Duplicated from Qwen/Qwen3-VL-Embedding-2B
How to use Anker12138/Qwen3-VL-Embedding-2B with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("Anker12138/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]
How to use Anker12138/Qwen3-VL-Embedding-2B with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("Anker12138/Qwen3-VL-Embedding-2B") model = AutoModelForMultimodalLM.from_pretrained("Anker12138/Qwen3-VL-Embedding-2B", device_map="auto")
