# Jackrong LLM Fine-Tuning Guide

> Source: <https://github.com/R6410418/Jackrong-llm-finetuning-guide>
> Published: 2026-07-07 00:16:33+00:00

An educational, end-to-end open-source knowledge base for LLM fine-tuning, dataset distillation, reinforcement learning, and local deployment.

🌐 **Languages:** English | [中文](/R6410418/Jackrong-llm-finetuning-guide/blob/main/docs/README_zh.md) | [한국어](/R6410418/Jackrong-llm-finetuning-guide/blob/main/docs/README_ko.md) | [日本語](/R6410418/Jackrong-llm-finetuning-guide/blob/main/docs/README_ja.md)

🤗 **Hugging Face:** [Jackrong](https://huggingface.co/Jackrong)

This repository is a growing educational resource portal for beginners and developers who want reproducible training pipelines, SFT and RL workflows including GRPO and GSPO, data preparation and distillation recipes, 16-bit export and GGUF deployment workflows, and agent-ready Qwen MTP GGUF conversion tools.

[🚀 Start Here](#-start-here)[🗺️ Repository Map](#%EF%B8%8F-repository-map)[🏋️ Training Recipes](#%EF%B8%8F-training-recipes)[✅ Supported Workflows](#-supported-workflows)[🛣️ Model Support Roadmap](#%EF%B8%8F-model-support-roadmap)[⚙️ Qwen MTP GGUF Conversion Skill](#%EF%B8%8F-qwen-mtp-gguf-conversion-skill)[📘 Guides and Reports](#-guides-and-reports)[🧠 High-Fidelity Dataset Catalog](#-high-fidelity-dataset-catalog)[🤝 Open-Source Commitment](#-open-source-commitment)[📚 Citation](#-citation)

| I want to... | Recommended entry |
|---|---|
| Fine-tune my first model in a browser |
|

[Open the GSPO Python tutorial](/R6410418/Jackrong-llm-finetuning-guide/blob/main/train_code/Qwopus3.6-27B-GSPO/qwopus3_6_27b_gspo_training.py)[Browse data-processing recipes](/R6410418/Jackrong-llm-finetuning-guide/blob/main/data_processing_code)[Open the dataset catalog](/R6410418/Jackrong-llm-finetuning-guide/blob/main/High-fidelity%20Dataset)[Open the Qwen MTP GGUF Skill](/R6410418/Jackrong-llm-finetuning-guide/blob/main/qwen-mtp-gguf)[Open the PDF guide library](/R6410418/Jackrong-llm-finetuning-guide/blob/main/guidePDF)[Open the Codex Goal templates](/R6410418/Jackrong-llm-finetuning-guide/blob/main/codex-goals)| Resource | What you will find | Entry |
|---|---|---|
| 🏋️ Training Recipes | SFT, GRPO, and GSPO notebooks and Python tutorials |
|

[Open](/R6410418/Jackrong-llm-finetuning-guide/blob/main/data_processing_code)[Open](/R6410418/Jackrong-llm-finetuning-guide/blob/main/High-fidelity%20Dataset)[Open](/R6410418/Jackrong-llm-finetuning-guide/blob/main/qwen-mtp-gguf)[Open](/R6410418/Jackrong-llm-finetuning-guide/blob/main/guidePDF)[Open](/R6410418/Jackrong-llm-finetuning-guide/blob/main/docs)[Open](/R6410418/Jackrong-llm-finetuning-guide/blob/main/codex-goals)| Model | Method | Environment | Quick setup |
|---|---|---|---|
| Qwopus3.5 27B | SFT | Google Colab | |
| Qwopus3.6 27B | GSPO | Python script | |
| Qwen3.5 9B | SFT | Kaggle | |
| Qwopus3.5 35B | SFT | Kaggle | |
| Llama3.2-R1 3B | GRPO | Kaggle |

Browse the full catalog in [train_code/README.md](/R6410418/Jackrong-llm-finetuning-guide/blob/main/train_code/README.md).

