Visual Question Answering
Transformers
Safetensors
English
florence2
image-text-to-text
vision-language
VQA
florence
microsoft
inclusive-ai
custom_code
Eval Results (legacy)
Instructions to use Zagarsuren/florence2-finetuned-vizwiz with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Zagarsuren/florence2-finetuned-vizwiz with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("visual-question-answering", model="Zagarsuren/florence2-finetuned-vizwiz", trust_remote_code=True)# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("Zagarsuren/florence2-finetuned-vizwiz", trust_remote_code=True) model = AutoModelForMultimodalLM.from_pretrained("Zagarsuren/florence2-finetuned-vizwiz", trust_remote_code=True) - Notebooks
- Google Colab
- Kaggle
File too large to display, you can check the raw version instead.