webnn/Florence-2-base

By webnn · ↓ 0 · ♥ 0 · Updated 2025-11-20

What's in this repo

This page lists the files in webnn/Florence-2-base, including vision_encoder_fp16.onnx, vision_encoder_q4f16.onnx.

2 ONNX models (.onnx files)
4 files, including 2 .onnx, 1 .md
Last updated 2025-11-20

ONNX files

File	Size	Download
onnx/vision_encoder_fp16.onnx	—	Download
onnx/vision_encoder_q4f16.onnx	—	Download

How to use

These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.

README

Changes for WebNN

Vision Encoder: Changed data type of Pow Y = 0.5 to float32 from float16 for fp16 and q4f16 models.

Based on: https://huggingface.co/onnx-community/Florence-2-base/ https://huggingface.co/microsoft/Florence-2-base with ONNX weights to be compatible with Transformers.js.

Model info

image-text-to-text transformers.js

transformers.js onnx vision text-generation text2text-generation image-to-text image-text-to-text base_model:microsoft/Florence-2-base base_model:quantized:microsoft/Florence-2-base license:mit region:us

↓ 0 ♥ 0

Created: 2025-11-18

Updated: 2025-11-20

View on Hugging Face

Files (4)

.gitattributes

README.md

onnx/vision_encoder_fp16.onnx ONNX

onnx/vision_encoder_q4f16.onnx ONNX

Related models

More image-text-to-text models

Browse all image-text-to-text models