phi3-vision

This is a Phi Family of SLMs book for getting started with Phi Models. Phi a family of open sourced AI models developed by Microsoft. Phi 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

🔥🔥 LLaVA++: Extending LLaVA with Phi-3 and LLaMA-3 (LLaVA LLaMA-3, LLaVA Phi-3)

This repository is used for making demonstration of running Phi-3, Microsoft's Small Language Model, locally on the device by using ollama, along with Python library, Streamlit. With the use case of Phi-3 vision.

This repository contains Python code for performing vision tasks using the Microsoft Phi-3 Vision model and the Hugging Face library. It demonstrates generating textual responses based on image content, showcasing the integration of advanced vision-language models for tasks such as image analysis and descriptive text generation.

Setting up LLM inference On-Premise Environments

Desktop VLM: Real-time PHI-3.5 analysis of video & textures with live compute shaders

This is an integration application for Canva platform. User who uses this application can get feedback on their presentations and designs from AI. AI evaluates user's designs by giving them a score from 0 to 10, explanation of why such a score was given and some tips for improvements.

Proof of concept for using the 'microsoft/Phi-3-vision-128k-instruct-onnx-cpu' model in the .NET ecosystem with the ONNX runtime running on the CPU.