pdufour
/

Qwen2-VL-7B-Instruct-onnx

This is the 7b Qwen2-VL image model (https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct) exported via https://github.com/pdufour/llm-export.

Author: Paul Dufour (https://www.linkedin.com/in/pauldufour/)

Original model: https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct

Credit: All credit for the model architecture, training, and published weights belongs to the original authors model linked above. This repo only provides the ONNX export.

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

Downloads last month: 5

Inference Providers NEW

Image-Text-to-Text

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for pdufour/Qwen2-VL-7B-Instruct-onnx

Base model

Qwen/Qwen2-VL-7B

Finetuned

Qwen/Qwen2-VL-7B-Instruct

Quantized

(59)

this model