max_new_tokens update

app.py

@@ -38,7 +38,8 @@ llm = AutoModelForCausalLM.from_pretrained("TheBloke/Llama-2-7B-Chat-GGUF",
                                            model_file="llama-2-7b-chat.Q3_K_S.gguf", 
                                            model_type="llama", 
                                            temperature = 0.2,
-                                           repetition_penalty = 1.5
+                                           repetition_penalty = 1.5,
+                                           max_new_tokens = 300,
                                            )