Instructions to use gagan3012/ViTGPT2_vizwiz with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use gagan3012/ViTGPT2_vizwiz 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="gagan3012/ViTGPT2_vizwiz")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("gagan3012/ViTGPT2_vizwiz") model = AutoModelForMultimodalLM.from_pretrained("gagan3012/ViTGPT2_vizwiz", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download pytorch_model.bin from gagan3012/ViTGPT2_vizwiz: direct link, hf CLI and curl.
- Browser
- Download file 743 MB
-
https://huggingface.co/gagan3012/ViTGPT2_vizwiz/resolve/main/pytorch_model.bin
- Command line
-
hf download hf://gagan3012/ViTGPT2_vizwiz/pytorch_model.bin
-
curl -L -o pytorch_model.bin https://huggingface.co/gagan3012/ViTGPT2_vizwiz/resolve/main/pytorch_model.bin
743 MB
- Xet hash:
- b591d67b85b2563534902fd0e4be0d72df1411011d77f274adb543852c085878
- Size of remote file:
- 743 MB
- SHA256:
- c6b97772ecd10f82d3058a03ee8119858c4e868755ca5ff17409cc97fcf9f2f2
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.