| This is a cross-encoder model with dot-product based scoring mechanism trained on MS-MARCO dataset. | |
| The parameters of the cross-encoder are initialized using a 6-layer [minilm model](https://huggingface.co/nreimers/MiniLM-L6-H384-uncased) and is trained via distillation using scores from three different teacher models. | |
| This model is used in experiments of our [EMNLP 2023](https://aclanthology.org/2023.findings-emnlp.544/) and [ICLR 2024](https://openreview.net/forum?id=1CPta0bfN2) papers. | |
| See our EMNLP 2022 paper titled "Efficient Nearest Neighbor Search for Cross-Encoder Models using Matrix Factorization" for more details on the dot-product based scoring mechanism. | |
| --- | |
| license: apache-2.0 | |
| --- | |