Text Classification
Transformers
Safetensors
xlm-roberta
reranker
retrieval
multilingual
zen
zen3
hanzo
text-embeddings-inference
Instructions to use zhengyuanqi/zen3-reranker with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use zhengyuanqi/zen3-reranker with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="zhengyuanqi/zen3-reranker")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("zhengyuanqi/zen3-reranker") model = AutoModelForSequenceClassification.from_pretrained("zhengyuanqi/zen3-reranker", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Zen3 Reranker
Zen LM by Hanzo AI — Multilingual cross-encoder reranker supporting 100+ languages. Optimized for search result refinement and RAG pipelines. 568M parameters.
Specs
| Property | Value |
|---|---|
| Parameters | 568M |
| Context Length | 8192 tokens |
| Languages | 100+ |
| Architecture | Zen MoDE (Mixture of Distilled Experts) |
| Generation | Zen3 |
Usage
from transformers import AutoModelForSequenceClassification, AutoTokenizer
model = AutoModelForSequenceClassification.from_pretrained("zenlm/zen3-reranker")
tokenizer = AutoTokenizer.from_pretrained("zenlm/zen3-reranker")
API Access
Available via the Hanzo AI API at console.hanzo.ai — $5 free credit on signup.
License
Apache 2.0
Zen LM is developed by Hanzo AI — Frontier AI infrastructure.
- Downloads last month
- 1