Update app.py

app.py

@@ -1,15 +1,15 @@
 import gradio as gr
-from llama_cpp import Llama
-
+#from llama_cpp import Llama
+from transformers import AutoModelForCausalLM
 # Load the model
-llm = Llama.from_pretrained(
+llm = AutoModelForCausalLM.from_pretrained(
     repo_id="Viet-Mistral/Vistral-7B-Chat"
    # filename="models-7B-F16.gguf"
 )
 
 # Define the function to interact with the model
 def chat_with_model(user_input):
-    response = llm.create_chat_completion(
+    response = llm.generate(
         messages=[
             {"role": "user", "content": user_input}
         ]