Stars
Visualizer for neural network, deep learning and machine learning models
Multimodal computer agent data collection program
What would you do with 1000 H100s...
Run AI models locally on your machine with node.js bindings for llama.cpp. Enforce a JSON schema on the model output on the generation level
Python library for designing and training your own Diffusion Models with PyTorch.
🔊 Text-Prompted Generative Audio Model
An unofficial PyTorch implementation of the audio LM VALL-E
Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"
Implementation of GigaGAN, new SOTA GAN out of Adobe. Culmination of nearly a decade of research into GANs
Creating a diffusion model from scratch in PyTorch to learn exactly how they work.
Automate your browser with GPT-4
Puzzles for exploring transformers
Blazing fast framework for fine-tuning similarity learning models
A game theoretic approach to explain the output of any machine learning model.
Noise supression using deep filtering
Official Code for DragGAN (SIGGRAPH 2023)
Brain-Inspired Modular Training (BIMT), a method for making neural networks more modular and interpretable.
Tensor computation with WebGPU acceleration
Conditional diffusion model to generate MNIST. Minimal script. Based on 'Classifier-Free Diffusion Guidance'.
Code repo for "Most Language Models can be Poets too: An AI Writing Assistant and Constrained Text Generation Studio" at the (CAI2) workshop, jointly held at (COLING 2022)
Fast Differentiable Tensor Library in JavaScript and TypeScript with Bun + Flashlight
Notebooks and various random fun
High availability implementation of AWS NAT instances.
GitHub App to watch for PRs merged without a reviewer approving.
Reference implementation of "An Algorithm for Routing Vectors in Sequences" (Heinsen, 2022) and "An Algorithm for Routing Capsules in All Domains" (Heinsen, 2019), for composing deep neural networks.
tiktoken is a fast BPE tokeniser for use with OpenAI's models.
An in memory postgres DB instance for your unit tests