microsoft
/

Florence-2-large-ft

Image-Text-to-Text

text-generation

Model card Files Files and versions Community

Resources

View closed (8)

Using multiple prompts during inference

#28 opened 28 days ago by

Fix invalid escape sequences

#27 opened about 1 month ago by

Can someone explain the suffix for training task 'REFERRING_EXPRESSION_SEGMENTATION'?

#26 opened about 1 month ago by

Fixed a minor bug with region OCR always returning the first label with an erronious </s>

#25 opened about 2 months ago by

Resolving Accuracy Issues in Chinese Output for Florence-2 Fine-Tuned with LoRA

#24 opened 2 months ago by

Another finetune florence-2 example

#23 opened 2 months ago by

Are there a way to avoid trust_remote_code=True

#22 opened 2 months ago by

Fine Tuning for VQA

#21 opened 2 months ago by

Add get_output_embeddings

#18 opened 3 months ago by

hello, how can i reduce temperature?

#17 opened 3 months ago by

OPEN_VOCABULARY_DETECTION returns polygons which cannot be displayed

#16 opened 3 months ago by

Update README.md

#15 opened 3 months ago by

Swift now supports inference, training, and deployment of the Florence models.

#14 opened 3 months ago by

What is the prompt format for VQA?

#13 opened 3 months ago by

Chinese very bad

#12 opened 3 months ago by

Prompt Format for microsoft/Florence-2-large-ft model

#9 opened 3 months ago by

Fine Tuning

#8 opened 3 months ago by

Onnx version of this model for use with .NET apps

#7 opened 3 months ago by

How to utilize Florence to capture web element coordinates?

#6 opened 3 months ago by

Failed to run on MacBook: requiring flash_attn

#4 opened 3 months ago by