An open-source AI agent that brings the power of Gemini directly into your terminal.

Entropy Based Sampling and Parallel CoT Decoding

Benchmark LLMs by fighting in Street Fighter 3! The new way to evaluate the quality of an LLM

Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation

Transformers are Sample-Efficient World Models. ICLR 2023, notable top 5%.

Accessible large language models via k-bit quantization for PyTorch.

Data and code for the paper "A Neural Network Solves, Explains, and Generates University Math Problems by Program Synthesis and Few-Shot Learning at Human Level" by Drori et al., 2022.

Python library which enables complex compositions of language models such as scratchpads, chain of thought, tool use, selection-inference, and more.

Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.

Making large AI models cheaper, faster and more accessible

Train transformer language models with reinforcement learning.

Code for the paper "Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer"

Unsupervised text tokenizer for Neural Network-based text generation.

Beyond the Imitation Game collaborative benchmark for measuring and extrapolating the capabilities of language models

Residual Feature Distillation Network for Lightweight Image Super-Resolution

An implementation of the RL-NTM from http://arxiv.org/abs/1505.00521

A PyTorch implementation of the Transformer model in "Attention is All You Need".

Objectron is a dataset of short, object-centric video clips. In addition, the videos also contain AR session metadata including camera poses, sparse point-clouds and planes. In each video, the came…

A deep learning library for video understanding research.

Platform for Situated Intelligence

Pretrained Language Models for Source code

☁️ 🚀 📊 📈 Evaluating state of the art in AI

The Unity Machine Learning Agents Toolkit (ML-Agents) is an open-source project that enables games and simulations to serve as environments for training intelligent agents using deep reinforcement …

Code repository for the Animal AI Olympics competition

A Python port of Google TensorFlow.js PoseNet (Real-time Human Pose Estimation)

Dear PyGui: A fast and powerful Graphical User Interface Toolkit for Python with minimal dependencies

Gesture based playback control. Build with 20bn-realtimenet!

Retro Games in Gym

Enhance your iOS app with the ability to see and interact with humans using the RGB camera.