| library_name: transformers | |
| datasets: | |
| - flaviagiammarino/path-vqa | |
| language: | |
| - en | |
| base_model: | |
| - Salesforce/blip-vqa-base | |
| pipeline_tag: visual-question-answering | |
| # How to use: | |
| ## For inference | |
| ### Load model directly | |
| ```python | |
| from transformers import BlipForQuestionAnswering, BlipProcessor | |
| model = BlipForQuestionAnswering.from_pretrained("trieutm/blip-vqa-finetuned") | |
| processor = BlipProcessor.from_pretrained("trieutm/blip-vqa-finetuned") | |
| ``` |