hidehisa-arai commited on
Commit
07ddef8
1 Parent(s): e1c09c5

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -3
README.md CHANGED
@@ -1,5 +1,5 @@
1
  ---
2
- license: mit
3
  language:
4
  - ja
5
  pipeline_tag: feature-extraction
@@ -15,7 +15,7 @@ tags:
15
  * **Developed by**: [Recruit Co., Ltd.](https://huggingface.co/recruit-jp)
16
  * **Model type**: Contrastive Language-Image Pretrained Model
17
  * **Language(s)**: Japanese
18
- * **LICENSE**: MIT
19
 
20
  More details are described in our tech blog post.
21
  * [日本語CLIP学習済みモデルとその評価用データセットの公開](https://blog.recruit.co.jp/data/articles/japanese-clip/)
@@ -119,4 +119,9 @@ Note that stabilityai/japanese-stable-clip-vit-l-16 is trained on STAIR Captions
119
 
120
  ## Training Dataset
121
 
122
- This model is trained with 128M image-text pairs from the Japanese subset of [LAION2B-multi](https://huggingface.co/datasets/laion/laion2B-multi) dataset.
 
 
 
 
 
 
1
  ---
2
+ license: cc-by-4.0
3
  language:
4
  - ja
5
  pipeline_tag: feature-extraction
 
15
  * **Developed by**: [Recruit Co., Ltd.](https://huggingface.co/recruit-jp)
16
  * **Model type**: Contrastive Language-Image Pretrained Model
17
  * **Language(s)**: Japanese
18
+ * **LICENSE**: CC-BY-4.0
19
 
20
  More details are described in our tech blog post.
21
  * [日本語CLIP学習済みモデルとその評価用データセットの公開](https://blog.recruit.co.jp/data/articles/japanese-clip/)
 
119
 
120
  ## Training Dataset
121
 
122
+ This model is trained with 128M image-text pairs from the Japanese subset of [LAION2B-multi](https://huggingface.co/datasets/laion/laion2B-multi) dataset.
123
+
124
+ ## Disclaimer
125
+
126
+ (Japanese)
127
+ ㈱リクルートは、本モデル利用による成果に関し、正確性、有用性、確実性、違法性の確認及び何らの保証および補償を行わないものとし、また、モデル利用によって利用者に生じた損害および第三者との間における紛争について㈱リクルートは一切責任を負いません。