An open-source framework for detecting, redacting, masking, and anonymizing sensitive data (PII) across text, images, and structured data. Supports NLP, pattern matching, and customizable pipelines.

An Open-Source Framework for Prompt-Learning.

🚀 Efficient implementations of state-of-the-art linear attention models

Sky-T1: Train your own O1 preview model within $450

Version-control CVs/resumes as source code

Code and model for the paper "Improving Language Understanding by Generative Pre-Training"

Dataset of GPT-2 outputs for research in detection, biases, and more

Your Virtual Development Team

🔥 Reliable Browser AI Agents (YC S25)

THIS REPOSITORY IS JUST A MIRROR! The main development repository is https://codeberg.org/Freedium-cfd/web

Official implementation of the papers "GECToR – Grammatical Error Correction: Tag, Not Rewrite" (BEA-20) and "Text Simplification by Tagging" (BEA-21)

Running Docling as an API service

Heuristic based boilerplate removal tool

OpenMusic: SOTA Text-to-music (TTM) Generation

Efficient Inference for Big Models

MAGMA - a GPT-style multimodal model that can understand any combination of images and language. NOTE: The freely available model from this repo is only a demo. For the latest multimodal and multil…

Interactive Jupyter Notebook Environment for using the GPT-3 Instruct API

Ling-V2 is a MoE LLM provided and open-sourced by InclusionAI.

Model Compression for Big Models

The RedStone repository includes code for preparing extensive datasets used in training large language models.

TUTA and ForTaP for Structure-Aware and Numerical-Reasoning-Aware Table Pre-Training

Stable Diffusion

Easily test webhooks and other HTTP requests