fix

app.py

@@ -72,11 +72,12 @@ def respond(
     # model.generate(input_ids = inputs, streamer = text_streamer, max_new_tokens = max_tokens,
     #                 use_cache = True, temperature = temperature, min_p = top_p)
     response = tokenizer.batch_decode(outputs, skip_special_tokens=True)[0]
+    print(tokenizer.batch_decode(outputs, skip_special_tokens=True))
 
     if "assistant" in response:
         response = response.split("assistant")[-1].strip()
     
-    print(response)
+    yield response
 
 
 """