure tokenizer and trainer.
3. Run a tiny smoke training step.
4. Evaluate and save/push outputs.