🧑🏫 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, ... 🧠
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.8, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM5.3, Gemma4, Llava, Phi4, ...) (AAAI 2025).
stable diffusion webui colab
Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"
- gpt-2
- adaptation
- language-model
- gpt-3
QLoRA: Efficient Finetuning of Quantized LLMs
TranslatedQwen-Image 2.1 NSFW/pose image generation skill: author-level prompt recipes + NSFW LoRA + 136-pose VNCCS mannequin control; works with Claude Code / Codex / Cursor / OpenClaw
OpenDILab Decision AI Engine. The Most Comprehensive Reinforcement Learning Framework B.P.
:truck: Agile Data Preparation Workflows made easy with Pandas, Dask, cuDF, Dask-cuDF, Vaex and PySpark
moDel Agnostic Language for Exploration and eXplanation
DataFrames for Go: For statistics, machine-learning, and data manipulation/exploration
Imagination Studio by keys+Wasserman powered by TensorFold: an AI film studio for Mac and NVIDIA DGX Spark. Plan a film like a crew (Slate workflow by Sam Wasserman), render Qwen-Image-2.1 / FLUX3-K pictures and MiniMax H3 / FastH3 video with sound on TensorFold.
- apple-silicon
- minimax-h3
- mlx
- qwen-image
Engine for AI/ML/Data tracking, visualization, explainability, drift detection, and dashboards for Polyaxon.
Reference-image character and style transfer for Anima in ComfyUI (offset-RoPE reference frame + LoRA)
- anima
- character-consistency
- comfyui
- comfyui-nodes
Peax is a tool for interactive visual pattern search and exploration in epigenomic data based on unsupervised representation learning with autoencoders
Conflict-free merge for DataFrames, JSON, ML models & distributed agents — powered by CRDTs. The first merge library where every operation is mathematically guaranteed to converge.