Jina Reranker v2 Base Multilingual

Run Jina Reranker v2 optimized for Qualcomm NPUs with nexaSDK.

Quickstart

Install NexaSDK and create a free account at sdk.nexa.ai

Activate your device with your access token:

nexa config set license '<access_token>'

Run the model on Qualcomm NPU in one line:
```
nexa infer NexaAI/jina-v2-rerank-npu
```

Description

Jina Reranker v2 Base Multilingual is a multilingual cross-encoder model for document reranking. Given a query–document pair, it outputs a relevance score to improve ranking in retrieval systems.

Features

Cross-encoder architecture for fine-grained relevance scoring
Supports multilingual inputs
Handles inputs up to 1024 tokens using sliding window chunking
Employs flash attention optimizations

Use Cases

Reranking candidate passages in multilingual search
Enhancing retrieval in QA / RAG pipelines
Improving semantic relevance in recommendation systems

Inputs & Outputs

Input: Query & document (text pair)
Output: Scalar relevance score (for ranking)

License

This model is licensed under CC BY-NC 4.0, intended for research and evaluation use. Commercial use requires separate arrangement.

NexaAI
/

jina-v2-rerank-npu