Instructions to use NCAI/NCAI-BERT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use NCAI/NCAI-BERT with Transformers:
# Load model directly from transformers import LeanAlbertForPretraining model = LeanAlbertForPretraining.from_pretrained("NCAI/NCAI-BERT", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update config.json
Browse files- config.json +1 -0
config.json
CHANGED
|
@@ -16,6 +16,7 @@
|
|
| 16 |
"hidden_act": "gelu_new",
|
| 17 |
"hidden_act_gated": true,
|
| 18 |
"sandwich_norm": true,
|
|
|
|
| 19 |
"position_embedding_type": "rotary",
|
| 20 |
"hidden_dropout_prob": 0,
|
| 21 |
"classifier_dropout_prob": 0.1,
|
|
|
|
| 16 |
"hidden_act": "gelu_new",
|
| 17 |
"hidden_act_gated": true,
|
| 18 |
"sandwich_norm": true,
|
| 19 |
+
"inner_group_num": 1,
|
| 20 |
"position_embedding_type": "rotary",
|
| 21 |
"hidden_dropout_prob": 0,
|
| 22 |
"classifier_dropout_prob": 0.1,
|