Update app.py

app.py

@@ -6,7 +6,7 @@ import torch
 if torch.cuda.is_available():
     tokenizer = AutoTokenizer.from_pretrained("ai-forever/mGPT-13B")
     model = AutoModelForCausalLM.from_pretrained("ai-forever/mGPT-13B", load_in_8bit=True, device_map="auto")
-    pipe = pipeline("text-generation", model=model, tokenizer=tokenizer, device=0)
+    pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)
 
 @spaces.GPU
 def predict(text):