skip prompt

app.py

@@ -54,7 +54,7 @@ def generate(
         input_ids = input_ids[-MAX_INPUT_TOKEN_LENGTH:]
         gr.Warning("Trimmed input from conversation as it was longer than {MAX_INPUT_TOKEN_LENGTH} tokens.")
 
-    streamer = TextIteratorStreamer(tokenizer, timeout=10.0, skip_special_tokens=True)
+    streamer = TextIteratorStreamer(tokenizer, timeout=10.0, skip_prompt=True, skip_special_tokens=True)
     generate_kwargs = dict(
         {"input_ids": input_ids},
         streamer=streamer,