Instructions to use facebook/dpr-question_encoder-single-nq-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use facebook/dpr-question_encoder-single-nq-base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="facebook/dpr-question_encoder-single-nq-base")# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("facebook/dpr-question_encoder-single-nq-base") model = AutoModel.from_pretrained("facebook/dpr-question_encoder-single-nq-base", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update config.json
Browse files- config.json +3 -3
config.json
CHANGED
|
@@ -1,10 +1,10 @@
|
|
| 1 |
{
|
| 2 |
"architectures": [
|
| 3 |
-
"
|
| 4 |
],
|
| 5 |
"model_type": "dpr",
|
| 6 |
-
"
|
| 7 |
-
"
|
| 8 |
"projection_dim": 0,
|
| 9 |
"sequence_length": 512
|
| 10 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"architectures": [
|
| 3 |
+
"DPRQuestionEncoder"
|
| 4 |
],
|
| 5 |
"model_type": "dpr",
|
| 6 |
+
"pad_token_id": 0,
|
| 7 |
+
"pretrained_model_config_name": "bert-base-uncased",
|
| 8 |
"projection_dim": 0,
|
| 9 |
"sequence_length": 512
|
| 10 |
}
|