Update app.py

app.py

@@ -12,7 +12,7 @@ def generate_text(input_text):
     output = llm(f"Q: {input_text}  A:", max_tokens=521, stop=["Q:", "\n"], echo=True)
     return output['choices'][0]['text']
 
-input_text = user_message
+input_text = gr.inputs.Textbox(lines= 10, label="Enter your input text")
 output_text = gr.outputs.Textbox(label="Output text")
 
 description = "bro neil it currently dosent work two people sending it request at the same time so going to fix that but currently running ggml models with llama.cpp implementation in python [https://github.com/abetlen/llama-cpp-python]"
@@ -23,28 +23,7 @@ examples = [
     ["What is the square root of 64?", "The square root of 64 is 8."]
 ]
 
-with gr.Blocks() as demo:
-    chatbot = gr.Chatbot()
-    msg = gr.Textbox()
-    clear = gr.Button("Clear")
-
-    def user(user_message, history):
-        return "", history + [[user_message, None]]
-
-    def bot(history):
-        bot_message = gr.outputs.Textbox(label="Output text")
-        history[-1][1] = ""
-        for character in bot_message:
-            history[-1][1] += character
-            time.sleep(0.05)
-            yield history
-
-    msg.submit(user, [msg, chatbot], [msg, chatbot], queue=False).then(
-        bot, chatbot, chatbot
-    )
-    clear.click(lambda: None, None, chatbot, queue=False)
-    
-demo.queue()
-if __name__ == "__main__":
-    demo.launch()
+demo = gr.Interface(fn=generate_text, inputs=input_text, outputs=output_text, title="Llama Language Model", description=description, examples=examples)
+demo.queue(concurrency_count=3)
+demo.launch()