huggingface-llm-trainer

Official

Train LLMs with TRL on Hugging Face Jobs.

AuthorLAF-US
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Train and align large language models using Transformer Reinforcement Learning (TRL) on Hugging Face Jobs, providing ready-to-use templates for SFT, DPO, GRPO, and model deployment workflows.

Core Features & Use Cases

  • End-to-end TRL-based fine-tuning templates for SFT, DPO, and GRPO with Trackio monitoring and Hub push.
  • Production-ready references, best practices, and troubleshooting guidance for dataset validation, cost estimation, and model deployment.
  • GGUF conversion guidance to deploy trained models locally with llama.cpp, Ollama, or LM Studio.

Quick Start

Submit a training job via hf_jobs inline script to start TRL-based fine-tuning on Hugging Face Jobs.

Dependency Matrix

Required Modules

trl>=0.12.0peft>=0.7.0transformers>=4.36.0accelerate>=0.24.0trackiodatasetshuggingface_hub[hf_transfer]tensorboardtrl==0.22.2unslothtransformers==4.57.3huggingface_hub>=0.20.0sentencepiece>=0.1.99protobuf>=3.20.0numpygguftorch>=2.0.0

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: huggingface-llm-trainer
Download link: https://github.com/LAF-US/IDAHO-VAULT/archive/main.zip#huggingface-llm-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.