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")
# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("Salesforce/blip-image-captioning-base") model = AutoModelForMultimodalLM.from_pretrained("Salesforce/blip-image-captioning-base", device_map="auto")
https://huggingface.co/Salesforce/blip-image-captioning-base/resolve/refs%2Fpr%2F11/tokenizer.json
hf download hf://Salesforce/blip-image-captioning-base@refs/pr/11/tokenizer.json
curl -L -o tokenizer.json https://huggingface.co/Salesforce/blip-image-captioning-base/resolve/refs%2Fpr%2F11/tokenizer.json
