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.
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for webnn/Florence-2-base
Base model
microsoft/Florence-2-base