{"slug": "jackrong-llm-fine-tuning-guide", "title": "Jackrong LLM Fine-Tuning Guide", "summary": "Jackrong released an open-source knowledge base for LLM fine-tuning, dataset distillation, reinforcement learning, and local deployment. The guide provides reproducible training pipelines, SFT and RL workflows, data preparation recipes, and GGUF conversion tools for models like Qwen and Llama. It targets beginners and developers seeking educational resources for large language model customization.", "body_md": "An educational, end-to-end open-source knowledge base for LLM fine-tuning, dataset distillation, reinforcement learning, and local deployment.\n\n🌐 **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)\n\n🤗 **Hugging Face:** [Jackrong](https://huggingface.co/Jackrong)\n\nThis 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.\n\n[🚀 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)\n\n| I want to... | Recommended entry |\n|---|---|\n| Fine-tune my first model in a browser |\n|\n\n[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 |\n|---|---|---|\n| 🏋️ Training Recipes | SFT, GRPO, and GSPO notebooks and Python tutorials |\n|\n\n[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 |\n|---|---|---|---|\n| Qwopus3.5 27B | SFT | Google Colab | |\n| Qwopus3.6 27B | GSPO | Python script | |\n| Qwen3.5 9B | SFT | Kaggle | |\n| Qwopus3.5 35B | SFT | Kaggle | |\n| Llama3.2-R1 3B | GRPO | Kaggle |\n\nBrowse the full catalog in [train_code/README.md](/R6410418/Jackrong-llm-finetuning-guide/blob/main/train_code/README.md).\n\n| Workflow | Status | Documentation |\n|---|---|---|\n| SFT with LoRA / QLoRA | ✅ Released |\n|\n\n[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.\n\n| Model Family | SFT Support | RL Support |\n|---|---|---|\n| Qwen 3.5 | ✅ Released | Scheduled |\n| Qwen 3.6 | ✅ Released | ✅ Released |\n| Qwen 3 | Scheduled | Scheduled |\n| Llama3.2-R1 3B | ✅ Included | ✅ Released |\n| Llama 3.1 / 3.3 | Scheduled | Scheduled |\n\nThe [ 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.\n\n[🚀 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)\n\nLong-form PDFs live in the [guide and technical report library](/R6410418/Jackrong-llm-finetuning-guide/blob/main/guidePDF/README.md).\n\n| Guide | Topic | File |\n|---|---|---|\n| Qwopus3.5 27B Colab complete guide | Beginner-friendly end-to-end fine-tuning walkthrough | |\n| Qwopus GLM 18B technical report | Model design and training notes |\n\nThe 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.\n\nThis 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).\n\nIf you find this repository helpful in your learning or research, please consider citing it:\n\n```\n@misc{jackrong-llm-finetuning,\n  author = {Jackrong},\n  title = {Jackrong LLM Fine-Tuning Guide: An Educational LLM Fine-Tuning Knowledge Base},\n  year = {2026},\n  publisher = {GitHub},\n  journal = {GitHub repository},\n  howpublished = {\\url{https://github.com/R6410418/Jackrong-llm-finetuning-guide}}\n}\n```\n\n", "url": "https://wpnews.pro/news/jackrong-llm-fine-tuning-guide", "canonical_source": "https://github.com/R6410418/Jackrong-llm-finetuning-guide", "published_at": "2026-07-07 00:16:33+00:00", "updated_at": "2026-07-07 00:39:10.389159+00:00", "lang": "en", "topics": ["large-language-models", "machine-learning", "ai-research", "ai-tools", "developer-tools"], "entities": ["Jackrong", "Hugging Face", "Qwen", "Llama", "Google Colab", "Kaggle", "GRPO", "GSPO"], "alternates": {"html": "https://wpnews.pro/news/jackrong-llm-fine-tuning-guide", "markdown": "https://wpnews.pro/news/jackrong-llm-fine-tuning-guide.md", "text": "https://wpnews.pro/news/jackrong-llm-fine-tuning-guide.txt", "jsonld": "https://wpnews.pro/news/jackrong-llm-fine-tuning-guide.jsonld"}}