The official repo of Qwen2-Audio chat & pretrained large audio language model proposed by Alibaba Cloud.

Macros for simplifying boilerplate for creating UI using Ratatui.

🔍 A Hex Editor for Reverse Engineers, Programmers and people who value their retinas when working at 3 AM.

Arena-Hard-Auto: An automatic LLM benchmark.

20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.

🙌 OpenHands: Code Less, Make More

An interactive NVIDIA-GPU process viewer and beyond, the one-stop solution for GPU process management.

Official inference library for Mistral models

DSPy: The framework for programming—not prompting—foundation models

Fast inference engine for Transformer models

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

🎛 🔊 A Python library for audio.

An unofficial PyTorch implementation of Music Source Separation with Band-split RNN for MDX-23 ("Label Noise" Track)

Unofficial PyTorch implementation of Music Source Separation with Band-split RNN

Model for MDX23 music separation contest

A modern Anki custom scheduling based on Free Spaced Repetition Scheduler algorithm

Fast and easy-to-use event-driven network library.

💥 Fast State-of-the-Art Tokenizers optimized for Research and Production

document image degradation

A small script that makes it easy to fling a folder of images onto the Samsung Frame TV

Solve puzzles. Improve your pytorch.

LlamaIndex is a data framework for your LLM applications

the AI-native open-source embedding database

Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of …

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

Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.

Stable Diffusion built-in to Blender