21 Lessons, Get Started Building with Generative AI 🔗 https://microsoft.github.io/generative-ai-for-beginners/

A High-Quality Real Time Upscaler for Anime Video

Scripts for fine-tuning Meta Llama with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting…

Foundational Models for State-of-the-Art Speech and Text Translation

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…

AirLLM 70B inference with single 4GB GPU

A Bulletproof Way to Generate Structured JSON from Language Models

OmniGen: Unified Image Generation. https://arxiv.org/pdf/2409.11340

[ACL 2024] An Easy-to-use Knowledge Editing Framework for LLMs.

Efficient neural feature detector and descriptor

Open-source implementation of Google Vizier for hyper parameters tuning

Kernl lets you run PyTorch transformer models several times faster on GPU with a single line of code, and is designed to be easily hackable.

🦘 Explore multimedia datasets at scale

Recipes for shrinking, optimizing, customizing cutting edge vision models. 💜

Official implementation of "DCT-Net: Domain-Calibrated Translation for Portrait Stylization", SIGGRAPH 2022 (TOG); Multi-style cartoonization

Real-time portrait segmentation for mobile devices

NLP Zero to Hero in just 10 Kernels

Annotated version of the Mamba paper

This is the official repository for the LENS (Large Language Models Enhanced to See) system.

A Strict JSON Framework for LLM Outputs

Code for the paper "PortraitNet: Real-time portrait segmentation network for mobile device" @ CAD&Graphics2019

Quick exploration into fine tuning florence 2

The HierText dataset contains ~12k images from the Open Images dataset v6 with large amount of text entities. We provide word, line and paragraph level annotations.

The Java implementation of Dive into Deep Learning (D2L.ai)

Low-Rank adapter extraction for fine-tuned transformers models

Preprocessing pipeline notebooks and API supporting text extraction from SEC documents

Multidimensional indexing for tensors

look how they massacred my boy