doberst's picture
Update README.md
8128083 verified
metadata
license: apache-2.0
inference: false
base_model: Qwen/Qwen2-VL-7B-Instruct
base_model_relation: quantized
tags:
  - green
  - llmware-vision
  - p7
  - ov
  - emerald

qwen2-vl-7b-instruct-ov

qwen2-vl-7b-instruct-ov is an OpenVino int4 quantized version of Qwen2-VL-7B-Instruct, providing a very fast, very small inference implementation, optimized for AI PCs using Intel GPU, CPU and NPU.

This is a multi-modal vision-to-text model from the Qwen2 release series from Qwen (summer 2024), and is a very high-quality innovative model that accepts multi-modal inputs (image/video, text).

Model Description

  • Developed by: Qwen
  • Quantized by: llmware
  • Model type: qwen2-vl
  • Parameters: 7 billion
  • Model Parent: Qwen/Qwen2-VL-7B-Instruct
  • Language(s) (NLP): English
  • License: Apache 2.0
  • Uses: Multi-Modal LLM
  • Quantization: int4

For an open source inference implementation, please see this Intel OpenVino notebook

Model Card Contact

llmware on github

llmware on hf

llmware website