handling max_new_token errors.

app.py

@@ -41,6 +41,9 @@ llm = AutoModelForCausalLM.from_pretrained("TheBloke/Llama-2-7B-Chat-GGUF",
                                            model_type="llama", 
                                           #  config = ctransformers.hub.AutoConfig,
                                            # hf = True
+                                           temperature = 0.2,
+                                           max_new_tokens = 1024,
+                                           stop = ['\n']
                                            )
 
 
@@ -157,5 +160,5 @@ gr.Interface(
     description="This app facilitates a conversation with PDFs available on https://www.delo.si/assets/media/other/20110728/100%20Weird%20Facts%20About%20the%20Human%20Body.pdf💡",
     theme="soft",
     examples=["Hello", "what is the speed of human nerve impulses?"],
-    cache_examples=True,
+    # cache_examples=True,
 ).launch()