Repository navigation
Support for microsoft/Florence-2-large-ft vision model #658
Replies: 14 comments 4 replies
|
+1! Would love to have this in ONNX |
|
+1 It would be great to have this in ONNX. |
|
Thanks all for the suggestion; we'll add this model to our roadmap and we'll discuss the priority internally. Thanks! |
|
Xenova created an Onnx version of the Florence model |
|
AshD (@AshD) Been looking for that, thank you! |
Thank you. Any news for support on python? Xenova's onnx florence-2 model requires transformers.js |
|
Thank you for your interest in Florence-2 V. We are looking into it. Moving this issue into Discussions |
|
+1 |
|
+1 |
|
Could the author write a document about how to convert florence model to onnx format? |
|
Add same support request for new phi-3.5-vision |
|
I made an onnxruntime inference script for Florence2: |
|
Nat Kershaw (MSFT) (@natke) Any update regarding Florence 2? |
|
Please provide an official onnx for the model 🙏 Using this in the meantime. |
Uh oh!
There was an error while loading. Please reload this page.
microsoft/Florence-2-large-ft works really well and it is much smaller than Phi-3 vision.
Would it be possible to convert this model in Onnx format?
Thanks,
Ash
All reactions