{"data":{"slug":"r6410418-jackrong-llm-finetuning-guide","name":"Jackrong-llm-finetuning-guide","tagline":"A guide for fine-tuning large language models like LLaMA3 and Qwen using PyTorch","github_url":"https://github.com/R6410418/Jackrong-llm-finetuning-guide","owner":"R6410418","repo":"Jackrong-llm-finetuning-guide","owner_avatar_url":"https://avatars.githubusercontent.com/u/115608084?v=4","primary_language":"Jupyter Notebook","stars":1661,"forks":269,"topics":["dataset","deepseek","fine-tuning","guide","llama3","llm","machine-learning","nlp","openai","pytorch","qwen","unsloth"],"archived":false,"github_pushed_at":"2026-07-11T05:10:47+00:00","maintenance_label":"Steady","stars_delta_30d":57,"url":"https://www.graphcanon.com/tools/r6410418-jackrong-llm-finetuning-guide","markdown_url":"https://www.graphcanon.com/tools/r6410418-jackrong-llm-finetuning-guide.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/r6410418-jackrong-llm-finetuning-guide","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=r6410418-jackrong-llm-finetuning-guide","description":null,"homepage_url":"https://r6410418.github.io/Jackrong-llm-finetuning-guide/","license":"Apache-2.0","open_issues":11,"watchers":25,"ai_summary":"This repository contains a guide focused on the process of fine-tuning large language models such as LLaMA3 and Qwen with PyTorch. The resource likely includes datasets, deepseek techniques, and machine-learning practices pertinent to improving NLP capabilities.","readme_excerpt":"<div align=\"center\">\n\n# Jackrong LLM Fine-Tuning Guide\n\nAn educational, end-to-end open-source knowledge base for LLM fine-tuning,\ndataset distillation, reinforcement learning, and local deployment.\n\n🌐 **Languages:** English | [中文](docs/README_zh.md) | [한국어](docs/README_ko.md) | [日本語](docs/README_ja.md)\n\n🤗 **Hugging Face:** [Jackrong](https://huggingface.co/Jackrong)\n\n🌐 **Product Website:** [Explore Qwopus3.6 models and fine-tuning guides →](https://r6410418.github.io/Jackrong-llm-finetuning-guide/)\n\n<br>\n\n\n\n\n\n\n\n\n</div>\n\n---\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## 📚 Table of Contents\n\n- [🚀 Start Here](#-start-here)\n- [🗺️ Repository Map](#️-repository-map)\n- [🏋️ Training Recipes](#️-training-recipes)\n- [✅ Supported Workflows](#-supported-workflows)\n- [🛣️ Model Support Roadmap](#️-model-support-roadmap)\n- [⚙️ Qwen MTP GGUF Conversion Skill](#️-qwen-mtp-gguf-conversion-skill)\n- [📘 Guides and Reports](#-guides-and-reports)\n- [🧠 High-Fidelity Dataset Catalog](#-high-fidelity-dataset-catalog)\n- [🤝 Open-Source Commitment](#-open-source-commitment)\n- [📚 Citation](#-citation)\n\n## 🚀 Start Here\n\n| I want to... | Recommended entry |\n|---|---|\n| Fine-tune my first model in a browser | [Open the training recipe catalog](train_code/) |\n| Run the Qwopus3.6 27B GSPO tutorial | [Open the GSPO Python tutorial](train_code/Qwopus3.6-27B-GSPO/qwopus3_6_27b_gspo_training.py) |\n| Prepare or distill training data | [Browse data-processing recipes](data_processing_code/) |\n| Find curated reasoning, coding, and conversation datasets | [Open the dataset catalog](High-fidelity%20Dataset/) |\n| Convert a Qwen model to MTP-enabled GGUF | [Open the Qwen MTP GGUF Skill](qwen-mtp-gguf/) |\n| Read full beginner guides and reports | [Open the PDF guide library](guidePDF/) |\n| Automate repeatable Codex workflows | [Open the Codex Goal templates](codex-goals/) |\n\n## 🗺️ Repository Map\n\n| Resource | What you will find | Entry |\n|---|---|---|\n| 🏋️ Training Recipes | SFT, GRPO, and GSPO notebooks and Python tutorials | [Open](train_code/) |\n| 🧪 Data Processing | Distillation, preprocessing, filtering, and sampling workflows | [Open](data_processing_code/) |\n| 🧠 Dataset Catalog | Curated high-fidelity datasets and download helpers | [Open](High-fidelity%20Dataset/) |\n| ⚙️ Qwen MTP GGUF Skill | Agent-ready MTP extraction, injection, conversion, validation, quantization, and upload pipeline | [Open](qwen-mtp-gguf/) |\n| 📘 Guides and Reports | Long-form PDF tutorials and technical reports | [Open](guidePDF/) |\n| 🌐 Multilingual Docs | Chinese, Korean, and Japanese landing pages plus documentation indexes | [Open](docs/) |\n| 🤖 Codex Goal Templates | Editable goal templates for RL training, MTP GGUF conversion, and repository maintenance | [Open](codex-goals/) |\n\n## 🏋️ Training Recipes\n\n| 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](train_code/README.md).