Exploration into leveraging vision capabilities of an LLM

Official inference framework for 1-bit LLMs

A framework for standardizing evaluations of large foundation models, beyond single-score reporting and rankings.

LLM token utility library

Semantic Kernel for Java. Integrate cutting-edge LLM technology quickly and easily into your Java based apps. See https://aka.ms/semantic-kernel.

Prompty makes it easy to create, manage, debug, and evaluate LLM prompts for your AI applications. Prompty is an asset class and format for LLM prompts designed to enhance observability, understandability, and portability for developers.

Research and development (R&D) is crucial for the enhancement of industrial productivity, especially in the AI era, where the core aspects of R&D are mainly focused on data and models. We are committed to automating these high-value generic R&D processes through our open source R&D automation tool RD-Agent, which lets AI drive data-driven AI.

A modular graph-based Retrieval-Augmented Generation (RAG) system

BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.

Low-bit LLM inference on CPU with lookup table

A UI-Focused Agent for Windows OS Interaction.

Learn how to build solutions with Large Language Models.

A low-latency & high-throughput serving engine for LLMs

OTOv1-v3, NeurIPS, ICLR, TMLR, DNN Training, Compression, Structured Pruning, Erasing Operators, CNN, Diffusion, LLM

Model, Code & Data for the EMNLP'23 paper "Making Large Language Models Better Data Creators"

GenAIOps with Prompt Flow is a "GenAIOps template and guidance" to help you build LLM-infused apps using Prompt Flow. It offers a range of features including Centralized Code Hosting, Lifecycle Management, Variant and Hyperparameter Experimentation, A/B Deployment, reporting for all runs and experiments and so on.

The RAG Experiment Accelerator is a versatile tool designed to expedite and facilitate the process of conducting experiments and evaluations using Azure Cognitive Search and RAG pattern.

A code-first agent framework for seamlessly planning and executing data analytics tasks.

Bridging LLM and Recommender System.

A programming framework for agentic AI 🤖

Automatable GenAI Scripting

RAG architecture: index and query any data using LLM and natural language, track sources, show citations, asynchronous memory patterns.

[EMNLP'23, ACL'24] To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.

Build high-quality LLM apps - from prototyping, testing to production deployment and monitoring.

TypeChat is a library that makes it easy to build natural language interfaces using types.

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

Large Language-and-Vision Assistant for Biomedicine, built towards multimodal GPT-4 level capabilities.

Sample code for a simple web chat experience through Azure OpenAI, including Azure OpenAI On Your Data.

JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf

Integrate cutting-edge LLM technology quickly and easily into your apps

Community for applying LLMs to robotics and a robot simulator with ChatGPT integration

Generating and validating natural-language explanations.

General technology for enabling AI capabilities w/ LLMs and MLLMs

Foundation Architecture for (M)LLMs

A pre-trained GPT model for Python code completion and generation

Official Implementation of "DialogLM: Pre-trained Model for Long Dialogue Understanding and Summarization."

[NeurIPS 2021] COCO-LM: Correcting and Contrasting Text Sequences for Language Model Pretraining

Code to reproduce experiments in the paper "Constrained Language Models Yield Few-Shot Semantic Parsers" (EMNLP 2021).

Large-scale pretraining for dialogue

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

A library & tools to evaluate predictive language models.

Windows SDK for the Microsoft Web Language Model API, part of Cognitive Services