Instructions to use webis/bert-bi-encoder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Lightning IR
How to use webis/bert-bi-encoder with Lightning IR:
#install from https://github.com/webis-de/lightning-ir from lightning_ir import BiEncoderModule model = BiEncoderModule("webis/bert-bi-encoder") model.score("query", ["doc1", "doc2", "doc3"]) - Notebooks
- Google Colab
- Kaggle
Update config.json
Browse files- config.json +1 -1
config.json
CHANGED
|
@@ -21,7 +21,7 @@
|
|
| 21 |
"intermediate_size": 3072,
|
| 22 |
"layer_norm_eps": 1e-12,
|
| 23 |
"max_position_embeddings": 512,
|
| 24 |
-
"model_type": "
|
| 25 |
"normalize": false,
|
| 26 |
"num_attention_heads": 12,
|
| 27 |
"num_hidden_layers": 12,
|
|
|
|
| 21 |
"intermediate_size": 3072,
|
| 22 |
"layer_norm_eps": 1e-12,
|
| 23 |
"max_position_embeddings": 512,
|
| 24 |
+
"model_type": "lir-dpr",
|
| 25 |
"normalize": false,
|
| 26 |
"num_attention_heads": 12,
|
| 27 |
"num_hidden_layers": 12,
|