Duplicated from Qwen/Qwen3-Reranker-4B

zenlm
/

zen-reranker

Text Classification

text-generation

text-embeddings-inference

Model card Files Files and versions

Zen Reranker

4B-parameter cross-encoder reranker for retrieval pipelines and search relevance — re-scores candidate passages for RAG and search quality. Part of the Zen reranker line.

Repackaged from Qwen/Qwen3-Reranker-4B (apache-2.0, Alibaba Qwen). Native HuggingFace safetensors, re-hosted under the Zen reranker line. Not trained from scratch — a permissively-licensed redistribution for the OSS-clean Zen model line.

Usage

Score query/passage pairs following the upstream Qwen/Qwen3-Reranker-4B recipe (yes/no token scoring).

Hosted via the Hanzo gateway (api.hanzo.ai) as zen-reranker. GGUF build for CPU inference: zenlm/zen-reranker-4B-GGUF.

License

apache-2.0. Upstream: Qwen/Qwen3-Reranker-4B by Alibaba Qwen. This repository redistributes the weights under the same license.

Downloads last month: 48

Safetensors

Model size

4B params

Tensor type

BF16

·

Model tree for zenlm/zen-reranker

Base model

Qwen/Qwen3-4B-Base

Finetuned

Qwen/Qwen3-Reranker-4B

Finetuned

(10)

this model

Quantizations

Collection including zenlm/zen-reranker

Zen Embeddings

Embedding model family for RAG and semantic search. • 7 items • Updated May 30