How to use google/pix2struct-textcaps-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="google/pix2struct-textcaps-base")
# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("google/pix2struct-textcaps-base") model = AutoModelForMultimodalLM.from_pretrained("google/pix2struct-textcaps-base", device_map="auto")
https://huggingface.co/google/pix2struct-textcaps-base/resolve/refs%2Fpr%2F5/tokenizer.json
hf download hf://google/pix2struct-textcaps-base@refs/pr/5/tokenizer.json
curl -L -o tokenizer.json https://huggingface.co/google/pix2struct-textcaps-base/resolve/refs%2Fpr%2F5/tokenizer.json
