pdufour
/

Qwen2-VL-7B-Instruct-onnx

Image-Text-to-Text

Transformers.js

Model card Files Files and versions Community

Qwen2-VL-7B-Instruct-onnx / README.md

pdufour's picture

Update README.md

e9d7494 verified 11 days ago

|

history blame contribute delete

308 Bytes

metadata

license: apache-2.0
tags:
  - transformers.js
base_model:
  - Qwen/Qwen2-VL-7B-Instruct

This is the 7b Qwen2-VL image model exported via https://github.com/pdufour/llm-export.

Also see https://huggingface.co/pdufour/Qwen2-VL-2B-Instruct-ONNX-Q4-F16 for a 2b model that is onnxruntime-webgpu compatible.