Stars
Flake for OpenStack compatible NixOS images
Burn is a next generation Deep Learning Framework that doesn't compromise on flexibility, efficiency and portability.
Pytorch implementations of Bayes By Backprop, MC Dropout BDA0 , SGLD, the Local Reparametrization Trick, KF-Laplace, SG-HMC and more
Minimal C# bindings for llama.cpp + .NET core library with API host/client.
Statistical model comparison with bootstrap and beyond
Generative LLMs & Uncertainty Estimates
Ultimate Plumber is a tool for writing Linux pipes with instant live preview
Saliency Cards are transparency documentation for saliency methods. Learn about new saliency methods or document your own!
Interact with your documents using the power of GPT, 100% privately, no data leaks
A library for writing reactive single page web apps
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 RN…
GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.
Display Zotero collection on E-Readers with KOReader
Train to 94% on CIFAR-10 in <6.3 seconds on a single A100. Or ~95.79% in ~110 seconds (or less!)
A toolkit to optimize ML models for deployment for Keras and TensorFlow, including quantization and pruning.