Instructions to use Salesforce/blip-vqa-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Salesforce/blip-vqa-base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("visual-question-answering", model="Salesforce/blip-vqa-base")# Load model directly from transformers import AutoProcessor, AutoModelForVisualQuestionAnswering processor = AutoProcessor.from_pretrained("Salesforce/blip-vqa-base") model = AutoModelForVisualQuestionAnswering.from_pretrained("Salesforce/blip-vqa-base") - 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=5.014e-03; Maximum crossload hidden layer difference=1.158e-01;
Maximum conversion output difference=5.014e-03; Maximum conversion hidden layer difference=1.158e-01;
CAUTION: The maximum admissible error was manually increased to 0.2!
Thanks!
ybelkada changed pull request status to merged