Update README.md

README.md

@@ -1,10 +1,9 @@
 # TDDBench: A Benchmark for Training data detection
 
-We have uploaded the datasets and target models used by TDDBench on [Huggingface](https://huggingface.co/TDDBench) to facilitate a quick evaluation of the Training Data Detection algorithm. This includes 12 datasets and 60 target models, with plans to upload more data and target models in the future.
+We have uploaded the datasets and target models used by TDDBench on Huggingface to facilitate a quick evaluation of the Training Data Detection algorithm. This includes 12 datasets and 60 target models, with plans to upload more data and target models in the future.
 
 To load an evaluation dataset, you can use the following code:
 ```python
-
 # Load dataset
 from datasets import load_dataset
 dataset_name = "student"
@@ -14,7 +13,6 @@ dataset = load_dataset(dataset_path)["train"]
 
 To load a target model, you can use the following code:
 ```python
-
 from transformers import AutoConfig, AutoModel
 from hfmodel import MLPConfig, MLPHFModel, WRNConfig, WRNHFModel
 
@@ -38,7 +36,6 @@ tdd_label = np.array(config.tdd_label)
 The [demo.ipynb](https://github.com/zzh9568/TDDBench/blob/main/demo.ipynb) file in our [release code](https://github.com/zzh9568/TDDBench) hub offers a straightforward example of how to download the target model and dataset from Hugging Face, along with instructions for recording the output loss of the model for both training and non-training data.
 
 ### References
-
 ```python
 @article{zhu2024tddbench,
   title={TDDBench: A Benchmark for Training data detection},