Instructions to use microsoft/trocr-small-stage1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use microsoft/trocr-small-stage1 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="microsoft/trocr-small-stage1")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("microsoft/trocr-small-stage1") model = AutoModelForMultimodalLM.from_pretrained("microsoft/trocr-small-stage1", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download sentencepiece.bpe.model from microsoft/trocr-small-stage1: direct link, hf CLI and curl.
- Browser
- Download file 1.36 MB
-
https://huggingface.co/microsoft/trocr-small-stage1/resolve/main/sentencepiece.bpe.model
- Command line
-
hf download hf://microsoft/trocr-small-stage1/sentencepiece.bpe.model
-
curl -L -o sentencepiece.bpe.model https://huggingface.co/microsoft/trocr-small-stage1/resolve/main/sentencepiece.bpe.model
1.36 MB
- Xet hash:
- 44c0a3aaeef5a35edcaec1f4e03f742bafed8a9e8dbf9c6df0bcd8e63caa7e4c
- Size of remote file:
- 1.36 MB
- SHA256:
- 6f5e2fefcf793761a76a6bfb8ad35489f9c203b25557673284b6d032f41043f4
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.