Instructions to use microsoft/kosmos-2-patch14-224 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use microsoft/kosmos-2-patch14-224 with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "image-to-text" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("image-to-text", model="microsoft/kosmos-2-patch14-224")# Load model directly from transformers import AutoProcessor, AutoModelForImageTextToText processor = AutoProcessor.from_pretrained("microsoft/kosmos-2-patch14-224") model = AutoModelForImageTextToText.from_pretrained("microsoft/kosmos-2-patch14-224") - Notebooks
- Google Colab
- Kaggle
How to get the model to describe the picture in detail
#7
by li111111111123 - opened
When I change the prompt to "Describe this image in detail:", the model outputs the same as when the prompt is "An image of ". But I want to make the kosmos-2 model describe the image in detail, how should I do it?
Have you tried <grounding> Describe this image in detail: as the prompt?
Have you tried
<grounding> Describe this image in detail:as the prompt?
Thanks for the reply, I found the reason because I selected load_in_4bit=True when I loaded the model