rinna
/
japanese-clip-vit-b-16
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

update README.md

This commit is contained in:
mkshing 2022-05-11 10:39:40 +09:00
parent 062b689ee1
commit f093721140
1 changed files with 12 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
README.md
View File

@ -1,7 +1,9 @@
---
language: ja
thumbnail: https://github.com/rinnakk/japanese-pretrained-models/blob/master/rinna.png
license: apache-2.0
tags:
- feature-extraction
- ja
- japanese
- clip
@ -56,3 +58,13 @@ with torch.no_grad():
print("Label probs:", text_probs) # prints: [[1.0, 0.0, 0.0]]
```
# Model architecture
The model was trained a ViT-B/16 Transformer architecture as an image encoder and uses a 12-layer RoBERTa as a text encoder. The text encoder was trained upon the pre-trained Japanese RoBERTa model [rinna/japanese-roberta-base](https://huggingface.co/rinna/japanese-roberta-base) with the same sentencepiece tokenizer.
# Training
The model was trained on [CC12M](https://github.com/google-research-datasets/conceptual-12m) translated the captions to Japanese.
# License
[Apache-2.0 license](https://www.apache.org/licenses/LICENSE-2.0)