Instructions to use google/pix2struct-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google/pix2struct-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-base")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("google/pix2struct-base") model = AutoModelForMultimodalLM.from_pretrained("google/pix2struct-base", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download pytorch_model.bin from google/pix2struct-base: direct link, hf CLI and curl.
- Browser
- Download file 1.13 GB
-
https://huggingface.co/google/pix2struct-base/resolve/main/pytorch_model.bin
- Command line
-
hf download hf://google/pix2struct-base/pytorch_model.bin
-
curl -L -o pytorch_model.bin https://huggingface.co/google/pix2struct-base/resolve/main/pytorch_model.bin
1.13 GB
- Xet hash:
- 5d1724882b85f065e1c7d7a22a25f4bb9355f49fca55f75055cef7ec62b19431
- Size of remote file:
- 1.13 GB
- SHA256:
- 9309d0f92cbfd28c13a38cbbea117dd2263a426e713b2559b192974566e34f28
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.