update

app.py

@@ -1,6 +1,7 @@
 import streamlit as st
 import subprocess
 import sys
+import time
 
 def install(package):
     subprocess.check_call([sys.executable, "-m", "pip", "install", package])
@@ -10,7 +11,10 @@ from llama_cpp import Llama
 prompt = st.chat_input("Say something")
 if prompt:
     llm = Llama(model_path="Meta-Llama-3.1-8B-Instruct-Q4_K_M.gguf")
+    start = time.time()
     r=llm(prompt, max_tokens=1000)
+    end = time.time()
+    print(f"The Generation time for 1000 tokens is : {end - start}")
     l="Nothing"
     try:
         l=r["choices"][0]["text"]