Update app.py

app.py

@@ -4,7 +4,8 @@ import requests, tempfile
 import gradio as gr
 from llama_cpp import Llama
 
-MODEL_URL = "https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.1-GGUF/resolve/main/mistral-7b-instruct-v0.1.Q4_K_M.gguf"
+MODEL_URL = "https://huggingface.co/TheBloke/TinyLlama-1.1B-Chat-v1.0-GGUF/resolve/main/tinyllama-1.1b-chat-v1.0.Q2_K.gguf"
+#"https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.1-GGUF/resolve/main/mistral-7b-instruct-v0.1.Q4_K_M.gguf"
 
 print("Downloading model into temporary memory... This may take a while ⏳")
 response = requests.get(MODEL_URL, stream=True)