Text Classification
Transformers
decision-model
latent-reasoning
recurrent-depth
adaptive-compute
multilingual
Instructions to use d2v1shx/dazo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use d2v1shx/dazo with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="d2v1shx/dazo")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("d2v1shx/dazo", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Publish Dazo from GitHub 756d216
Browse files
configs/dazo-v0-small.json
CHANGED
|
@@ -17,5 +17,7 @@
|
|
| 17 |
"halt_threshold": 0.65,
|
| 18 |
"convergence_threshold": 0.02,
|
| 19 |
"correctness_threshold": 0.70,
|
| 20 |
-
"freeze_backbone": true
|
|
|
|
|
|
|
| 21 |
}
|
|
|
|
| 17 |
"halt_threshold": 0.65,
|
| 18 |
"convergence_threshold": 0.02,
|
| 19 |
"correctness_threshold": 0.70,
|
| 20 |
+
"freeze_backbone": true,
|
| 21 |
+
"base_compatibility": true,
|
| 22 |
+
"recurrent_logit_scale": 0.1
|
| 23 |
}
|