https://github.com/labmlai/annotated_deep_learning_paper_implementations
🧑🏫 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, ... 🧠
https://github.com/labmlai/annotated_deep_learning_paper_implementations
attention deep-learning deep-learning-tutorial gan literate-programming lora machine-learning neural-networks optimizers pytorch reinforcement-learning transformer transformers
Last synced: 1 day ago
JSON representation
🧑🏫 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, ... 🧠
- Host: GitHub
- URL: https://github.com/labmlai/annotated_deep_learning_paper_implementations
- Owner: labmlai
- License: mit
- Created: 2020-08-25T02:29:34.000Z (about 6 years ago)
- Default Branch: master
- Last Pushed: 2026-11-02T05:57:43.000Z (15 days ago)
- Last Synced: 2026-11-14T21:33:55.819Z (2 days ago)
- Topics: attention, deep-learning, deep-learning-tutorial, gan, literate-programming, lora, machine-learning, neural-networks, optimizers, pytorch, reinforcement-learning, transformer, transformers
- Language: Python
- Homepage: https://nn.labml.ai
- Size: 149 MB
- Stars: 67,752
- Watchers: 496
- Forks: 6,790
- Open Issues: 47
-
Metadata Files:
- Readme: readme.md
- Funding: .github/FUNDING.yml
- License: license
Awesome Lists containing this project
- awesome-python - labmlai/annotated_deep_learning_paper_implementations - 🧑🏫 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, ... 🧠 (Other / Scientific Computing)
- awesome-cs-tutorial - https://github.com/labmlai/annotated_deep_learning_paper_implementations
- awesome-open-source-ai-tools - labmlai/annotated_deep_learning_paper_implementations - 🧑🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original... (Image Generation & Editing)
- awesome-ARTificial - annotated_deep_learning_paper_implementations - 🧑🏫 59 Implementations/tutorials of deep learning papers. (Uncategorized / Uncategorized)
- ai-links - GitHub - labmlai/annotated_deep_learning_paper_implementations: 🧑🏫 50! Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, …), optimizers (Adam, adabelief, …), gans(cyclegan, stylegan2, …), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, … 🧠
- AiTreasureBox - labmlai/annotated_deep_learning_paper_implementations
- awesome-data-analysis - Annotated deep learning paper implementations - Implementations of deep learning papers with annotated code. (🤖 Machine Learning & AI / Resources)
- awesome-ai-agent-stack - labmlai/annotated_deep_learning_paper_implementations - Paper implementations with line-by-line notes. (Learning Path)
- github-ultimate-repos - labmlai/annotated_deep_learning_paper_implementations - | ⭐ 67,600★ | 🍴 6,755 | 💻 `Python`🔗 <https://github.com/labmlai/annotated_deep_learning_paper_implementations>📝 🧑🏫 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, ... 🧠⚙️ `BPE/SentencePiece tokenization -> RoPE positional rotation -> FlashAttention-2 KV-cache -> fused quantized GEMM execution -> Softmax top-p sampling.` (📜 Master Categorized Repository Directory (100% Clickable Links) / [02] ARTIFICIAL INTELLIGENCE, LARGE LANGUAGE MODELS, FOUNDATION MODELS & QUANTIZATION)
- best_ai_repo_collection - labmlai/annotated_deep_learning_paper_implementations - by-side notes 📝; including transformers (original, xl, swit... | (🧠 LLMs & Foundation Models (45))