AI chat for any model.

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

Machine Learning Engineering Open Book

Converts text input or URL into knowledge graph and displays

A natural language interface for computers

High accuracy RAG for answering questions from scientific documents with citations

Python script to stream EEG data from the muse 2016 headset

Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".

VSCode extension for code suggestion

Full description can be found here: https://discuss.huggingface.co/t/pretrain-gpt-neo-for-open-source-github-copilot-model/7678?u=ncoop57

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.

A walkthrough of transformer architecture code

Supercharge Your Model Training

Turn (almost) any Python command line program into a full GUI application with one line

Sparsity-aware deep learning inference runtime for CPUs

Structured state space sequence models

A gallery to display recent images from the #the-faraday-cage discord channel

[IJCV 2022] Bridging Composite and Real: Towards End-to-end Deep Image Matting

Create delightful software with Jupyter Notebooks

Just playing with getting VQGAN+CLIP running locally, rather than having to use colab.

A CLIP conditioned Decision Transformer.

Adversarial Threat Landscape for AI Systems

A data augmentations library for audio, image, text, and video.

Implementation of popular deep learning networks with TensorRT network definition API

Labs and demos for courses for GCP Training (http://cloud.google.com/training).

Taming Transformers for High-Resolution Image Synthesis

A list of Machine Learning Art Colabs

Official Implementation for "StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery" (ICCV 2021 Oral)

StyleGAN2-ADA - Official PyTorch implementation

🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support