update name

README.md

@@ -13,7 +13,7 @@ tags:
 - feature-extraction
 ---
 
-# Taiyi-CLIP-Roberta-326M-ViT-H-Chinese
+# Taiyi-CLIP-RoBERTa-326M-ViT-H-Chinese
 
 - Github: [Fengshenbang-LM](https://github.com/IDEA-CCNL/Fengshenbang-LM)
 - Docs: [Fengshenbang-Docs](https://fengshenbang-doc.readthedocs.io/)
@@ -42,15 +42,15 @@ We follow the experimental setup of CLIP to obtain powerful visual-language inte
 
 |  model   | dataset  | Top1 | Top5 |
 |  ----  | ----  | ---- | ---- |
-| Taiyi-CLIP-Roberta-326M-ViT-H-Chinese  | ImageNet1k-CN | 54.35% | 80.64% |
+| Taiyi-CLIP-RoBERTa-326M-ViT-H-Chinese  | ImageNet1k-CN | 54.35% | 80.64% |
 
 **Zero-Shot Text-to-Image Retrieval**
 
 |  model   | dataset  | Top1 | Top5 | Top10 |
 |  ----  | ----  | ---- | ---- | ---- |
-| Taiyi-CLIP-Roberta-326M-ViT-H-Chinese  | Flickr30k-CNA-test | 60.82% | 85.00%  | 91.04% |
-| Taiyi-CLIP-Roberta-326M-ViT-H-Chinese  | COCO-CN-test | 60.02% | 83.95%  | 93.26% |
-| Taiyi-CLIP-Roberta-326M-ViT-H-Chinese  | wukong50k | 66.85% | 92.81% | 96.69% |
+| Taiyi-CLIP-RoBERTa-326M-ViT-H-Chinese  | Flickr30k-CNA-test | 60.82% | 85.00%  | 91.04% |
+| Taiyi-CLIP-RoBERTa-326M-ViT-H-Chinese  | COCO-CN-test | 60.02% | 83.95%  | 93.26% |
+| Taiyi-CLIP-RoBERTa-326M-ViT-H-Chinese  | wukong50k | 66.85% | 92.81% | 96.69% |
 
 ## 使用 Usage
 
@@ -65,8 +65,8 @@ import numpy as np
 
 query_texts = ["一只猫", "一只狗",'两只猫', '两只老虎','一只老虎']  # 这里是输入文本的，可以随意替换。
 # 加载Taiyi 中文 text encoder
-text_tokenizer = BertTokenizer.from_pretrained("IDEA-CCNL/Taiyi-CLIP-Roberta-326M-ViT-H-Chinese")
-text_encoder = BertModel.from_pretrained("IDEA-CCNL/Taiyi-CLIP-Roberta-326M-ViT-H-Chinese").eval()
+text_tokenizer = BertTokenizer.from_pretrained("IDEA-CCNL/Taiyi-CLIP-RoBERTa-326M-ViT-H-Chinese")
+text_encoder = BertModel.from_pretrained("IDEA-CCNL/Taiyi-CLIP-RoBERTa-326M-ViT-H-Chinese").eval()
 
 url = "http://images.cocodataset.org/val2017/000000039769.jpg"  # 这里可以换成任意图片的url
 # 加载openclip的image encoder