ghwatson
Follow
Stars
Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.
Get up and running with OpenAI gpt-oss, DeepSeek-R1, Gemma 3 and other models.
Implementation of the proposed Spline-Based Transformer from Disney Research
Deep learning for dummies. All the practical details and useful utilities that go into working with real models.
PyTorch Lightning + Hydra. A very user-friendly template for ML experimentation. ⚡🔥⚡
Hiera: A fast, powerful, and simple hierarchical vision transformer.
Pytorch Implementation of the sparse attention from the paper: "Generating Long Sequences with Sparse Transformers"
Self-contained, minimalistic implementation of diffusion models with Pytorch.
Huggingface-compatible SDXL Unet implementation that is readily hackable
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
Official Pytorch Implementation for "TokenFlow: Consistent Diffusion Features for Consistent Video Editing" presenting "TokenFlow" (ICLR 2024)
Implementation of “DreamDiffusion: Generating High-Quality Images from Brain EEG Signals”
Invoke is a leading creative engine for Stable Diffusion models, empowering professionals, artists, and enthusiasts to generate and create visual media using the latest AI-driven technologies. The …
Deep learning toolkit for image, video, and audio synthesis
Official PyTorch implementation of Contrastive Learning of Musical Representations
This is the repo for my experiments with StyleGAN2. There are many like it, but this one is mine. Contains code for the paper Audio-reactive Latent Interpolations with StyleGAN.
python (BigGANx2048), MATLAB (wavenet, arss GUI), & WLNET (VAE, WGAN, etc.)
An adversarial example library for constructing attacks, building defenses, and benchmarking both
Repository for Kuzushiji-MNIST, Kuzushiji-49, and Kuzushiji-Kanji
A toolbox to iNNvestigate neural networks' predictions!
PHATE (Potential of Heat-diffusion for Affinity-based Transition Embedding) is a tool for visualizing high dimensional data.
Fast Fourier Transform-accelerated Interpolation-based t-SNE (FIt-SNE)
"Neural 3D Mesh Renderer" (CVPR 2018) by H. Kato, Y. Ushiku, and T. Harada.
Tensorflow implementation of a Neural Turing Machine
Code of 2D-to-3D style transfer in the paper "Neural 3D Mesh Renderer" by H. Kato, Y. Ushiku, and T. Harada.