kunyi
commited on
Commit
·
e6525dd
1
Parent(s):
f76d30f
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,6 +1,5 @@
|
|
| 1 |
[**中文说明**](README_CN.md) | [**English**](README.md)
|
| 2 |
# Introduction
|
| 3 |
-
<br><br>
|
| 4 |
This project aims to provide a better Chinese CLIP model. The training data used in this project consists of publicly accessible image URLs and related Chinese text descriptions, totaling 400 million. After screening, we ultimately used 100 million data for training.
|
| 5 |
This project is produced by QQ-ARC Joint Lab, Tencent PCG.
|
| 6 |
<br><br>
|
|
@@ -273,7 +272,7 @@ bash scripts/zeroshot_eval.sh 0 \
|
|
| 273 |
ViT-B-16 RoBERTa-wwm-ext-base-chinese \
|
| 274 |
./pretrained_weights/QA-CLIP-base.pt
|
| 275 |
```
|
| 276 |
-
# Acknowledgments
|
| 277 |
<br><br>
|
|
|
|
| 278 |
The project code is based on implementation of <b>[Chinese-CLIP](https://github.com/OFA-Sys/Chinese-CLIP)</b>, and we are very grateful for their outstanding open-source contributions.
|
| 279 |
<br><br>
|
|
|
|
| 1 |
[**中文说明**](README_CN.md) | [**English**](README.md)
|
| 2 |
# Introduction
|
|
|
|
| 3 |
This project aims to provide a better Chinese CLIP model. The training data used in this project consists of publicly accessible image URLs and related Chinese text descriptions, totaling 400 million. After screening, we ultimately used 100 million data for training.
|
| 4 |
This project is produced by QQ-ARC Joint Lab, Tencent PCG.
|
| 5 |
<br><br>
|
|
|
|
| 272 |
ViT-B-16 RoBERTa-wwm-ext-base-chinese \
|
| 273 |
./pretrained_weights/QA-CLIP-base.pt
|
| 274 |
```
|
|
|
|
| 275 |
<br><br>
|
| 276 |
+
# Acknowledgments
|
| 277 |
The project code is based on implementation of <b>[Chinese-CLIP](https://github.com/OFA-Sys/Chinese-CLIP)</b>, and we are very grateful for their outstanding open-source contributions.
|
| 278 |
<br><br>
|