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
| trainer: | |
| logger: false | |
| callbacks: | |
| - class_path: lightning_ir.IndexCallback | |
| init_args: | |
| index_dir: ./index | |
| index_config: | |
| class_path: lightning_ir.FaissFlatIndexConfig | |
| model: | |
| class_path: lightning_ir.BiEncoderModule | |
| init_args: | |
| model_name_or_path: webis/bert-bi-encoder | |
| data: | |
| class_path: lightning_ir.LightningIRDataModule | |
| init_args: | |
| num_workers: 1 | |
| inference_batch_size: 256 | |
| inference_datasets: | |
| - class_path: DocDataset | |
| init_args: | |
| doc_dataset: msmarco-passage |