hugging-face-model-trainer

Community

Train and fine-tune LLMs on Hugging Face Jobs.

AuthorAniket-a14
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill provides end-to-end tooling and templates to train and fine-tune language models on Hugging Face Jobs using TRL (SFT, DPO, GRPO), including integration with Trackio, hub pushing, and GGUF conversion for local deployment.

Core Features & Use Cases

  • Production-ready training templates for SFT, DPO, and GRPO with inline scripts and dataset validation.
  • GGUF conversion workflow for deploying trained models locally with Ollama and llama.cpp.
  • Hub authentication and monitoring guidance, Trackio integration, and cost estimation workflows.
  • Use case: Quickly fine-tune a small Qwen/Qwen2.5-0.5B model on TRL-ready data and push to Hugging Face Hub.

Quick Start

Use the hugging-face-model-trainer skill to launch a TRL training job on HF Jobs with a small dataset and inline script.

Dependency Matrix

Required Modules

trl>=0.12.0peft>=0.7.0transformers>=4.36.0accelerate>=0.24.0trackiotorch>=2.0.0huggingface_hub>=0.20.0sentencepiece>=0.1.99protobuf>=3.20.0numpygguf

Components

scriptsreferences

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: hugging-face-model-trainer
Download link: https://github.com/Aniket-a14/Wizard-w1/archive/main.zip#hugging-face-model-trainer

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.