Instructions to use Mooshie/eva02_large_patch14_448.dbv4-full with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- timm
How to use Mooshie/eva02_large_patch14_448.dbv4-full with timm:
import timm model = timm.create_model("hf-hub:Mooshie/eva02_large_patch14_448.dbv4-full", pretrained=True) - Transformers
How to use Mooshie/eva02_large_patch14_448.dbv4-full with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="Mooshie/eva02_large_patch14_448.dbv4-full") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Mooshie/eva02_large_patch14_448.dbv4-full", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download thresholds.csv from Mooshie/eva02_large_patch14_448.dbv4-full: direct link, hf CLI and curl.
- Browser
- Download file 279 Bytes
-
https://huggingface.co/Mooshie/eva02_large_patch14_448.dbv4-full/resolve/main/thresholds.csv
- Command line
-
hf download hf://Mooshie/eva02_large_patch14_448.dbv4-full/thresholds.csv
-
curl -L -o thresholds.csv https://huggingface.co/Mooshie/eva02_large_patch14_448.dbv4-full/resolve/main/thresholds.csv
279 Bytes
| category,name,alpha,threshold,f1,precision,recall | |
| 0,general,1.0,0.39,0.6809765913302411,0.6741370425645552,0.6879563457106442 | |
| 4,character,1.0,0.61,0.9428597466503706,0.9614295553684855,0.9249936889936049 | |
| 9,rating,1.0,0.38,0.8318551577464783,0.8010638797190106,0.8651081689341255 | |