Update README.md

README.md

@@ -35,8 +35,8 @@ device = "cuda" if torch.cuda.is_available() else "cpu"
 
 # Load tokenizer and models
 print("Loading models...")
-tokenizer = AutoTokenizer.from_pretrained("unsloth/llama-3.2-1b-instruct")
-base_model = AutoModelForCausalLM.from_pretrained("unsloth/llama-3.2-1b-instruct").to(device)
+tokenizer = AutoTokenizer.from_pretrained("unsloth/llama-3.2-1b-instruct-bnb-4bit")
+base_model = AutoModelForCausalLM.from_pretrained("unsloth/llama-3.2-1b-instruct-bnb-4bit").to(device)
 model = PeftModel.from_pretrained(base_model, "HackWeasel/llama-3.2-1b-QLORA-IMDB").to(device)
 model.eval()
 print("Models loaded!")