filannim

qdrant

Qdrant - High-performance, massive-scale Vector Database for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/

fluentui

Fluent UI web represents a collection of utilities, React components, and web components for building web applications.

codellama

Inference code for CodeLlama models

flair

A very simple framework for state-of-the-art Natural Language Processing (NLP)

promptflow

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

gpt-prompt-engineer

lm-evaluation-harness

A framework for few-shot evaluation of language models.

TaskWeaver

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

pandarallel

A simple and efficient tool to parallelize Pandas operations on all available CPUs

LMOps

General technology for enabling AI capabilities w/ LLMs and MLLMs

lida

Automatic Generation of Visualizations and Infographics using Large Language Models

DialoGPT

Large-scale pretraining for dialogue

numexpr

Fast numerical array expression evaluator for Python, NumPy, Pandas, PyTables and more

pythia

The hub for EleutherAI's work on interpretability and learning dynamics

bert_score

BERT score for text generation

sample-app-aoai-chatGPT

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

Phi-3CookBook

This is a Phi-3 book for getting started with Phi-3. Phi-3, a family of open AI models developed by Microsoft. Phi-3 models are the most capable and cost-effective small language models (SLMs) available, outperforming models of the same size and next size up across a variety of language, reasoning, coding, and math benchmarks.

Semi-supervised-learning

A Unified Semi-Supervised Learning Codebase (NeurIPS'22)

DB-GPT-Hub

A repository that contains models, datasets, and fine-tuning techniques for DB-GPT, with the purpose of enhancing model performance in Text-to-SQL

fastRAG

Efficient Retrieval Augmentation and Generation Framework

whisper.api

This project provides an API with user level access support to transcribe speech to text using a finetuned and processed Whisper ASR model.

fill

Generative fill in 3D.

onprem

A tool for running on-premises large language models with non-public data

PubSec-Info-Assistant

Information Assistant, built with Azure OpenAI Service, Industry Accelerator

llama2_aided_tesseract

Enhance Tesseract OCR output for scanned PDFs by applying Large Language Model (LLM) corrections, complete with options for text validation and hallucination filtering.

umberto

UmBERTo: an Italian Language Model trained with Whole Word Masking.

assistant-pf-demo

Demo for a Prompt Flow using OpenAI Assistants

mslearn-ai-document-intelligence

Lab files for Azure AI Document Intelligence modules

azure-streamlit-chatbot

Example for Deploying Chatbot using Streamlit and Azure Web App

fairseq

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.