# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("zenlm/zen-reranker-8B")
model = AutoModelForCausalLM.from_pretrained("zenlm/zen-reranker-8B", device_map="auto")Zen Reranker 8B
8B-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-8B (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-8B recipe (yes/no token scoring).
Hosted via the Hanzo gateway (api.hanzo.ai) as zen-reranker-8b. GGUF build for CPU inference: zenlm/zen-reranker-8B-GGUF.
License
apache-2.0. Upstream: Qwen/Qwen3-Reranker-8B by Alibaba Qwen. This repository redistributes the weights under the same license.
- Downloads last month
- 7
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="zenlm/zen-reranker-8B")