Update README.md

README.md

@@ -40,54 +40,7 @@ Bagel‑Zebra‑CoT is fine-tuned from [Bagel‑7B](https://huggingface.co/ByteD
 
 ## Usage
 
-Here's a quick example to use the model with the `transformers` library:
-
-```python
-from transformers import AutoProcessor, AutoModel
-from PIL import Image
-import torch
-
-# Load model and processor
-model_id = "multimodal-reasoning-lab/Bagel-Zebra-CoT"
-model = AutoModel.from_pretrained(model_id, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map="auto")
-processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)
-
-# Example image and question (replace with your path and query)
-image_path = "test_images/image.png" 
-image = Image.open(image_path).convert('RGB')
-question = "Subtract all cylinders. Add 1 red sphere. How many objects are left?"
-
-# Prepare inputs
-messages = [
-    {
-        "role": "user",
-        "content": [
-            {"type": "image", "image": image},
-            {"type": "text", "text": question},
-        ],
-    }
-]
-
-text = processor.apply_chat_template(
-    messages, tokenize=False, add_generation_prompt=True
-)
-inputs = processor(
-    text=[text],
-    images=[image],
-    padding=True,
-    return_tensors="pt",
-)
-inputs = {k: v.to(model.device) for k, v in inputs.items()}
-
-# Generate response
-generated_ids = model.generate(**inputs, max_new_tokens=512)
-
-# Decode and print output
-output_text = processor.batch_decode(generated_ids, skip_special_tokens=False, clean_up_tokenization_spaces=False)[0]
-print(output_text)
-```
-
-For more advanced usage, training details, and additional examples, please refer to the [official GitHub repository](https://github.com/multimodal-reasoning-lab/Bagel-Zebra-CoT).
+For more interleaved text and image inference and training, please refer to the [official GitHub repository](https://github.com/multimodal-reasoning-lab/Bagel-Zebra-CoT).
 
 ---