Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: microsoft/Florence-2-base
|
| 3 |
+
library_name: transformers.js
|
| 4 |
+
license: mit
|
| 5 |
+
pipeline_tag: image-text-to-text
|
| 6 |
+
tags:
|
| 7 |
+
- vision
|
| 8 |
+
- text-generation
|
| 9 |
+
- text2text-generation
|
| 10 |
+
- image-to-text
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
|
| 14 |
+
|
| 15 |
+
## Changes for WebNN
|
| 16 |
+
|
| 17 |
+
Vision Encoder: Changed data type of Pow Y = 0.5 to float32 from float16 for fp16 and q4f16 models.
|
| 18 |
+
|
| 19 |
+
Based on:
|
| 20 |
+
https://huggingface.co/onnx-community/Florence-2-base/
|
| 21 |
+
https://huggingface.co/microsoft/Florence-2-base with ONNX weights to be compatible with Transformers.js.
|
| 22 |
+
|