Removed requirements ... more pt 6

app.py

@@ -25,11 +25,11 @@ HF_TOKEN = os.getenv("HF_TOKEN")  # Load from Render environment variable
 device = "cuda" if torch.cuda.is_available() else "cpu"
 
 #tokenizer = AutoTokenizer.from_pretrained(REPO_NAME, token=HF_TOKEN)
-tokenizer = LlamaTokenizer.from_pretrained(REPO_NAME, token=HF_TOKEN)
+tokenizer = LlamaTokenizer.from_pretrained(REPO_NAME, use_auth_token=HF_TOKEN)
 
 model = AutoModelForCausalLM.from_pretrained(
     REPO_NAME,
-    token=HF_TOKEN,
+    use_auth_token=HF_TOKEN,
     torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32,
     device_map="auto"
 )