Instructions to use apple/mobilevit-small with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use apple/mobilevit-small with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="apple/mobilevit-small") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("apple/mobilevit-small", dtype="auto") - Inference
- Notebooks
- Google Colab
- Kaggle
Add TF weights
#1
by sayakpaul HF Staff - opened
Model converted by the transformers' pt_to_tf CLI. All converted model outputs and hidden layers were validated against its Pytorch counterpart.
Maximum crossload output difference=1.287e-04; Maximum crossload hidden layer difference=4.578e-05;
Maximum conversion output difference=1.287e-04; Maximum conversion hidden layer difference=4.578e-05;
CAUTION: The maximum admissible error was manually increased to 0.0002!
@joaogante @lysandre relevant discussion as to why the threshold had to be adjusted: https://github.com/huggingface/transformers/pull/18555#issuecomment-1229703811
Matthijs changed pull request status to merged