Update app.py

app.py

@@ -2,7 +2,7 @@ import gradio as gr
 import torch
 from transformers import pipeline
 
-pipe = pipeline("text-generation", model="NousResearch/Llama-2-13b-chat-hf", device_map="auto")
+pipe = pipeline("text-generation", model="NousResearch/Llama-2-13b-chat-hf", torch_dtype=torch.bfloat16, device_map="auto")
 
 def model_generate(text):
     # We use the tokenizer's chat template to format each message - see https://huggingface.co/docs/transformers/main/en/chat_templating