Instructions to use google/pix2struct-ocrvqa-large with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google/pix2struct-ocrvqa-large with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "visual-question-answering" 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("visual-question-answering", model="google/pix2struct-ocrvqa-large")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("google/pix2struct-ocrvqa-large") model = AutoModelForMultimodalLM.from_pretrained("google/pix2struct-ocrvqa-large", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download pytorch_model.bin from google/pix2struct-ocrvqa-large: direct link, hf CLI and curl.
- Browser
- Download file 5.34 GB
-
https://huggingface.co/google/pix2struct-ocrvqa-large/resolve/main/pytorch_model.bin
- Command line
-
hf download hf://google/pix2struct-ocrvqa-large/pytorch_model.bin
-
curl -L -o pytorch_model.bin https://huggingface.co/google/pix2struct-ocrvqa-large/resolve/main/pytorch_model.bin
5.34 GB
- Xet hash:
- b0a23708bbfced0a22449eb19970cb792261d6abc5bf352152bbc8713dab7eb2
- Size of remote file:
- 5.34 GB
- SHA256:
- afb0be96f4cd19b9a46789beb486ad64e812efd353a7e1370acb7dbe216ca6b4
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.