Update main.py

main.py

@@ -61,7 +61,7 @@ device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 model = AutoModelForCausalLM.from_pretrained(
     model_path,
     cache_dir=".",
-    load_in_8bit=True if 'cuda' in device else False,  # Enable loading in INT8
+    load_in_8bit=False,  # Enable loading in INT8
     device_map="auto"  # Automatically map model to available devices
 )