Flax is a neural network library for JAX that is designed for flexibility.

Vector (and Scalar) Quantization, in Pytorch

Evaluation of Vision-Language models' multilingual properties in 20 different languages.

Official Implementation of "Graph-constrained Reasoning: Faithful Reasoning on Knowledge Graphs with Large Language Models".

Pocket-Sized Multimodal AI for content understanding and generation across multilingual texts, images, and 🔜 video, up to 5x faster than OpenAI CLIP and LLaVA 🖼️ & 🖋️

Web Serving and Remote Procedure Calls at 50x lower latency and 70x higher bandwidth than FastAPI, implementing JSON-RPC & REST over io_uring ☎️

A library for mechanistic interpretability of GPT-style language models

Docs of the Hugging Face Hub

🚀 A simple way to train and use PyTorch models with multi-GPU, TPU, mixed-precision

Demonstration that finetuning RoPE model on larger sequences than the pre-trained model adapts the model context limit

RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference,…

Course notes for CS228: Probabilistic Graphical Models.

A multi-voice TTS system trained with an emphasis on quality

A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API

Flower - A Friendly Federated Learning Framework