open source interpretability platform 🧠

A FastAPI library that provides Model Context Protocol (MCP) tools for endpoint introspection and OpenAPI documentation. This library allows AI agents to discover and understand your FastAPI endpoi…

A TTS model capable of generating ultra-realistic dialogue in one pass.

Jan is an open source alternative to ChatGPT that runs 100% offline on your computer.

This project simulates the WWVB signal broadcast from the National Institute of Standards and Technology (NIST) in Fort Collins Colorado.

Tools for merging pretrained large language models.

A graph node engine and editor written in Javascript similar to PD or UDK Blueprints, comes with its own editor in HTML5 Canvas2D. The engine can run client side or server side using Node. It allow…

Implementation of E2-TTS, "Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS", in Pytorch

Fast and memory-efficient exact attention

StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models

AudioLDM: Generate speech, sound effects, music and beyond, with text.

Noise supression using deep filtering

QLoRA: Efficient Finetuning of Quantized LLMs

Official implementation of Half-Quadratic Quantization (HQQ)

Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs

Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)

This is a port of Mistral-7B model in JAX

LLM training in simple, raw C/CUDA

Port of Mistral 7B in Keras and JAX

Agent driven automation starting with the web. Try it: https://www.emergence.ai/web-automation-api

Official repository of Evolutionary Optimization of Model Merging Recipes

Code at the speed of thought – Zed is a high-performance, multiplayer code editor from the creators of Atom and Tree-sitter.

Latency and Memory Analysis of Transformer Models for Training and Inference

3D Visualization of an GPT-style LLM

Modular Python framework for AI agents and workflows with chain-of-thought reasoning, tools, and memory.

A high-throughput and memory-efficient inference and serving engine for LLMs

A chrome extension that corrects typos & mispellings on-demand

Minimalist ML framework for Rust

Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable…