IDEA-CCNL
/

Taiyi-CLIP-RoBERTa-326M-ViT-H-Chinese

Feature Extraction

text-embeddings-inference

Inference Endpoints

Model card Files Files and versions Community

weifeng-chen commited on Sep 26, 2022

Commit

294f468

•

1 Parent(s): 6e7d1f4

update readme

Files changed (1) hide show

README.md +4 -4

README.md CHANGED Viewed

@@ -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-Chinese  | ImageNet1k-CN | 54.35% | 80.64% |
 **Zero-Shot Text-to-Image Retrieval**
 |  model   | dataset  | Top1 | Top5 | Top10 |
 |  ----  | ----  | ---- | ---- | ---- |
-| Taiyi-CLIP-Roberta-326M-Chinese  | Flickr30k-CNA-test | 60.82% | 85.00%  | 91.04% |
-| Taiyi-CLIP-Roberta-326M-Chinese  | COCO-CN-test | 60.02% | 83.95%  | 93.26% |
-| Taiyi-CLIP-Roberta-326M-Chinese  | wukong50k | 66.85% | 92.81% | 96.69% |
 ## 使用 Usage

 |  model   | dataset  | Top1 | Top5 |
 |  ----  | ----  | ---- | ---- |
+| 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% |
 ## 使用 Usage