GitHub Open Source Insight
Computed at Sep 11, 2026GitHub repo leaderboard by stars, growth rate and activity.
microsoft
21 Lessons, Get Started Building with Generative AI
Jupyter Notebook119,458 starslast pushed Yesterdayrasbt
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
Jupyter Notebook104,659 starslast pushed 1 week agohiyouga
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
Python74,682 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, ... 🧠
Python67,405 starslast pushed 8 months agorohitg00
Learn it. Build it. Ship it for others.
Python53,785 starslast pushed 4 days agohuggingface
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
Python21,647 starslast pushed Yesterdaystas00
Machine Learning Engineering Open Book
Python18,950 starslast pushed Yesterdayarc53
Private AI platform for agents, assistants and enterprise search. Built-in Agent Builder, Deep research, Document analysis, Multi-model support, and API connectivity for agents.
Python18,248 starslast pushed YesterdayNVIDIA
Ongoing research training transformer models at scale
Python17,825 starslast pushed 23 hours agoBlinkDL
RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.
Python14,700 starslast pushed 1 week ago
| # | Repo | Language | Stars | 30-day trend | Last updated |
|---|---|---|---|---|---|
| 1 | microsoft 21 Lessons, Get Started Building with Generative AI | Jupyter Notebook | 119,458 | last pushed Yesterday | |
| 2 | rasbt Implement a ChatGPT-like LLM in PyTorch from scratch, step by step | Jupyter Notebook | 104,659 | last pushed 1 week ago | |
| 3 | hiyouga Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024) | Python | 74,682 | last pushed 2 days ago | |
| 4 | 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 | 67,405 | last pushed 8 months ago | |
| 5 | rohitg00 Learn it. Build it. Ship it for others. | Python | 53,785 | last pushed 4 days ago | |
| 6 | huggingface 🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning. | Python | 21,647 | last pushed Yesterday | |
| 7 | stas00 Machine Learning Engineering Open Book | Python | 18,950 | last pushed Yesterday | |
| 8 | arc53 Private AI platform for agents, assistants and enterprise search. Built-in Agent Builder, Deep research, Document analysis, Multi-model support, and API connectivity for agents. | Python | 18,248 | last pushed Yesterday | |
| 9 | NVIDIA Ongoing research training transformer models at scale | Python | 17,825 | — | last pushed 23 hours ago |
| 10 | BlinkDL RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding. | Python | 14,700 | last pushed 1 week ago |
All · 11,474