Update app.py

app.py

@@ -6,11 +6,11 @@ from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStream
 import gradio as gr
 from threading import Thread
 
-MODEL_LIST = ["meta-llama/Meta-Llama-3.1-8B-Instruct"]
+MODEL_LIST = ["microsoft/Phi-3.5-MoE-instruct"]
 HF_TOKEN = os.environ.get("HF_TOKEN", None)
 MODEL = os.environ.get("MODEL_ID")
 
-TITLE = "<h1><center>Meta-Llama3.1-8B</center></h1>"
+TITLE = "<h1><center>Phi-3.5-MoE-instruct</center></h1>"
 
 PLACEHOLDER = """
 <center>
@@ -45,6 +45,7 @@ model = AutoModelForCausalLM.from_pretrained(
     torch_dtype=torch.bfloat16,
     device_map="auto",
     quantization_config=quantization_config)
+    trust_remote_code=True
 
 @spaces.GPU()
 def stream_chat(