Fast and accurate automatic speech recognition (ASR) for edge devices

A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API

Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

Official inference framework for 1-bit LLMs

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

PyTorch native finetuning library

Official code repo for the O'Reilly Book - "Hands-On Large Language Models"

Next-Token Prediction is All You Need

An AI-powered file management tool that ensures privacy by organizing local texts, images. Using Llama3.2 3B and Llava v1.6 models with the Nexa SDK, it intuitively scans, restructures, and organiz…

Inference code for CodeLlama models

tmux source code

VIP cheatsheets for Stanford's CS 229 Machine Learning

Kolmogorov-Arnold Transformer: A PyTorch Implementation with CUDA kernel

Repo designed to help learn the Hugging Face ecosystem (transformers, datasets, accelerate more).

Transform datasets at scale. Optimize datasets for fast AI model training.

vnc-lm is a Discord bot with Ollama, OpenRouter, Mistral, and Cohere API integration

Which model is the best at object detection? Which is best for small or large objects? We compare the results in a handy leaderboard.

Machine learning metrics for distributed, scalable PyTorch applications.

Robust Speech Recognition via Large-Scale Weak Supervision

Langflow is a low-code app builder for RAG and multi-agent AI applications. It’s Python-based and agnostic to any model, API, or database.

Library for Jacobian descent with PyTorch. It enables optimization of neural networks with multiple losses (e.g. multi-task learning).

A compact LLM pretrained in 9 days by using high quality data

KAN for Vision Transformer

This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. RAG systems combine information retrieval with generative models to provide accurate and cont…

Speech Recognition using DeepSpeech2.

A throughput-oriented high-performance serving framework for LLMs

LLM training in simple, raw C/CUDA

Efficient Triton Kernels for LLM Training