Instructions to use Salesforce/blip-image-captioning-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Salesforce/blip-image-captioning-base 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="Salesforce/blip-image-captioning-base")# Load model directly from transformers import AutoProcessor, AutoModelForImageTextToText processor = AutoProcessor.from_pretrained("Salesforce/blip-image-captioning-base") model = AutoModelForImageTextToText.from_pretrained("Salesforce/blip-image-captioning-base") - Notebooks
- Google Colab
- Kaggle
Add tokenizer.json
#8
by jonatanklosko - opened
This is the only Salesforce/blip-* checkpoint without tokenizer.json, so adding for consistency :)
Generated with:
from transformers import BertTokenizerFast
tokenizer = BertTokenizerFast.from_pretrained("/Users/jonatanklosko/git/hf/blip-image-captioning-base/")
tokenizer.save_pretrained("/Users/jonatanklosko/git/hf/blip-image-captioning-base/")
jonatanklosko changed pull request status to open
Thanks a lot for the addition!
ybelkada changed pull request status to merged