Update README.md

README.md

@@ -1,8 +1,6 @@
-## About `GME-VARCO-VISION-Embedding`
+## About GME-VARCO-VISION-Embedding
 `GME-VARCO-VISION-Embedding` is a multimodal embedding model that computes semantic similarity between text, images, and videos in a high-dimensional embedding space. In particular, the model focuses on video retrieval, which demands greater complexity and contextual understanding compared to image retrieval. It achieves high retrieval accuracy and strong generalization performance across various scenarios, such as scene-based search, description-based search, and question-answering-based search.
 
-<br>
-
 ## Demo Video
 Check out our demo videos showcasing our multimodal embedding model in action:
 - [English Demo Video](https://www.youtube.com/watch?v=kCvz82Y1BQg)
@@ -10,8 +8,6 @@ Check out our demo videos showcasing our multimodal embedding model in action:
 
 The demo demonstrates how our embedding model works together with an AI agent to search for relevant videos based on user queries and generate responses using the retrieved video content.
 
-<br>
-
 ### Model Architecture and Training Method
 `GME-VARCO-VISION-Embedding` is based on [`Qwen/Qwen2-VL-7B-Instruct`](https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct), and uses the parameters of [`Alibaba-NLP/gme-Qwen2-VL-7B-Instruct`](https://huggingface.co/Alibaba-NLP/gme-Qwen2-VL-7B-Instruct) to improve the model's general retrieval ability.
 
@@ -22,11 +18,11 @@ as hard-negatives for the gold answers. . Each query is trained with in-batch ne
 #### 2. Adding Retrieval Vector
 To compensate for the insufficiency of training instances and enhance the generalization ability of the fine-tuned model, we compute a retrieval vector 𝜏 by subtracting the weights of the original [`Qwen/Qwen2-VL-7B-Instruct`](https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct) model from those of [`Alibaba-NLP/gme-Qwen2-VL-7B-Instruct`](https://huggingface.co/Alibaba-NLP/gme-Qwen2-VL-7B-Instruct), a Qwen2-VL based image-text retrieval model. This approach is inspired by Chat Vector, which is a method to equip pre-trained language models with chat capabilities in new languages by adding a vector obtained from the weight difference between a base model and its chat-optimized counterpart.
 
-<br>
 
 ### Performance
 Our model achieves **state-of-the-art (SOTA) zero-shot performance** on the MultiVENT2.0 dataset as of July 2025. See the [official leaderboard](https://eval.ai/web/challenges/challenge-page/2507/leaderboard/6262) for detailed results.
 
+
 <br>
 
 ## Code Examples
@@ -49,14 +45,7 @@ model = Qwen2VLForConditionalGeneration.from_pretrained(
     device_map="auto",
 )
 
-tokenizer = AutoTokenizer.from_pretrained(
-        model_name,
-        padding_side="left",
-    )
-
-
-processor = AutoProcessor.from_pretrained("Qwen/Qwen2-VL-7B-Instruct")
-processor.tokenizer = tokenizer
+processor = AutoProcessor.from_pretrained(model_name)
 device = model.device
 
 
@@ -77,7 +66,7 @@ qry_input = processor(
             text=[qry_txt],
             padding=True,
             return_tensors="pt",
-        ).to("cuda")  
+        ).to(device)  
 
 
 img_msg = [
@@ -134,7 +123,7 @@ image_inputs = processor(
         # videos=,
         padding=True,
         return_tensors="pt",
-    ).to("cuda")
+    ).to(device)
 
 with torch.inference_mode():
     qry_emb = model(
@@ -149,7 +138,7 @@ qry_emb = F.normalize(qry_emb, dim=-1)
 img_emb = F.normalize(img_emb, dim=-1)
 
 score = qry_emb @ img_emb.t()
-# tensor([[0.2432, 0.0962, 0.0747, 0.0898]], device='cuda:0', dtype=torch.bfloat16)
+# tensor([[0.3066, 0.1108, 0.1226, 0.1245]], device='cuda:0', dtype=torch.bfloat16)
 # corresponding to the score of photos (cat, dog, baseball, crowd) 
 ```
 <br>
@@ -179,7 +168,7 @@ video_input = processor(
         videos=video_input,
         padding=True,
         return_tensors="pt",
-    ).to("cuda")
+    ).to(device)
 
 with torch.inference_mode():
     video_emb = model(