Update README.md

README.md

@@ -3696,8 +3696,7 @@ The `GME` models support three types of input: **text**, **image**, and **image-
 
 ```python
 # You can find the script gme_inference.py in https://huggingface.co/Alibaba-NLP/gme-Qwen2-VL-2B-Instruct/blob/main/gme_inference.py
-from gme_inference import GmeQwen2VL
-
+from transformers import AutoModel
 texts = [
     "What kind of car is this?",
     "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023."
@@ -3707,7 +3706,7 @@ images = [
     'https://en.wikipedia.org/wiki/File:2024_Tesla_Cybertruck_Foundation_Series,_front_left_(Greenwich).jpg',
 ]
 
-gme = GmeQwen2VL("Alibaba-NLP/gme-Qwen2-VL-2B-Instruct")
+gme = AutoModel("Alibaba-NLP/gme-Qwen2-VL-2B-Instruct", trust_remote_code=True)
 
 # Single-modal embedding
 e_text = gme.get_text_embeddings(texts=texts)