Instructions to use nvidia/RADIO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nvidia/RADIO with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-feature-extraction", model="nvidia/RADIO", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("nvidia/RADIO", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
Create model_results.csv
Browse files- model_results.csv +2 -0
model_results.csv
ADDED
|
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Name,Architecture,Teachers,Throughput,Zero Shot Top-1, kNN Top-1,ADE20k,VOC,GQA,SQA,TextVQA,VQAv2
|
| 2 |
+
radio_v1,ViT-H/14-CPE,DFN CLIP;OpenAI CLIP;DINOv2,556,82.733,85.29,50.32,,,,,
|