Instructions to use castorini/bpr-nq-ctx-encoder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use castorini/bpr-nq-ctx-encoder with Transformers:
# Load model directly from transformers import AutoTokenizer, DPRContextEncoder tokenizer = AutoTokenizer.from_pretrained("castorini/bpr-nq-ctx-encoder") model = DPRContextEncoder.from_pretrained("castorini/bpr-nq-ctx-encoder") - Notebooks
- Google Colab
- Kaggle
Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
This model is converted from the original BPR [repo](https://github.com/studio-ousia/bpr) and fitted into Pyserini:
|
| 2 |
+
|
| 3 |
+
> Ikuya Yamada, Akari Asai, and Hannaneh Hajishirzi. 2021. Efficient passage retrieval with hashing for open-domain question answering. arXiv:2106.00882.
|