Update README.md

README.md

@@ -25,6 +25,7 @@ and directly outputs a **structured JSON** containing a professional risk evalua
 
 ### Output Format
 ```json
+
 {
   "intent": ["passive_suicide_ideation", "mild_distress", ...],
   "risk": "low" | "medium" | "high" | "ambiguous",
@@ -33,6 +34,8 @@ and directly outputs a **structured JSON** containing a professional risk evalua
   "recommended_action": ["empathize", "deep_assessment", ...]
 }
 
+```
+
 Key Capabilities
 
 Accurately detects subtle and indirect expressions of psychological distress common in Chinese (e.g., “活着没意思”、“快受不了了”、“不如解脱”)
@@ -57,8 +60,7 @@ Adapter type: LoRA (r=16, alpha=32, targeting q/k/v/o_proj)
 Dataset: Custom high-quality Chinese mental health risk assessment data (single-turn + multi-turn)
 Training objective: Supervised fine-tuning with strict JSON output formatting and EOS enforcement for clean generation
 
-
-'''python
+```python
 from peft import PeftModel, PeftConfig
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
@@ -79,4 +81,6 @@ prompt = """### 任务指令:
 
 inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
 outputs = model.generate(**inputs, max_new_tokens=256, do_sample=False)
-print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+
+```