Update README.md

README.md

@@ -117,27 +117,35 @@ Figure 2: Human evaluation comparing Crab, GPT-3.5, and Pygmalion-2-7B. We selec
 
 Table 2: The ablation study for Crab. Due to missing attributes in our dataset, we sampled 1,000 fully attributed instances as the sub-test set to conduct the ablation experiments, referred to as Crab (sampled). The notation “w/o base" means without base role information for training RP-LLMs, including age, gender, personality, description, and expression; “w/o ref." means without catchphrases and knowledge; “w/o scene" means without interlocutor, relation, scenario, and tags.
 
+<br>
+
 # 4. Three Datasets
 We publish three datasets, including Crab role-playing train set, Crab role-playing evaluation benchmark, and manually annotated role-playing evaluation dataset (can be used for training a Role-palying Evaluation Model).
 
-Crab role-playing train set:
+## 4.1 Crab role-playing train set:
 {https://huggingface.co/datasets/HeAAAAA/Crab-role-playing-train-set}
 
-Crab role-playing evaluation benchmark:
+## 4.2 Crab role-playing evaluation benchmark:
 {https://huggingface.co/datasets/HeAAAAA/Crab-role-playing-evaluation-benchmark}
 
-Crab manually annotated role-playing evaluation dataset:
+## 4.3 Crab manually annotated role-playing evaluation dataset:
 {https://huggingface.co/datasets/HeAAAAA/Crab-manually-annotated-role-playing-evaluation-dataset}
 
 
+<br>
+
 # 5. Fine-tuned Role-playing Model
 We release a fine-tuned model to achieve configurable Role-Playing tasks.
 {https://huggingface.co/HeAAAAA/Crab}
 
+<br>
+
 # 6. Role-palying Evaluation Model
 We release a trained model to automate the evaluation of role-playing tasks.
 {https://huggingface.co/HeAAAAA/RoleRM}
 
+<br>
+
 # 7. Citation
 
 ```bibtex