Update app.py

app.py

@@ -21,7 +21,7 @@ MAX_INPUT_TOKEN_LENGTH = 32000
 
 device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
 
-tokenizer = AutoTokenizer.from_pretrained("EvaByte/EvaByte", trust_remote_code=True)
+tokenizer = AutoTokenizer.from_pretrained("EvaByte/EvaByte-SFT", trust_remote_code=True)
 model = AutoModelForCausalLM.from_pretrained(
     "EvaByte/EvaByte-SFT",
     torch_dtype=torch.bfloat16,