How to use Alibaba-NLP/gme-Qwen2-VL-2B-Instruct with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("Alibaba-NLP/gme-Qwen2-VL-2B-Instruct", trust_remote_code=True) 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 Alibaba-NLP/gme-Qwen2-VL-2B-Instruct with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForImageTextToText processor = AutoProcessor.from_pretrained("Alibaba-NLP/gme-Qwen2-VL-2B-Instruct", trust_remote_code=True) model = AutoModelForImageTextToText.from_pretrained("Alibaba-NLP/gme-Qwen2-VL-2B-Instruct", trust_remote_code=True)
Integrate gme model with Transformers AutoModel.Now it's available with
gme
import torch model = AutoModel.from_pretrained("./gme-Qwen2-VL-2B-Instruct", trust_remote_code=True)
@thenlper @izhx can you review?
· Sign up or log in to comment
