🙌 OpenHands: Code Less, Make More

A project to improve skills of large language models

Sparsify transformers with SAEs and transcoders

Training Sparse Autoencoders on Language Models

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

Python 3.6+ toolbox for submitting jobs to Slurm

YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/

An experimental open-source attempt to make GPT-4 fully autonomous.

LlamaIndex (GPT Index) is a project that provides a central interface to connect your LLM's with external data.

⚡ Building applications with LLMs through composability ⚡

VISSL is FAIR's library of extensible, modular and scalable components for SOTA Self-Supervised Learning with images.

Hydra is a framework for elegantly configuring complex applications

An implementation of Microsoft's "FastSpeech 2: Fast and High-Quality End-to-End Text to Speech"

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

Repo for external large-scale work