Instructions to use facebook/pixio-vitl16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use facebook/pixio-vitl16 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-feature-extraction", model="facebook/pixio-vitl16")# Load model directly from transformers import AutoImageProcessor, AutoModel processor = AutoImageProcessor.from_pretrained("facebook/pixio-vitl16") model = AutoModel.from_pretrained("facebook/pixio-vitl16") - Notebooks
- Google Colab
- Kaggle
Enable hidden state outputs for Pixio demo script
#1
by syun88 - opened
@yli1
Fixes a crash in demo python Script
where outputs.hidden_states was None
Requests hidden states in the forward call so outputs.hidden_states[-1] is available
Keeps behavior unchanged otherwise (last hidden state still used)
thx you so much for the PR.
activebus changed pull request status to merged