Update README.md

README.md

@@ -121,14 +121,51 @@ We welcome collaboration with:
 
 ```python
 from transformers import AutoTokenizer, AutoModelForCausalLM
-
-tokenizer = AutoTokenizer.from_pretrained("snuh/hari-q2.5")
-model = AutoModelForCausalLM.from_pretrained("snuh/hari-q2.5")
-
-prompt = "다음 환자의 주요 진단은 무엇인가요? 환자 정보: 60세 남성, 복통, 발열, 백혈구 증가..."
-inputs = tokenizer(prompt, return_tensors="pt")
-outputs = model.generate(**inputs, max_new_tokens=100)
-print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+import torch
+
+# Load tokenizer and model
+model_name = "snuh/hari-q2.5"
+tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True)
+model.eval()
+
+# Define multi-turn chat in ChatML format
+messages = [
+    {
+        "role": "system",
+        "content": "You are a helpful and knowledgeable Korean medical assistant. Answer the user's question accurately based on clinical reasoning."
+    },
+    {
+        "role": "user",
+        "content": (
+            "60세 남성이 복통과 발열을 호소하며 내원하였습니다. "
+            "혈액 검사 결과 백혈구 수치가 상승했고, 우측 하복부 압통이 확인되었습니다. "
+            "가장 가능성이 높은 진단명은 무엇인가요?"
+        )
+    }
+]
+
+# Apply ChatML template
+prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+
+# Tokenize input
+inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+
+# Generate model output
+with torch.no_grad():
+    outputs = model.generate(
+        **inputs,
+        max_new_tokens=128,
+        do_sample=True,
+        temperature=0.7,
+        top_p=0.9,
+        eos_token_id=tokenizer.eos_token_id,
+    )
+
+# Decode and display response
+response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+print("🧠 Model Response:\n")
+print(response)
 ````
 
 ---