Update README.md

README.md

@@ -18,7 +18,9 @@ python pretrain.py > log.log
 
 ## Pre-trained Models
 
-We provide pretrained model weights for the [vit base version](https://huggingface.co/OpenFace-CQUPT/Facial-language-image-pretraining-model/tree/main/ckpt)
+We provide pretrained model weights :
+[FLIP Base](https://huggingface.co/OpenFace-CQUPT/Facial-language-image-pretraining-model/tree/main/ckpt)
+[FLIP Large] Coming soon......
 
 ## Datasets
 
@@ -29,19 +31,19 @@ Download the FaceCaption-15M dataset from [here](https://huggingface.co/dataset
 
 ### Task1: Text-Image Retrieval
 
-**Comparison with other classical pretrained models. All pretrained model backbones are frozen, with only the linear layer being fine-tuned. † represents the model pretrained on the LAION-Face [86] dataset; * represents the model pretrained on the FaceCaption dataset constructed without using LLM text generation.**
+**Table 1:** Comparison with other classical pretrained models. All pretrained model backbones are frozen, with only the linear layer being fine-tuned. † represents the model pretrained on the LAION-Face [86] dataset; * represents the model pretrained on the FaceCaption dataset constructed without using LLM text generation.
 
 ![](https://img.yutangli.net/img/202403181015142.png)
 
 ### Task2: Facial Attributes Prediction
 
-**Comparison with other classical models. † represents the model pre-trained on the original LAION-Face dataset.**
+**Table 2:** Comparison with other classical models. † represents the model pre-trained on the original LAION-Face dataset.
 
 ![image-20240318101126897](https://img.yutangli.net/img/202403181011115.png)
 
 ### Task3: Sketch Less Facial Image Retrieval
 
-**Comparative results with different baseline methods. † represents the model pre-trained on the LAION-Face dataset.**
+**Table 3:** Comparative results with different baseline methods. † represents the model pre-trained on the LAION-Face dataset.
 
 ![image-20240318101633671](https://img.yutangli.net/img/202403181016876.png)