Update app.py

app.py

@@ -3,7 +3,7 @@ from llama_cpp import Llama
 
 llm = Llama(model_path="model.gguf", n_ctx=8000, n_threads=2, chat_format="chatml")
   
-def generate(message, history, do_sample=True, temperature=0.7,max_tokens=4000, top_p=0.9):
+def generate(message, history, do_sample=True, temperature=0.7,max_tokens=8000, top_p=0.9):
     system_prompt = """You are an advanced artificial intelligence assistant. Your role is to give clear and precise answers."""
     formatted_prompt = [{"role": "system", "content": system_prompt}]
     for user_prompt, bot_response  in history:
@@ -23,7 +23,7 @@ avatar_images=["user.png", "botnb.png"], bubble_full_width=False, show_label=Fal
 iface = gr.ChatInterface(fn=generate, chatbot=mychatbot, retry_btn=None, undo_btn=None)
 
 with gr.Blocks() as demo:
-    gr.HTML("<center><h1> Hermes-2-Theta-Llama-3-8B - Q8_K_M - GGUF (Quantized) </h1></center>")
+    gr.HTML("<center><h1> Hermes-2-Theta-Llama-3-8B </h1></center>")
     iface.render()
 
 demo.queue().launch(show_api=False, server_name="0.0.0.0")