increased max_length vicuna

app.py

@@ -60,7 +60,7 @@ def vicuna_respond(tab_name, message, chat_history):
     print('Prompt + Context:')
     print(formatted_prompt)
     input_ids = vicuna_tokenizer.encode(formatted_prompt, return_tensors="pt")
-    output_ids = vicuna_model.generate(input_ids, do_sample=True, max_length=149, num_beams=5, no_repeat_ngram_size=2)
+    output_ids = vicuna_model.generate(input_ids, do_sample=True, max_length=200, num_beams=5, no_repeat_ngram_size=2)
     bot_message = vicuna_tokenizer.decode(output_ids[0], skip_special_tokens=True)
     
     # Remove formatted prompt from bot_message