Instructions to use nyu-visionx/webssl300m_decoder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nyu-visionx/webssl300m_decoder with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-to-image", model="nyu-visionx/webssl300m_decoder")# Load model directly from transformers import AutoImageProcessor, AutoModelForPreTraining processor = AutoImageProcessor.from_pretrained("nyu-visionx/webssl300m_decoder") model = AutoModelForPreTraining.from_pretrained("nyu-visionx/webssl300m_decoder") - Notebooks
- Google Colab
- Kaggle
Fix config.json: Change hidden_size from 1152 to 1024 to match WebSSL DINO encoder output dimension
Browse files- config.json +1 -1
config.json
CHANGED
|
@@ -10,7 +10,7 @@
|
|
| 10 |
"decoder_num_hidden_layers": 28,
|
| 11 |
"hidden_act": "gelu",
|
| 12 |
"hidden_dropout_prob": 0.0,
|
| 13 |
-
"hidden_size":
|
| 14 |
"image_size": 224,
|
| 15 |
"initializer_range": 0.02,
|
| 16 |
"intermediate_size": 3072,
|
|
|
|
| 10 |
"decoder_num_hidden_layers": 28,
|
| 11 |
"hidden_act": "gelu",
|
| 12 |
"hidden_dropout_prob": 0.0,
|
| 13 |
+
"hidden_size": 1024,
|
| 14 |
"image_size": 224,
|
| 15 |
"initializer_range": 0.02,
|
| 16 |
"intermediate_size": 3072,
|