setu4993 commited on
Commit
082cccc
1 Parent(s): cc90758

Update model card

Browse files
Files changed (1) hide show
  1. README.md +1 -0
README.md CHANGED
@@ -131,6 +131,7 @@ Language-agnostic BERT Sentence Encoder (LaBSE) is a BERT-based model trained fo
131
  - Paper: [arXiv](https://arxiv.org/abs/2007.01852).
132
  - Original model: [TensorFlow Hub](https://tfhub.dev/google/LaBSE/2).
133
  - Blog post: [Google AI Blog](https://ai.googleblog.com/2020/08/language-agnostic-bert-sentence.html).
 
134
 
135
  This is migrated from the v2 model on the TF Hub, which uses dict-based input. The embeddings produced by both the versions of the model are [equivalent](https://github.com/setu4993/convert-labse-tf-pt/blob/ec3a019159a54ed6493181a64486c2808c01f216/tests/test_conversion.py#L31).
136
 
131
  - Paper: [arXiv](https://arxiv.org/abs/2007.01852).
132
  - Original model: [TensorFlow Hub](https://tfhub.dev/google/LaBSE/2).
133
  - Blog post: [Google AI Blog](https://ai.googleblog.com/2020/08/language-agnostic-bert-sentence.html).
134
+ - Conversion from TensorFlow to PyTorch: [GitHub](https://github.com/setu4993/convert-labse-tf-pt).
135
 
136
  This is migrated from the v2 model on the TF Hub, which uses dict-based input. The embeddings produced by both the versions of the model are [equivalent](https://github.com/setu4993/convert-labse-tf-pt/blob/ec3a019159a54ed6493181a64486c2808c01f216/tests/test_conversion.py#L31).
137