Deploy DeepSeek V4 Flash (MoE reasoning model) on dual DGX Spark nodes with 1M token context, InfiniBand, and FP8 KV-cache

SurrealDB SDK for Python

A scalable, distributed, collaborative, document-graph database, for the realtime web

[MLsys2026]: RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.

Source Code of Paper "GPTScore: Evaluate as You Desire"

Implementation of "BitNet: Scaling 1-bit Transformers for Large Language Models" in pytorch

ChatRWKV is like ChatGPT but powered by RWKV (100% RNN) language model, and open source.

Run Mixtral-8x7B models in Colab or consumer desktops

Pomerium is an identity and context-aware access proxy.

A reverse proxy that provides authentication with Google, Azure, OpenID Connect and many more identity providers.

🔐 Lockdoor Framework : A Penetration Testing framework with Cyber Security Resources

Lbl2Vec learns jointly embedded label, document and word vectors to retrieve documents with predefined topics from an unlabeled document corpus.

My Implementation of LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding

A SQLite extension for efficient vector search, based on Faiss!

Official PyTorch implementation of LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding (ACL 2022)

LLM training code for Databricks foundation models

OpenMMLab Text Detection, Recognition and Understanding Toolbox

Official implementation of the paper "Estimation of continuous valence and arousal levels from faces in naturalistic conditions", Antoine Toisoul, Jean Kossaifi, Adrian Bulat, Georgios Tzimiropoulo…

Pythonic bindings for FFmpeg's libraries.

WebRTC and ORTC implementation for Python using asyncio

Dimensional estimation of emotions (Arousal, Valence, Intensity) from facial landmarks extracted by DLIB.

A Lightweight Face Recognition and Facial Attribute Analysis (Age, Gender, Emotion and Race) Library for Python

Packaged, Pytorch-based, easy to use, cross-platform version of the CRAFT text detector

Official Implementation of OCR-free Document Understanding Transformer (Donut) and Synthetic Document Generator (SynthDoG), ECCV 2022

Powerful handwritten text recognition. A simple-to-use, unofficial implementation of the paper "TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models".

Handwritten text recognition using transformers.

REL: Radboud Entity Linker

spaCy module for linking text to Wikidata items