added repetition penalty.

app.py

@@ -36,11 +36,8 @@ print("loading the LLM......................................")
 llm = AutoModelForCausalLM.from_pretrained("TheBloke/Llama-2-7B-Chat-GGUF", 
                                            model_file="llama-2-7b-chat.Q3_K_L.gguf", 
                                            model_type="llama", 
-                                          #  config = ctransformers.hub.AutoConfig,
-                                           # hf = True
                                            temperature = 0.2,
-                                           # max_new_tokens = 1024,
-                                           # stop = ['\n']
+                                           repetition_penalty = 1.5
                                            )