How to use michaelfeil/Qwen3-Embedding-4B-auto with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("michaelfeil/Qwen3-Embedding-4B-auto") sentences = [ "The weather is lovely today.", "It's so sunny outside!", "He drove to the stadium." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3]
How to use michaelfeil/Qwen3-Embedding-4B-auto with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="michaelfeil/Qwen3-Embedding-4B-auto")
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("michaelfeil/Qwen3-Embedding-4B-auto") model = AutoModel.from_pretrained("michaelfeil/Qwen3-Embedding-4B-auto", device_map="auto")
https://huggingface.co/michaelfeil/Qwen3-Embedding-4B-auto/resolve/main/generation_config.json
hf download hf://michaelfeil/Qwen3-Embedding-4B-auto/generation_config.json
curl -L -o generation_config.json https://huggingface.co/michaelfeil/Qwen3-Embedding-4B-auto/resolve/main/generation_config.json
