Update app.py

app.py

@@ -77,7 +77,7 @@ def generate(
         input_ids = input_ids[:, -MAX_INPUT_TOKEN_LENGTH:]
         gr.Warning(f"Trimmed input from conversation as it was longer than {MAX_INPUT_TOKEN_LENGTH} tokens.")
     
-    streamer = TextIteratorStreamer(tokenizer, timeout=10.0, skip_prompt=True, skip_special_tokens=True)
+    streamer = TextIteratorStreamer(tokenizer, timeout=10.0, skip_prompt=False, skip_special_tokens=True)
     generate_kwargs = dict(
         {"input_ids": input_ids},
         streamer=streamer,
@@ -91,6 +91,7 @@ def generate(
     )
     t = Thread(target=model.generate, kwargs=generate_kwargs)
     t.start()
+    t.join()
 
     outputs = []
     for text in streamer: