Update app.py

app.py

@@ -14,10 +14,10 @@ MAX_MAX_NEW_TOKENS = 2048
 DEFAULT_MAX_NEW_TOKENS = 1024
 MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "8192"))
 
-if torch.cuda.is_available():
-    model_id = "BramVanroy/GEITje-7B-ultra"
-    model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")
-    tokenizer = AutoTokenizer.from_pretrained(model_id)
+model_id = "BramVanroy/GEITje-7B-ultra"
+model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+tokenizer.pad_token_id = tokenizer.eos_token_id
 
 
 @spaces.GPU