Update app.py

app.py

@@ -31,6 +31,8 @@ REPO_NAME = "jaydatech/phi3-finetuned-project"
 BASE_MODEL = "microsoft/Phi-3-mini-4k-instruct"
 HF_TOKEN = os.getenv("HF_TOKEN")  # Load from Render environment variable
 
+config = AutoConfig.from_pretrained(REPO_NAME, use_auth_token=HF_TOKEN)
+
 device = "cuda" if torch.cuda.is_available() else "cpu"
 
 #tokenizer = LlamaTokenizerFast.from_pretrained(REPO_NAME, token=HF_TOKEN)
@@ -43,8 +45,7 @@ device = "cuda" if torch.cuda.is_available() else "cpu"
 #     use_auth_token=HF_TOKEN
 # )
 
-config = AutoConfig.from_pretrained(REPO_NAME, use_auth_token=HF_TOKEN)
-tokenizer = AutoTokenizer.from_pretrained(BASE_MODEL, trust_remode_code=True, use_auth_token=HF_TOKEN)
+tokenizer = AutoTokenizer.from_pretrained(BASE_MODEL, trust_remote_code=True)
 
 model = AutoModelForCausalLM.from_pretrained(
     REPO_NAME,