Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

Qwen
/
Qwen3-VL-Embedding-2B

Sentence Similarity
sentence-transformers
Safetensors
Transformers
qwen3_vl
image-text-to-text
multimodal embedding
qwen
embedding
Model card Files Files and versions
xet
Community
23

Instructions to use Qwen/Qwen3-VL-Embedding-2B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • sentence-transformers

    How to use Qwen/Qwen3-VL-Embedding-2B with sentence-transformers:

    from sentence_transformers import SentenceTransformer
    
    model = SentenceTransformer("Qwen/Qwen3-VL-Embedding-2B")
    
    sentences = [
        "That is a happy person",
        "That is a happy dog",
        "That is a very happy person",
        "Today is a sunny day"
    ]
    embeddings = model.encode(sentences)
    
    similarities = model.similarity(embeddings, embeddings)
    print(similarities.shape)
    # [4, 4]
  • Transformers

    How to use Qwen/Qwen3-VL-Embedding-2B with Transformers:

    # Load model directly
    from transformers import AutoProcessor, AutoModelForImageTextToText
    
    processor = AutoProcessor.from_pretrained("Qwen/Qwen3-VL-Embedding-2B")
    model = AutoModelForImageTextToText.from_pretrained("Qwen/Qwen3-VL-Embedding-2B")
  • Notebooks
  • Google Colab
  • Kaggle
New discussion
Resources
  • PR & discussions documentation
  • Code of Conduct
  • Hub documentation

Add trust_remote_code support via AutoModel integration

#22 opened about 2 months ago by
whybe-choi

Built a server to make this OpenAI compatible

👍 1
#21 opened about 2 months ago by
sur4guy101

Usage for multiple images and videos

#20 opened 3 months ago by
wongyukim

making the script compatible with transformers 5.2+

❤️ 2
2
#19 opened 3 months ago by
mfarre

Instruction issue

👍 1
#18 opened 3 months ago by
hh1212

language support

#17 opened 4 months ago by
KevinCha

求助:vllm 在线部署qwen3-vl-Embedding模型,产出结果和离线transformer调用结果不一致是什么原因呢?

1
#16 opened 4 months ago by
AHuaa

Missing Pooling Config

#15 opened 4 months ago by
bweigel1

支持多图吗

1
#12 opened 5 months ago by
chaxjli

Add pipeline_tag, library_name and paper link

#11 opened 5 months ago by
nielsr

which vllm version is for Qwen/Qwen3-VL-Embedding-2B

1
#10 opened 5 months ago by
xinquan

chatllm.cpp supports this model

#9 opened 5 months ago by
J22

does vLLM support the Qwen3-VL-Embedding series to deploy locally?

2
#7 opened 5 months ago by
wushiqi22

Installation Video and Testing - Step by Step

👍 2
#6 opened 5 months ago by
fahdmirzac

Are there plans for an even smaller embedding model?

👍 8
#5 opened 5 months ago by
nautilu
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs