Instructions to use nvidia/E-RADIO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nvidia/E-RADIO with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="nvidia/E-RADIO", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("nvidia/E-RADIO", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
Upload model
Browse files- eradio_model.py +2 -0
eradio_model.py
CHANGED
|
@@ -24,6 +24,8 @@ import numpy as np
|
|
| 24 |
import torch.nn.functional as F
|
| 25 |
import warnings
|
| 26 |
|
|
|
|
|
|
|
| 27 |
|
| 28 |
SIMPLER_UP_TOWER = False
|
| 29 |
|
|
|
|
| 24 |
import torch.nn.functional as F
|
| 25 |
import warnings
|
| 26 |
|
| 27 |
+
# Register extra models
|
| 28 |
+
from . import extra_timm_models
|
| 29 |
|
| 30 |
SIMPLER_UP_TOWER = False
|
| 31 |
|