Image-to-Text
Transformers
PyTorch
Safetensors
vision-encoder-decoder
image-text-to-text
vision
nougat
Instructions to use facebook/nougat-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use facebook/nougat-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="facebook/nougat-base")# Load model directly from transformers import AutoTokenizer, AutoModelForImageTextToText tokenizer = AutoTokenizer.from_pretrained("facebook/nougat-base") model = AutoModelForImageTextToText.from_pretrained("facebook/nougat-base") - Notebooks
- Google Colab
- Kaggle
Are there any plans to update the license?
#11
by tatyanavidrevich - opened
Hi,
Are there any plans to update the license to be similar to that of llama2? This is a great model, I can see it being used beyond scientific publications.
It would be really useful for legacy engineering documentation. I experimented with its application, playing with the resolution of the old scanned documents before running them through the model and got fantastic results. Unfortunately we cannot use it due to the license. And as a small company we do not have the resources to train a model from scratch.