Update app.py

app.py

@@ -5,14 +5,15 @@ import logging
 from datetime import datetime
 import torch
 from transformers import AutoTokenizer, AutoModelForCausalLM
-from transformers import TextStreamer
+from transformers import pipeline
 
 device = "cuda" if torch.cuda.is_available() else "cpu"
 
-# Load the model and tokenizer
-model_name = "mixtral/instruct-v0.1"
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForCausalLM.from_pretrained(model_name).to(device)
+messages = [
+    {"role": "user", "content": "Who are you?"},
+]
+pipe = pipeline("text-generation", model="mistralai/Mixtral-8x7B-Instruct-v0.1")
+pipe(messages)
 
 def stream_chat(
     message: str,