Instructions to use Salesforce/blip-itm-base-coco with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Salesforce/blip-itm-base-coco with Transformers:
# Load model directly from transformers import AutoProcessor, BlipForImageTextRetrieval processor = AutoProcessor.from_pretrained("Salesforce/blip-itm-base-coco") model = BlipForImageTextRetrieval.from_pretrained("Salesforce/blip-itm-base-coco") - Notebooks
- Google Colab
- Kaggle
Add TF weights
#2
by Rocketknight1 HF Staff - opened
Model converted by the transformers' pt_to_tf CLI. All converted model outputs and hidden layers were validated against its PyTorch counterpart.
Maximum crossload output difference=1.669e-06; Maximum crossload hidden layer difference=1.544e-01;
Maximum conversion output difference=1.669e-06; Maximum conversion hidden layer difference=1.544e-01;
CAUTION: The maximum admissible error was manually increased to 0.2!
Thanks!
ybelkada changed pull request status to merged