Instructions to use savasy/bert-base-turkish-squad with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use savasy/bert-base-turkish-squad with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "question-answering" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # pip install "transformers<5.0.0" from transformers import pipeline pipe = pipeline("question-answering", model="savasy/bert-base-turkish-squad")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("savasy/bert-base-turkish-squad") model = AutoModelForQuestionAnswering.from_pretrained("savasy/bert-base-turkish-squad", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update config.json
Browse files- config.json +2 -0
config.json
CHANGED
|
@@ -1,4 +1,5 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"architectures": [
|
| 3 |
"BertForQuestionAnswering"
|
| 4 |
],
|
|
@@ -13,6 +14,7 @@
|
|
| 13 |
"model_type": "bert",
|
| 14 |
"num_attention_heads": 12,
|
| 15 |
"num_hidden_layers": 12,
|
|
|
|
| 16 |
"pad_token_id": 0,
|
| 17 |
"type_vocab_size": 2,
|
| 18 |
"vocab_size": 32000
|
|
|
|
| 1 |
{
|
| 2 |
+
"_num_labels": 2,
|
| 3 |
"architectures": [
|
| 4 |
"BertForQuestionAnswering"
|
| 5 |
],
|
|
|
|
| 14 |
"model_type": "bert",
|
| 15 |
"num_attention_heads": 12,
|
| 16 |
"num_hidden_layers": 12,
|
| 17 |
+
"output_past": true,
|
| 18 |
"pad_token_id": 0,
|
| 19 |
"type_vocab_size": 2,
|
| 20 |
"vocab_size": 32000
|