Update app.py

app.py

@@ -99,56 +99,56 @@ def respond(age, gender, height, weight,
         f"- Plasma  (PV): {pv} mL"
     )
 
-    # --- Model Inference + Streaming ---
-try:
-    messages = [
-        {"role": "system", "content": system_message},
-        {"role": "user", "content": user_message}
-    ]
-
-    # Tokenize messages
-    encodings = tokenizer.apply_chat_template(
-        messages,
-        return_tensors="pt",
-        add_special_tokens=True,
-        padding=True,
-        truncation=True
-    )
-
-    input_ids = encodings["input_ids"].to(model.device)
-    attention_mask = encodings["attention_mask"].to(model.device)  # ✅ Correct attention mask
-
-    # Streamer for capturing tokens
-    streamer = TextIteratorStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
-
-    generation_kwargs = dict(
-        input_ids=input_ids,
-        attention_mask=attention_mask,
-        max_new_tokens=2000,
-        temperature=0.3,
-        top_p=0.9,
-        do_sample=True,
-        streamer=streamer,
-        pad_token_id=tokenizer.pad_token_id
-    )
-
-    # Run model in separate thread
-    thread = threading.Thread(target=model.generate, kwargs=generation_kwargs)
-    thread.start()
-
-    # Collect tokens into full response
-    reply = ""
-    for token in streamer:
-        reply += token
-
-    # Convert Markdown → HTML
-    html_output = markdown.markdown(
-        reply,
-        extensions=["tables", "fenced_code", "nl2br"]
-    )
-
-except Exception as e:
-    html_output = f"<p style='color:red;'>⚠️ Error: {str(e)}</p>"
+        # --- Model Inference + Streaming ---
+    try:
+        messages = [
+            {"role": "system", "content": system_message},
+            {"role": "user", "content": user_message}
+        ]
+    
+        # Tokenize messages
+        encodings = tokenizer.apply_chat_template(
+            messages,
+            return_tensors="pt",
+            add_special_tokens=True,
+            padding=True,
+            truncation=True
+        )
+    
+        input_ids = encodings["input_ids"].to(model.device)
+        attention_mask = encodings["attention_mask"].to(model.device)  # ✅ Correct attention mask
+    
+        # Streamer for capturing tokens
+        streamer = TextIteratorStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
+    
+        generation_kwargs = dict(
+            input_ids=input_ids,
+            attention_mask=attention_mask,
+            max_new_tokens=2000,
+            temperature=0.3,
+            top_p=0.9,
+            do_sample=True,
+            streamer=streamer,
+            pad_token_id=tokenizer.pad_token_id
+        )
+    
+        # Run model in separate thread
+        thread = threading.Thread(target=model.generate, kwargs=generation_kwargs)
+        thread.start()
+    
+        # Collect tokens into full response
+        reply = ""
+        for token in streamer:
+            reply += token
+    
+        # Convert Markdown → HTML
+        html_output = markdown.markdown(
+            reply,
+            extensions=["tables", "fenced_code", "nl2br"]
+        )
+    
+    except Exception as e:
+        html_output = f"<p style='color:red;'>⚠️ Error: {str(e)}</p>"