Florence-2-base / README.md
captainspock's picture
Create README.md
64e4a8f verified
metadata
base_model: microsoft/Florence-2-base
library_name: transformers.js
license: mit
pipeline_tag: image-text-to-text
tags:
  - vision
  - text-generation
  - text2text-generation
  - image-to-text

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.