--- license: cc-by-sa-3.0 datasets: - natural_questions language: - en tags: - colbert --- # ColBERT NQ Checkpoint This trained model is based on the [ColBERT](https://github.com/stanford-futuredata/ColBERT) model, trained on the [Natural Questions](https://huggingface.co/datasets/natural_questions) dataset. # Model Details Model is based on ColBERT, which in turn is based around a BERT encoder. The model is trained for text retrieval using a contrastive loss; given a query there's a relevant and non relevant passages. The corpus is based on [Wikipeida](https://huggingface.co/datasets/wiki_dpr). # Uses Model can be used by the [ColBERT](https://github.com/stanford-futuredata/ColBERT) codebase to initiate a retriever; one needs to build a vector index and then queries can be ran. # Evaluation Evaluation results on NQ dev:
NQ | Recall | MRR |
---|---|---|
10 | 71.1 | 52.0 |
20 | 76.3 | 52.3 |
50 | 80.4 | 52.5 |
100 | 82.7 | 52.5 |