Efficient Retrieval Augmentation and Generation Framework
A full spaCy pipeline and models for scientific/biomedical documents
Dealing with all unstructured data, such as reverse image search
Data processing for and with foundation models
Statistical library designed to fill the void in Python's time series
Algorithms for outlier, adversarial and drift detection
Easy-to-use LLM fine-tuning framework (LLaMA-2, BLOOM, Falcon
Large-scale Self-supervised Pre-training Across Tasks, Languages, etc.
Open-source, code-first Python toolkit for building, evaluating, etc.
Magnetoencephalography (MEG) and Electroencephalography EEG in Python
A high performance implementation of HDBSCAN clustering
SkyPilot: Run AI and batch jobs on any infra
Generate audiobooks from e-books, voice cloning & 1107+ languages
A comprehensive quantitative trading system with AI-powered analysis
A long-running autonomous coding agent powered by the Claude Agent
A Unified Framework for Text-to-3D and Image-to-3D Generation
Multimodal Diffusion with Representation Alignment
Easy-to-use Speech Toolkit including Self-Supervised Learning model
Conditional GAN for generating synthetic tabular data
A python library for self-supervised learning on images
Python chatbot framework with Natural Language Understanding
Deep learning library
Models for the spaCy Natural Language Processing (NLP) library
Train a 26M-parameter GPT from scratch in just 2h
Research-oriented chatbot framework