Instructions to use google/deplot with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google/deplot 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/deplot")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("google/deplot") model = AutoModelForMultimodalLM.from_pretrained("google/deplot", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download onnx/encoder_model.onnx from google/deplot: direct link, hf CLI and curl.
- Browser
- Download file 368 MB
-
https://huggingface.co/google/deplot/resolve/refs%2Fpr%2F8/onnx/encoder_model.onnx
- Command line
-
hf download hf://google/deplot@refs/pr/8/onnx/encoder_model.onnx
-
curl -L -o encoder_model.onnx https://huggingface.co/google/deplot/resolve/refs%2Fpr%2F8/onnx/encoder_model.onnx
368 MB
- Xet hash:
- abb2523f875bfd3a0404e091610a2228cf39da8be8886db03db9e64f7fb313a9
- Size of remote file:
- 368 MB
- SHA256:
- 1fb7a8ffd1e06326ffb5259861edfcae560de518c2efd9b71edd9c36ec12c319
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.