| Workflow | Status | Documentation |
|---|---|---|
| SFT with LoRA / QLoRA | ✅ Released |
|

[Training recipes](/R6410418/Jackrong-llm-finetuning-guide/blob/main/train_code)[Qwopus3.6 27B GSPO tutorial](/R6410418/Jackrong-llm-finetuning-guide/blob/main/train_code/Qwopus3.6-27B-GSPO/qwopus3_6_27b_gspo_training.py)[Data-processing recipes](/R6410418/Jackrong-llm-finetuning-guide/blob/main/data_processing_code)[Training recipes](/R6410418/Jackrong-llm-finetuning-guide/blob/main/train_code)[Training recipes](/R6410418/Jackrong-llm-finetuning-guide/blob/main/train_code)[MTP conversion skill](/R6410418/Jackrong-llm-finetuning-guide/blob/main/qwen-mtp-gguf)Released RL recipes may use GRPO or GSPO depending on the model and training objective.

| Model Family | SFT Support | RL Support |
|---|---|---|
| Qwen 3.5 | ✅ Released | Scheduled |
| Qwen 3.6 | ✅ Released | ✅ Released |
| Qwen 3 | Scheduled | Scheduled |
| Llama3.2-R1 3B | ✅ Included | ✅ Released |
| Llama 3.1 / 3.3 | Scheduled | Scheduled |

The [ qwen-mtp-gguf](/R6410418/Jackrong-llm-finetuning-guide/blob/main/qwen-mtp-gguf) subproject supports Qwen-family MTP / nextn GGUF release workflows. It performs disk, RAM, tooling, token-access, and compatibility preflight checks, extracts compatible MTP tensors, injects them into the target model, converts with llama.cpp, smoke-tests outputs, quantizes releases, and supports safer upload/resume workflows.

[🚀 Open the MTP Skill](/R6410418/Jackrong-llm-finetuning-guide/blob/main/qwen-mtp-gguf) · [📖 Read the Pipeline Guide](/R6410418/Jackrong-llm-finetuning-guide/blob/main/qwen-mtp-gguf/docs/Qwen-MTP-GGUF-Pipeline-Guide.md) · [🤖 Read the Agent Usage Guide](/R6410418/Jackrong-llm-finetuning-guide/blob/main/qwen-mtp-gguf/docs/Qwen-MTP-GGUF-Agent-Usage.md)

Long-form PDFs live in the [guide and technical report library](/R6410418/Jackrong-llm-finetuning-guide/blob/main/guidePDF/README.md).

| Guide | Topic | File |
|---|---|---|
| Qwopus3.5 27B Colab complete guide | Beginner-friendly end-to-end fine-tuning walkthrough | |
| Qwopus GLM 18B technical report | Model design and training notes |

The repository includes 24 curated high-fidelity datasets for reasoning, mathematics, coding, instruction following, conversation, and domain-specific distillation. Browse the full [dataset catalog](/R6410418/Jackrong-llm-finetuning-guide/blob/main/High-fidelity%20Dataset/README.md), or use [ download_datasets.py](/R6410418/Jackrong-llm-finetuning-guide/blob/main/download_datasets.py) to batch download the suite for local training.

This project keeps the training source code and documentation for released fine-tuned models available so learners can reproduce, inspect, and adapt the workflows. The longer project philosophy and original message to builders are preserved in [docs/PROJECT_PHILOSOPHY.md](/R6410418/Jackrong-llm-finetuning-guide/blob/main/docs/PROJECT_PHILOSOPHY.md).

If you find this repository helpful in your learning or research, please consider citing it:

```
@misc{jackrong-llm-finetuning,
  author = {Jackrong},
  title = {Jackrong LLM Fine-Tuning Guide: An Educational LLM Fine-Tuning Knowledge Base},
  year = {2026},
  publisher = {GitHub},
  journal = {GitHub repository},
  howpublished = {\url{https://github.com/R6410418/Jackrong-llm-finetuning-guide}}
}
```