Qwen3-VL-Reranker-2B
RK1820
|
LlamaPi Ready
Model Overview
| Item | Details |
|---|---|
| Original model | Qwen3-VL-Reranker-2B (ModelScope | Hugging Face) |
| Original developer | Qwen Team |
| Model type | Multimodal reranking |
| Target platform | RK1820 |
| Converted by | Firefly AI Team |
| Deployment tool | LlamaPi |
Run with LlamaPi
llamapi pull qwen3-vl-reranker:2b
llamapi load qwen3-vl-reranker:2b
Use the loaded model through LlamaPi's rerank API. See the LlamaPi Wiki for setup and usage.
About the Original Model
Qwen3-VL-Reranker-2B is a 2B multimodal reranker from the Qwen team, built on Qwen3-VL for multimodal information retrieval and cross-modal understanding.
- Accepts text, images, screenshots, videos, and arbitrary multimodal combinations in a unified framework.
- Takes a (query, document) pair and outputs a precise relevance score to refine retrieval results.
- Supports 30+ languages with a 32K context length.
License & Attribution
The models provided in this repository are converted and adapted by the Firefly AI team from the original models. All intellectual property rights and copyright in the underlying original models remain with the original official team, and their distribution is governed by the corresponding official open-source license.