Update app.py

app.py

@@ -32,7 +32,7 @@ def process_paragraph(paragraph, progress=gr.Progress()):
 # Load model and tokenizer
 model_name = "princeton-nlp/Llama-3-Instruct-8B-SimPO"
 tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto", torch_dtype=torch.float16, load_in_8bit=True)
+model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto", torch_dtype=torch.float16)
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 model.to(device)