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
Add RADIOv2.1
Browse filesImproved SAM quality, runs in BFloat16 mode (e.g. the weights can be cast to this dtype).
- radio_v2.1_bf16.pth.tar +3 -0
radio_v2.1_bf16.pth.tar
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f0cd313e7cb52cda4e5f640510fc5ea059f2fe252fd1fc68a252545b58493a3d
|
| 3 |
+
size 2072846302
|