Back to Articles
Setup and Install Claude Code Codex Gemini CLI Connect to Hugging Face Your First Training Run Instruct the coding agent to fine tune Review Before Submitting Track Progress Use Your Model Training Methods Supervised Fine-Tuning (SFT) Direct Preference Optimization (DPO) Group Relative Policy Optimization (GRPO) Hardware and Cost Model Size to GPU Mapping Demo vs Production Dataset Validation Monitoring Training Converting to GGUF What's Next Resources
We gave Claude the ability to fine-tune language models using a new tool called Hugging Face Skills. Not just write training scripts, but to actually submit jobs to cloud GPUs, monitor progress, and push finished models to the Hugging Face Hub. This tutorial shows you how it works and how to use it yourself.
Claude Code can use "skills"—packaged instructions, scripts, and domain knowledge—to accomplish specialized tasks. The hf-llm-trainer skill teaches Claude everything it needs to know about training: which GPU to pick for your model size, how to configure Hub authentication, when to use LoRA versus full fine-tuning, and how to handle the dozens of other decisions that go into a successful training run.
With this skill, you can tell Claude things like:
