# Jackrong LLM Fine-Tuning Guide

An educational, end-to-end open-source knowledge base covering LLM fine-tuning, dataset distillation, reinforcement learning and local deployment, with notebooks and guides in four languages.

Jackrong LLM Fine-Tuning Guide is a growing educational resource for beginners and developers who want reproducible LLM training pipelines. It covers supervised fine-tuning and reinforcement-learning workflows including GRPO and GSPO, data preparation and distillation recipes, sixteen-bit export and GGUF deployment workflows, and tooling for converting Qwen models to an MTP-enabled GGUF format for agent use.

The repository organizes its material into training-recipe notebooks and Python tutorials for specific models and environments such as Google Colab and Kaggle, data-processing and distillation workflows, a catalog of curated datasets with download helpers, and long-form PDF guides and reports. Content is available in English, Chinese, Korean and Japanese, and the project also includes editable goal templates for automating repeatable training and maintenance workflows with a coding agent.

Website: https://r6410418.github.io/Jackrong-llm-finetuning-guide/