Langboat
/

mengzi-oscar-base

Inference Endpoints

Model card Files Files and versions Community

ckm commited on Sep 29, 2021

Commit

d0f25be

•

1 Parent(s): dbd59b8

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -5,8 +5,8 @@ license: apache-2.0
 ---
-# Mengzi-oscar-base (Chinese Multi-modal pretraining model)
-Mengzi-oscar was trained based on the English multi-mode pre-training model [Oscar](https://github.com/microsoft/Oscar), and was initialized using [Mengzi-Bert-Base](https://github.com/Langboat/Mengzi). 3.7M pairs of images and texts were used, including 0.7M Chinese image-caption pairs, 3M Chinese image-question pairs, a total of 0.22M  different images.
 ## Usage
 #### Installation

 ---
+# Mengzi-oscar-base (Chinese Multi-modal pre-training model)
+Mengzi-oscar is trained based on the Multi-modal pre-training model [Oscar](https://github.com/microsoft/Oscar), and is initialized using [Mengzi-Bert-Base](https://github.com/Langboat/Mengzi). 3.7M pairs of images and texts were used, including 0.7M Chinese image-caption pairs, 3M Chinese image-question pairs, a total of 0.22M different images.
 ## Usage
 #### Installation