AI wearables. Put it on, speak, transcribe, automatically

Foundational model for human-like, expressive TTS

LLM training in simple, raw C/CUDA

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

Parse partial JSON generated by LLM

tiny vision language model

Local semantic search. Stupidly simple.

Mamba SSM architecture

AppAgent: Multimodal Agents as Smartphone Users, an LLM-based multimodal agent framework designed to operate smartphone apps.

A natural language interface for computers

Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)

Swift app demonstrating Core ML Stable Diffusion

A drawer component for React.

Jitsu is an open-source Segment alternative. Fully-scriptable data ingestion engine for modern data teams. Set-up a real-time data pipeline in minutes, not days

Scheduling infrastructure for absolutely everyone.

Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

A Next.js template with everthing your web3 app needs.

very good whiteboard SDK / infinite canvas SDK

An AutoGPT agent that controls Chrome on your desktop

Fully transparent SSH, HTTPS, MySQL and Postgres bastion/PAM that doesn't need additional client-side software

An all in one solution for adding Temporal Stability to a Stable Diffusion Render via an automatic1111 extension

🔊 Text-Prompted Generative Audio Model

🚀 BARK INFINITY GUI CMD 🎶 Powered Up Bark Text-prompted Generative Audio Model

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

Vector AI — A platform for building vector based applications. Encode, query and analyse data using vectors.

Code for the paper "ViperGPT: Visual Inference via Python Execution for Reasoning"

EVM frontrunning tool