Instructions to use nvidia/C-RADIOv4-H with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nvidia/C-RADIOv4-H with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="nvidia/C-RADIOv4-H", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("nvidia/C-RADIOv4-H", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -2,6 +2,7 @@
|
|
| 2 |
license: other
|
| 3 |
license_name: nvidia-open-model-license
|
| 4 |
license_link: https://developer.download.nvidia.com/licenses/nvidia-open-model-license-agreement-june-2024.pdf
|
|
|
|
| 5 |
---
|
| 6 |
|
| 7 |
# Model Overview
|
|
@@ -12,8 +13,6 @@ This model performs visual feature extraction.
|
|
| 12 |
For instance, RADIO generates image embeddings that can be used by a downstream model to classify images.
|
| 13 |
|
| 14 |
C-RADIOv4 models are available in multiple sizes:
|
| 15 |
-
* Base (98M parameters).
|
| 16 |
-
* Large (320M parameters).
|
| 17 |
* Shape-Optimized (431M parameters).
|
| 18 |
* Huge (653M parameters).
|
| 19 |
|
|
@@ -136,8 +135,6 @@ This AI model can be embedded as an Application Programming Interface (API) call
|
|
| 136 |
|
| 137 |
## Model Version(s)
|
| 138 |
|
| 139 |
-
* C-RADIOv4-B (98M parameters).
|
| 140 |
-
* C-RADIOv4-L (320M parameters).
|
| 141 |
* C-RADIOv4-SO400M (400M parameters).
|
| 142 |
* C-RADIOv4-H (653M parameters).
|
| 143 |
|
|
|
|
| 2 |
license: other
|
| 3 |
license_name: nvidia-open-model-license
|
| 4 |
license_link: https://developer.download.nvidia.com/licenses/nvidia-open-model-license-agreement-june-2024.pdf
|
| 5 |
+
library_name: transformers
|
| 6 |
---
|
| 7 |
|
| 8 |
# Model Overview
|
|
|
|
| 13 |
For instance, RADIO generates image embeddings that can be used by a downstream model to classify images.
|
| 14 |
|
| 15 |
C-RADIOv4 models are available in multiple sizes:
|
|
|
|
|
|
|
| 16 |
* Shape-Optimized (431M parameters).
|
| 17 |
* Huge (653M parameters).
|
| 18 |
|
|
|
|
| 135 |
|
| 136 |
## Model Version(s)
|
| 137 |
|
|
|
|
|
|
|
| 138 |
* C-RADIOv4-SO400M (400M parameters).
|
| 139 |
* C-RADIOv4-H (653M parameters).
|
| 140 |
|