Update app.py

app.py

@@ -4,6 +4,16 @@ import gradio as gr
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
 
+torch.random.manual_seed(0)
+
+model = AutoModelForCausalLM.from_pretrained(
+    "microsoft/Phi-3-mini-128k-instruct",
+    device_map="cuda",
+    torch_dtype="auto",
+    trust_remote_code=True,
+)
+tokenizer = AutoTokenizer.from_pretrained("microsoft/Phi-3-mini-128k-instruct")
+
 pipe = pipeline(
     "text-generation",
     model=model,