Instructions to use dicta-il/dictabert-tiny-parse with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use dicta-il/dictabert-tiny-parse with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="dicta-il/dictabert-tiny-parse", trust_remote_code=True)# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("dicta-il/dictabert-tiny-parse", trust_remote_code=True) model = AutoModel.from_pretrained("dicta-il/dictabert-tiny-parse", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update config.json
Browse files- config.json +3 -0
config.json
CHANGED
|
@@ -2,6 +2,9 @@
|
|
| 2 |
"architectures": [
|
| 3 |
"BertForJointParsing"
|
| 4 |
],
|
|
|
|
|
|
|
|
|
|
| 5 |
"attention_probs_dropout_prob": 0.1,
|
| 6 |
"classifier_dropout": null,
|
| 7 |
"do_lex": true,
|
|
|
|
| 2 |
"architectures": [
|
| 3 |
"BertForJointParsing"
|
| 4 |
],
|
| 5 |
+
"auto_map": {
|
| 6 |
+
"AutoModel": "BertForJointParsing.BertForJointParsing"
|
| 7 |
+
},
|
| 8 |
"attention_probs_dropout_prob": 0.1,
|
| 9 |
"classifier_dropout": null,
|
| 10 |
"do_lex": true,
|