Update README.md

README.md

@@ -69,6 +69,58 @@ training_args = TrainingArguments(
 | 8100 | 1.499900      | 1.525138        |
 
 
+# 실행 코드
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
+import torch
+
+# Quantization config (must match QLoRA settings used during fine-tuning)
+bnb_config = BitsAndBytesConfig(
+    load_in_4bit=True,
+    bnb_4bit_quant_type="nf4",
+    bnb_4bit_use_double_quant=True,
+    bnb_4bit_compute_dtype=torch.float16,
+)
+
+# Load tokenizer and model (local or hub path)
+model_path = "your-username/your-model-name"  # or local path like "./saved_model(0412)"
+tokenizer = AutoTokenizer.from_pretrained(model_path)
+model = AutoModelForCausalLM.from_pretrained(
+    model_path,
+    quantization_config=bnb_config,
+    device_map="auto"
+)
+model.eval()
+
+# Define prompt using ChatML format (Qwen-style)
+def build_chatml_prompt(question: str) -> str:
+    system_msg = "<|im_start|>system\n당신은 유용한 한국어 도우미입니다.<|im_end|>\n"
+    user_msg = f"<|im_start|>user\n{question}<|im_end|>\n"
+    return system_msg + user_msg + "<|im_start|>assistant\n"
+
+# Run inference
+def generate_response(question: str, max_new_tokens: int = 128) -> str:
+    prompt = build_chatml_prompt(question)
+    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+
+    with torch.no_grad():
+        outputs = model.generate(
+            **inputs,
+            max_new_tokens=max_new_tokens,
+            do_sample=False,
+            top_p=0.9,
+            temperature=0.7,
+            eos_token_id=tokenizer.eos_token_id,
+        )
+
+    return tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+# Example
+question = "한국의 수도는 어디인가요?"
+response = generate_response(question)
+print("모델 응답:\n", response)
+```
 
 # 실행환경