GitHub Open Source Insight
Computed at Sep 11, 2026GitHub repo leaderboard by stars, growth rate and activity.
hiyouga
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
Python74,699 starslast pushed 2 days agolabmlai
🧑🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠
Python67,418 starslast pushed 8 months agolyogavin
AirLLM 70B inference with single 4GB GPU
Jupyter Notebook34,090 starslast pushed 22 hours agodatawhalechina
《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调（全参数/Lora）、部署国内外开源大模型（LLM）/多模态大模型（MLLM）教程
Jupyter Notebook32,138 starslast pushed 2 weeks agohuggingface
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
Python21,652 starslast pushed 14 hours agoymcui
中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)
Python18,941 starslast pushed 5 months agomodelscope
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Gemma4, Llava, Phi4, ...) (AAAI 2025).
Python15,583 starslast pushed 11 hours agomeshtastic
The official firmware for Meshtastic, an open-source, off-grid mesh communication system.
C++8,277 starslast pushed 46 minutes agomymusise
基于ChatGLM-6B + LoRA的Fintune方案
Python3,739 starslast pushed 3 years agoFine-tuning ChatGLM-6B with PEFT | 基于 PEFT 的高效 ChatGLM 微调
Python3,712 starslast pushed 3 years ago
| # | Repo | Language | Stars | 30-day trend | Last updated |
|---|---|---|---|---|---|
| 1 | hiyouga Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024) | Python | 74,699 | last pushed 2 days ago | |
| 2 | labmlai 🧑🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠 | Python | 67,418 | last pushed 8 months ago | |
| 3 | lyogavin AirLLM 70B inference with single 4GB GPU | Jupyter Notebook | 34,090 | last pushed 22 hours ago | |
| 4 | datawhalechina 《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调（全参数/Lora）、部署国内外开源大模型（LLM）/多模态大模型（MLLM）教程 | Jupyter Notebook | 32,138 | last pushed 2 weeks ago | |
| 5 | huggingface 🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning. | Python | 21,652 | last pushed 14 hours ago | |
| 6 | ymcui 中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs) | Python | 18,941 | last pushed 5 months ago | |
| 7 | modelscope Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Gemma4, Llava, Phi4, ...) (AAAI 2025). | Python | 15,583 | last pushed 11 hours ago | |
| 8 | meshtastic The official firmware for Meshtastic, an open-source, off-grid mesh communication system. | C++ | 8,277 | last pushed 46 minutes ago | |
| 9 | mymusise 基于ChatGLM-6B + LoRA的Fintune方案 | Python | 3,739 | last pushed 3 years ago | |
| 10 | hiyouga Fine-tuning ChatGLM-6B with PEFT | 基于 PEFT 的高效 ChatGLM 微调 | Python | 3,712 | last pushed 3 years ago |
All · 11,658