Update app.py

app.py

@@ -48,16 +48,9 @@ def generate(
     top_p: float,
     top_k: int,
 ) -> Iterator[list[tuple[str, str]]]:
-    if max_new_tokens > MAX_MAX_NEW_TOKENS:
-        raise ValueError
 
     history = history_with_input[:-1]
     generator = run(message, history, system_prompt, max_new_tokens, temperature, top_p, top_k)
-    try:
-        first_response = next(generator)
-        yield history + [(message, first_response)]
-    except StopIteration:
-        yield history + [(message, '')]
     for response in generator:
         yield history + [(message, response)]