Instructions to use webis/splade with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Lightning IR
How to use webis/splade with Lightning IR:
#install from https://github.com/webis-de/lightning-ir from lightning_ir import BiEncoderModule model = BiEncoderModule("webis/splade") model.score("query", ["doc1", "doc2", "doc3"]) - Notebooks
- Google Colab
- Kaggle
| trainer: | |
| logger: false | |
| callbacks: | |
| - class_path: SearchCallback | |
| init_args: | |
| index_dir: ./index | |
| search_config: | |
| class_path: SparseSearchConfig | |
| init_args: | |
| k: 10 | |
| model: | |
| class_path: lightning_ir.BiEncoderModule | |
| init_args: | |
| model_name_or_path: webis/bert-bi-encoder | |
| evaluation_metrics: | |
| - nDCG@10 | |
| data: | |
| class_path: lightning_ir.LightningIRDataModule | |
| init_args: | |
| inference_datasets: | |
| - class_path: QueryDataset | |
| init_args: | |
| doc_dataset: msmarco-passage/trec-dl-2019/judged |