Instructions to use webis/colbert with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Lightning IR
How to use webis/colbert with Lightning IR:
#install from https://github.com/webis-de/lightning-ir from lightning_ir import BiEncoderModule model = BiEncoderModule("webis/colbert") model.score("query", ["doc1", "doc2", "doc3"]) - Notebooks
- Google Colab
- Kaggle
Update config.json
Browse files- config.json +2 -0
config.json
CHANGED
|
@@ -11,6 +11,7 @@
|
|
| 11 |
"classifier_dropout": null,
|
| 12 |
"doc_expansion": false,
|
| 13 |
"doc_length": 256,
|
|
|
|
| 14 |
"doc_pooling_strategy": null,
|
| 15 |
"embedding_dim": 128,
|
| 16 |
"gradient_checkpointing": false,
|
|
@@ -31,6 +32,7 @@
|
|
| 31 |
"query_aggregation_function": "mean",
|
| 32 |
"query_expansion": true,
|
| 33 |
"query_length": 32,
|
|
|
|
| 34 |
"query_pooling_strategy": null,
|
| 35 |
"save_step": 44008,
|
| 36 |
"similarity_function": "dot",
|
|
|
|
| 11 |
"classifier_dropout": null,
|
| 12 |
"doc_expansion": false,
|
| 13 |
"doc_length": 256,
|
| 14 |
+
"query_mask_scoring_tokens": "punctuation",
|
| 15 |
"doc_pooling_strategy": null,
|
| 16 |
"embedding_dim": 128,
|
| 17 |
"gradient_checkpointing": false,
|
|
|
|
| 32 |
"query_aggregation_function": "mean",
|
| 33 |
"query_expansion": true,
|
| 34 |
"query_length": 32,
|
| 35 |
+
"query_mask_scoring_tokens": null,
|
| 36 |
"query_pooling_strategy": null,
|
| 37 |
"save_step": 44008,
|
| 38 |
"similarity_function": "dot",
|