Update app.py

app.py

@@ -31,8 +31,7 @@ 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)
-#model_id = "prithivMLmods/Pocket-Llama2-3.2-3B-Instruct"
-model_id = "prithivMLmods/Vvv"
+model_id = "prithivMLmods/Pocket-Llama2-3.2-3B-Instruct"
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 model = AutoModelForCausalLM.from_pretrained(
     model_id,