Instructions to use Qwen/Qwen3-Reranker-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Qwen/Qwen3-Reranker-4B with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen3-Reranker-4B") model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-Reranker-4B") - sentence-transformers
How to use Qwen/Qwen3-Reranker-4B with sentence-transformers:
from sentence_transformers import CrossEncoder model = CrossEncoder("Qwen/Qwen3-Reranker-4B") query = "Which planet is known as the Red Planet?" passages = [ "Venus is often called Earth's twin because of its similar size and proximity.", "Mars, known for its reddish appearance, is often referred to as the Red Planet.", "Jupiter, the largest planet in our solar system, has a prominent red spot.", "Saturn, famous for its rings, is sometimes mistaken for the Red Planet." ] scores = model.predict([(query, passage) for passage in passages]) print(scores) - Notebooks
- Google Colab
- Kaggle
Amazing work! Any plans to release the fine-tuning toolkit for Qwen3-Reranker?
#4
by wynne-mw - opened
Hi team,
Really appreciate the excellent work on Qwen3-Embedding and Qwen3-Reranker series β the performance looks great!
Just wondering: will the fine-tuning code or toolkit be open-sourced? It would be very helpful for those of us looking to apply or adapt the reranker to custom domains.
Thanks again!