Text Ranking
Transformers
Safetensors
sentence-transformers
qwen3_vl
image-text-to-text
multimodal rerank
text rerank
Instructions to use Qwen/Qwen3-VL-Reranker-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Qwen/Qwen3-VL-Reranker-8B with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("Qwen/Qwen3-VL-Reranker-8B") model = AutoModelForMultimodalLM.from_pretrained("Qwen/Qwen3-VL-Reranker-8B", device_map="auto") - sentence-transformers
How to use Qwen/Qwen3-VL-Reranker-8B with sentence-transformers:
from sentence_transformers import CrossEncoder model = CrossEncoder("Qwen/Qwen3-VL-Reranker-8B") 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
Commit History
-
Integrate with Sentence Transformers v5.4 (#9)
- Integrate Sentence Transformers v5.4.0 (51b80faf049ab8da33327e5da1f145de8b5dd0da) - Add unpad_inputs=False (179f0f6c4254916da6d0d3da76b1f7cb977c4704) - Rename CausalScoreHead to LogitScore (192e4f9dc1f3edd43fd21669ca242f31e0bd7005) - Move 'message_format' into 'modality_config' under 'message' -> 'format' (96fc4eefb7c07faf32e3a681302fbb35d10bd9c5)b212dc8
-
add model pipeline info and technical report info (#7)
Verified signature- add model pipeline info and technical report info (e20db4a7969d02b8a7642e80e9d56b5f8d003ee7) Co-authored-by: Dingkun Long <thenlper@users.noreply.huggingface.co>a718125
-
Add basic vllm usage (#5)
Verified signature- Add basic vllm usage (62176b0fdf44fcf081f8d43aa0eb7933d9598de9) Co-authored-by: yu <yuhao318@users.noreply.huggingface.co>8e52ab8 -
fix parameter size in readme (#4)
Verified signature- fix parameter size in readme (cefe3470730ac93ceb5121feea0498762088b955) Co-authored-by: Bálint Molnár-Kaló <molbal@users.noreply.huggingface.co>f0c49f7
-
Update README.md (#3)
Verified signature- Update README.md (de4ea3c18d9edc8c4bf0e4270587ea58c1b35075) - Update scripts/qwen3_vl_reranker.py (79d4fd0ffade942e7e647acb2cf6bd70610f8c10) Co-authored-by: yanzhao <zyznull@users.noreply.huggingface.co>fb0130d -
Update README.md (#2)
Verified signature- Update README.md (9bcf27acac63322d29074f44dc5f26cbcc132194) Co-authored-by: Dingkun Long <thenlper@users.noreply.huggingface.co>b649b95 -
Update README.md
Verified signature8255503
-
Update README.md
Verified signaturec56aa97 -
Upload folder using huggingface_hub
Verified signature9c50759 -
initial commit
Verified signature037194b