Update README.md

README.md

@@ -21,4 +21,20 @@ Med-R1 is a reinforcement learning (RL)-enhanced vision-language model (VLM) des
 - **Cross-Task Learning**: We provide checkpoints trained separately on the following tasks:
   - **Anatomy Identification**, **Disease Diagnosis**, **Lesion Grading**, **Modality Recognition**, and **Biological Attribute Analysis**.
 
+## Use of Models
+```
+from transformers import Qwen2VLForConditionalGeneration, AutoProcessor
+
+MODEL_PATH = "yuxianglai117/Med-R1"
+
+model = Qwen2VLForConditionalGeneration.from_pretrained(
+    MODEL_PATH,
+    torch_dtype=torch.bfloat16,
+    attn_implementation="flash_attention_2",
+    device_map="auto",
+)
+
+processor = AutoProcessor.from_pretrained(MODEL_PATH)
+```
+
 ## Citation