Update app.py

app.py

@@ -13,13 +13,9 @@ print(f"Using device: {device}")
 
 # Load base model and tokenizer
 tokenizer = AutoTokenizer.from_pretrained('GSAI-ML/LLaDA-8B-Instruct', trust_remote_code=True)
-base_model = AutoModel.from_pretrained('GSAI-ML/LLaDA-8B-Instruct', trust_remote_code=True, 
+model = AutoModel.from_pretrained('Proximile/LLaDA-8B-Tools', trust_remote_code=True, 
                                      torch_dtype=torch.bfloat16, load_in_8bit=True)
 
-# Load the LoRA adapter for better tool calling
-model = PeftModel.from_pretrained(base_model, "Proximile/LLaDA-8B-Tools-LoRA")
-model.eval()
-
 # Constants
 MASK_TOKEN = "[MASK]"
 MASK_ID = 126336  # The token ID of [MASK] in LLaDA