Update app.py

app.py

@@ -11,24 +11,16 @@ llm = Llama(model_path= hf_hub_download(repo_id="TheBloke/airoboros-l2-13b-gpt4-
 history = []
 
 def generate_text(input_text, history):
-    
     conversation_context = " ".join([f"{pair[0]} {pair[1]}" for pair in history])
     full_conversation = f"{conversation_context} Q: {input_text} \n A:"
-    
     output = llm(full_conversation, max_tokens=1024, stop=["Q:", "\n"], echo=True)
     response = output['choices'][0]['text']
     history.append([input_text, response])
-    for i in range(len(response)):
-    time.sleep(0.3)
-    yield "You typed: " + message[: i+1]
-            
+        for i in range(len(output)):
+        time.sleep(0.3)
+        yield "You typed: " + output[: i+1]
     
 
-with gr.Blocks() as demo:
-    chatbot = gr.Chatbot()
-    msg = gr.Textbox()
-    clear = gr.ClearButton([msg, chatbot])
-
 demo = gr.ChatInterface(generate_text)
 demo.queue(concurrency_count=1, max_size=5)
 demo.launch()