skills.rest
lidge-jun
lidge-junCOMMUNITY
Explore all skills by this author →
𝕏@claudeebumGitHub

hugging-face-model-trainer

Train and fine-tune language models via Hugging Face Jobs and TRL.

5|Updated Feb 26, 2026
Search Tags:#llm#fine-tuning#training#gguf#trl#hugging face#cloud gpu
One-click install
npx skills add https://github.com/lidge-jun/cli-jaw-skills --skill hugging-face-model-trainer-lidge-jun
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: hugging-face-model-trainer
Source: https://github.com/lidge-jun/cli-jaw-skills/tree/main/hugging-face-model-trainer
Command: npx skills add https://github.com/lidge-jun/cli-jaw-skills --skill hugging-face-model-trainer-lidge-jun

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires transformers, peft, trl, accelerate, trackio, gguf, sentencepiece, protobuf, numpy, unsloth, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill streamlines the process of training and fine-tuning large language models (LLMs) using Hugging Face's cloud infrastructure, eliminating the need for local GPU setup and complex environment management.

Core Features & Use Cases

  • Cloud-based Training: Leverage Hugging Face Jobs for SFT, DPO, GRPO, and reward modeling.
  • Automated Workflow: Submit training jobs directly via the hf_jobs() MCP tool with inline scripts.
  • GGUF Conversion: Convert trained models to GGUF format for local deployment with tools like Ollama and LM Studio.
  • Use Case: A user wants to fine-tune a Qwen2.5 model on a custom dataset using DPO. This Skill can generate the training script, submit the job to Hugging Face Jobs, and provide monitoring links.

Quick Start

Use the hugging-face-model-trainer skill to fine-tune the Qwen2.5-0.5B model using SFT on the Capybara dataset.

Frequently Asked Questions about hugging-face-model-trainer

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I fine-tune an LLM using Hugging Face Jobs without setting up local GPUs?▼

You can fine-tune LLMs using Hugging Face Jobs by submitting training scripts directly via the hf_jobs() tool. This cloud-based approach eliminates local GPU setup, handling infrastructure management and providing monitoring links asynchronously.

What is the best way to run DPO and GRPO training on a custom dataset?▼

To run DPO and GRPO training on a custom dataset, use the TRL library with Hugging Face Jobs infrastructure. This Skill supports supervised fine-tuning, direct preference optimization, group relative policy optimization, and reward modeling workflows.

Can I convert my fine-tuned Hugging Face model to GGUF format for local inference?▼

Yes, you can convert fine-tuned models to GGUF format for local inference. The Skill includes capabilities to transform trained models into GGUF, allowing deployment with local inference tools like Ollama and LM Studio.

Does this workflow support Unsloth and PEFT for cloud GPU training?▼

Yes, the workflow supports Unsloth and PEFT for cloud GPU training. It leverages these dependencies alongside the transformers and accelerate libraries to optimize the fine-tuning process on Hugging Face Jobs infrastructure.

How do I estimate hardware requirements and costs for LLM training jobs?▼

You can estimate hardware requirements and costs for LLM training jobs using the guidance provided by this Skill. It includes capabilities for hardware selection and cost estimation to help you manage asynchronous cloud training jobs effectively.

Related Skills

Explore More Software Engineering Skills→
hung-phanhung-phan
1

hf-jobs-workflow

Run Hugging Face Jobs training with pre-flight checks and OOM recovery.

Community
Advanced
afel6afel6

gguf-quantization

Convert and quantize transformer models into GGUF format for CPU inference.

Community
Advanced
icyzhicyzh
1

lambda-labs-gpu-cloud

Provision and manage on-demand GPU cloud instances for ML training.

Community
Advanced
huggingfacehuggingface
10.9k

hugging-face-model-trainer

Train and fine-tune language models on Hugging Face Jobs using TRL methods.

Official
Advanced