OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

Aligning pretrained language models with instruction data generated by themselves.

Kernl lets you run PyTorch transformer models several times faster on GPU with a single line of code, and is designed to be easily hackable.

Fast and memory-efficient exact attention

FauxPilot - an open-source alternative to GitHub Copilot server

Implementation of Memorizing Transformers (ICLR 2022), attention net augmented with indexing and retrieval of memories using approximate nearest neighbors, in Pytorch

Playwright is a framework for Web Testing and Automation. It allows testing Chromium, Firefox and WebKit with a single API.

The hub for EleutherAI's work on interpretability and learning dynamics

Evolutionary solver for RoboZZle

Template repository to build PyTorch projects from source on any version of PyTorch/CUDA/cuDNN.

A place to keep track of all the annotated papers.

A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron and DeepSpeed libraries

The Data Explorer gives you fast, safe access to data stored in Cassandra, Dynomite, and Redis.

Papers from the computer science community to read and discuss.

Rust bindings to DPDK

Easy & Flexible Alerting With ElasticSearch