Update app.py

app.py

@@ -30,7 +30,7 @@ MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
 
 device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
 
-# Load text-only model and tokenizer (Pocket Llama)
+# Load text-only model and tokenizer
 model_id = "prithivMLmods/Omega-Herculis-7B-Prime2"
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 model = AutoModelForCausalLM.from_pretrained(