Instructions to use google/pix2struct-ai2d-large with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google/pix2struct-ai2d-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-ai2d-large")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("google/pix2struct-ai2d-large") model = AutoModelForMultimodalLM.from_pretrained("google/pix2struct-ai2d-large", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download pytorch_model.bin from google/pix2struct-ai2d-large: direct link, hf CLI and curl.
- Browser
- Download file 5.34 GB
-
https://huggingface.co/google/pix2struct-ai2d-large/resolve/main/pytorch_model.bin
- Command line
-
hf download hf://google/pix2struct-ai2d-large/pytorch_model.bin
-
curl -L -o pytorch_model.bin https://huggingface.co/google/pix2struct-ai2d-large/resolve/main/pytorch_model.bin
5.34 GB
- Xet hash:
- da79876f50b04278e32e229b39540559ecf3b378df0c4123059b35da5881cdaf
- Size of remote file:
- 5.34 GB
- SHA256:
- d4abbc198c7eba33e396c855dbab4977cdf4813ce1cebe3599267438486aee9e
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.