Update app.py

app.py

@@ -49,14 +49,14 @@ def respond(
         add_generation_prompt=True,
         enable_thinking=True,
     )
-    input_text += "<think>" # TODO: remove short term fix
+    # input_text += "<think>" # TODO: remove short term fix
     print(input_text)
     inputs = tokenizer(input_text, return_tensors="pt").to(model.device) # .to(device)
 
     # Streamer setup
     streamer = TextIteratorStreamer(
         tokenizer,
-        skip_special_tokens=True,
+        # skip_special_tokens=True,
         skip_prompt=True
     )