Instructions to use google/pix2struct-widget-captioning-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google/pix2struct-widget-captioning-base 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-widget-captioning-base")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("google/pix2struct-widget-captioning-base") model = AutoModelForMultimodalLM.from_pretrained("google/pix2struct-widget-captioning-base", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download model.safetensors from google/pix2struct-widget-captioning-base: direct link, hf CLI and curl.
- Browser
- Download file 1.13 GB
-
https://huggingface.co/google/pix2struct-widget-captioning-base/resolve/main/model.safetensors
- Command line
-
hf download hf://google/pix2struct-widget-captioning-base/model.safetensors
-
curl -L -o model.safetensors https://huggingface.co/google/pix2struct-widget-captioning-base/resolve/main/model.safetensors
1.13 GB
- Xet hash:
- 3e21f035f7d7720b78187d81f7037fb71f49d004698e3133e463a0d47e6b06ae
- Size of remote file:
- 1.13 GB
- SHA256:
- 0b096c351692854237aa9fca73e973e3f764f376afc84999357614bac36e2b92
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.