Sentence Similarity
sentence-transformers
Safetensors
Transformers
qwen3_vl
image-text-to-text
multimodal embedding
qwen
embedding
Instructions to use Qwen/Qwen3-VL-Embedding-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use Qwen/Qwen3-VL-Embedding-8B with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("Qwen/Qwen3-VL-Embedding-8B") 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-8B with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("Qwen/Qwen3-VL-Embedding-8B") model = AutoModelForMultimodalLM.from_pretrained("Qwen/Qwen3-VL-Embedding-8B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Add pipeline tag, library name, and paper link
#6
by nielsr HF Staff - opened
Hi! I'm Niels from the Hugging Face community science team. I'm opening this PR to improve the model card for Qwen3-VL-Embedding-8B:
- Added
pipeline_tag: feature-extractionto ensure the model is categorized correctly as an embedding model. - Added
library_name: transformersas there is evidence of compatibility in the model configuration and requirements. - Linked the model card to the research paper: Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking.
- Included relevant tags for better discoverability.
These changes help users find and use the model more effectively!