Text Classification
Transformers
Safetensors
English
Chinese
qwen3
text-generation
zen
zen-reranker
zenlm
hanzo
reranker
retrieval
text-embeddings-inference
Instructions to use zenlm/zen-reranker with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use zenlm/zen-reranker with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="zenlm/zen-reranker")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("zenlm/zen-reranker") model = AutoModelForCausalLM.from_pretrained("zenlm/zen-reranker", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Restore upstream attribution in NOTICE (Qwen3-Reranker-4B)
#1
by zeekay - opened
The shipped NOTICE reads "Copyright 2025-2026 Zen Authors" and names no upstream, but these weights are a derivative of Qwen/Qwen3-Reranker-4B (Apache-2.0).
Apache-2.0 section 4(c) requires retaining upstream attribution notices in distributed derivative works; section 4(d) requires carrying upstream's NOTICE text where upstream ships one. Replacing upstream's copyright with Zen's drops both.
Evidence of derivation: model card declares base_model: Qwen/Qwen3-Reranker-4B
This PR names the upstream and its true license, and keeps Zen's copyright scoped to Zen's own modifications. One LICENSE + one NOTICE; no license change.