Update app.py

app.py

@@ -3,6 +3,7 @@
 import os
 from threading import Thread
 from typing import Iterator
+import torch
 
 import gradio as gr
 # import spaces
@@ -15,7 +16,7 @@ MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "8192"))
 
 if torch.cuda.is_available():
     model_id = "BramVanroy/GEITje-ultra-dpo-5e-7lr-128tbs-0.1b"
-    model = AutoModelForCausalLM.from_pretrained(model_id, load_in_8bit=True, device_map="auto")
+    model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")
     tokenizer = AutoTokenizer.from_pretrained(model_id)