efficient-splade-VI-BT-large-query

Efficient SPLADE model for passage retrieval. This architecture uses two distinct models for query and document inference. This is the **query** one, please also download the **doc** one (https://huggingface.co/naver/efficient-splade-VI-BT-large-doc). For additional details, please visit: * paper: https://dl.acm.org/doi/10.1145/3477495.3531833 * code: https://github.com/naver/splade | | MRR@10 (MS MARCO dev) | R@1000 (MS MARCO dev) | Latency (PISA) ms | Latency (Inference) ms | --- | --- | --- | --- | --- | | `naver/efficient-splade-V-large` | 38.8 | 98.0 | 29.0 | 45.3 | `naver/efficient-splade-VI-BT-large` | 38.0 | 97.8 | 31.1 | 0.7 This is a Asymmetric SPLADE Sparse Encoder model. It maps sentences & paragraphs to a 30522-dimensional sparse vector space and can be used for semantic search and sparse retrieval. - **Model Type:** SPLADE Sparse Encoder - **Maximum Sequence Length:** 512 tokens (256 for evaluation reproduction) - **Output Dimensionality:** 30522 dimensions - **Similarity Function:** Dot Product

翻訳準備中のため原文を表示しています