A Native-PyTorch Library for LLM Fine-tuning

Devika is an Agentic AI Software Engineer that can understand high-level human instructions, break them down into steps, research relevant information, and write code to achieve the given objective…

A nearly-live implementation of OpenAI's Whisper.

WhisperFusion builds upon the capabilities of WhisperLive and WhisperSpeech to provide a seamless conversations with an AI.

EmotiVoice 😊: a Multi-Voice and Prompt-Controlled TTS Engine

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficie…

Segment Anything in High Quality [NeurIPS 2023]

An open-source efficient deep learning framework/compiler, written in python.

Inference code and configs for the ReplitLM model family

OpenAGI: When LLM Meets Domain Experts

PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.

An unofficial implementation of the σReparam from the "Stabilizing Transformer Training by Preventing Attention Entropy Collapse" paper

Accessible large language models via k-bit quantization for PyTorch.

An Open Source text-to-speech system built by inverting Whisper.

A playbook for systematically maximizing the performance of deep learning models.

OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

LlamaIndex is a data framework for your LLM applications

A Library for Differentiable Logic Gate Networks

ROS bridge for CARLA Simulator

The simplest, fastest repository for training/finetuning medium-sized GPTs.

Cramming the training of a (BERT-type) language model into limited compute.

A multi-voice TTS system trained with an emphasis on quality

A modular RL library to fine-tune language models to human preferences

Streaming transcriber with whisper

Port of OpenAI's Whisper model in C/C++

Hackable and optimized Transformers building blocks, supporting a composable construction.

A PyTorch-based Speech Toolkit