A GPU-rendered terminal emulator with inline 3D graphics 🐀🧀

Give Claude Code a subconscious

Agent File (.af): An open file format for serializing stateful AI agents with persistent memory and behavior. Share, checkpoint, and version control agents across compatible frameworks.

Sandboxed code execution for AI agents, locally or on the cloud. Massively parallel, easy to extend. Powering SWE-agent and more.

control your music from the command line

Emoji for everyone.

Implementation for MatMul-free LM.

A curriculum for learning about foundation models, from scratch to the frontier

Open sourced predictions, execution logs, trajectories, and results from model inference + evaluation runs on the SWE-bench task.

Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.

SWE-bench: Can Language Models Resolve Real-world Github Issues?

Running large language models on a single GPU for throughput-oriented scenarios.

Pretrain and finetune ELECTRA with fastai and huggingface. (Results of the paper replicated !)

Presentation Slides for Developers

List of Computer Science courses with video lectures.

A full stack web framework written in janet

Shared repository for open-sourced projects from the Google AI Language team.

Princeton NLP's pre-training library based on fairseq with DeepSpeed kernel integration 🚃

A template repo for Python packages

Code to reproduce experiments in the paper "Task-Oriented Dialogue as Dataflow Synthesis" (TACL 2020).

[NeurIPS 2022] DataMUX: Data Multiplexing for Neural Networks

Fixes macOS Preview garbled annotations

This repository contains demos I made with the Transformers library by HuggingFace.