\n\n## ✅ Supported Workflows\n\n| Workflow | Status | Documentation |\n|---|---|---|\n| SFT with LoRA / QLoRA | ✅ Released | [Training recipes](train_code/) |\n| GRPO reinforcement learning | ✅ Released | [Training recipes](train_code/) |\n| GSPO reinforcement learning | ✅ Released | [Qwopus3.6 27B GSPO tutorial](train_code/Qwopus3.6-27B-GSPO/qwopus3_6_27b_gspo_training.py) |\n| Dataset distillation and preprocessing | ✅ Released | [Data-processing recipes](data_processing_code/) |\n| LoRA adapter save and merged 16-bit export | ✅ Released | [Training recipes](train_code/) |\n| GGUF quantiza","github_created_at":"2026-04-05T08:04:43+00:00","created_at":"2026-07-11T11:39:05.575787+00:00","updated_at":"2026-08-24T00:02:15.921511+00:00","categories":[{"slug":"llm-frameworks","name":"LLM Frameworks","url":"https://www.graphcanon.com/categories/llm-frameworks","markdown_url":"https://www.graphcanon.com/categories/llm-frameworks.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/llm-frameworks"},{"slug":"model-training","name":"Model Training","url":"https://www.graphcanon.com/categories/model-training","markdown_url":"https://www.graphcanon.com/categories/model-training.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/model-training"}],"tags":[{"slug":"dataset","name":"dataset"},{"slug":"deepseek","name":"deepseek"},{"slug":"fine-tuning","name":"fine-tuning"},{"slug":"llama3","name":"llama3"},{"slug":"llm","name":"llm"},{"slug":"machine-learning","name":"machine-learning"},{"slug":"nlp","name":"nlp"},{"slug":"openai","name":"openai"}],"trust":{"provenance":{"is_fork":false,"github_id":1201826173,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-24T00:02:15.222Z","maintenance":{"label":"Steady","score":60,"methodology":"github_public_v1","releases_90d":0,"days_since_push":43,"last_release_at":null,"stars_delta_30d":57,"open_issues_delta_30d":0},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T11:39:06.717Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-08-24T00:02:15.673Z"},"languages":{"value":["jupyter notebook"],"source":"github.language","observed_at":"2026-08-24T00:02:15.673Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-08-24T00:02:15.673Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":{"notes":["Requires Python environment setup for PyTorch and Jupyter Notebook familiarity."],"min_ram_gb":null},"constraints":{"min_ram_gb":null},"when_to_use":["You are specifically working with or planning to work with LLaMA3 or Qwen models, which this guide exclusively supports.","Your project requires PyTorch for model fine-tuning; the guide focuses on detailing the process within that framework."],"when_not_to_use":["You prefer TensorFlow (or another deep learning framework not covered by Jackrong-llm-finetuning-guide) as your primary environment for developing AI models.","Your interest lies in general knowledge about LLMs without the specifics of implementation or fine-tuning methodologies."],"source":"enrich:decision_facts","observed_at":"2026-07-12T17:32:23.757Z"},"constraint_facets":{"min_ram_gb":null},"decision_summary":[{"label":"Requirements","value":"Requires Python environment setup for PyTorch and Jupyter Notebook familiarity."},{"label":"Adopt for","value":"Jackrong-llm-finetuning-guide: A targeted instructive resource for those seeking to fine-tune their large language models such as LLaMA3 and Qwen using PyTorch."},{"label":"License detail","value":"Apache License Version 2.0: Permits free use, distribution and modification of the software."}]}}