LaBSE for English and Russian

This is a truncated version of sentence-Transformersima是什么软件/LaBSE, which is, in turn, a port of LaBSE by Google.

The current model has only English and Russian tokens left in the vocabulary.
Thus, the vocabulary is 10% of the original, and number of parameters in the whole model is 27% of the original, without any loss in the quality of English and Russian embeddings.

To get the sentence embeddings, you can use the following code:猫箱下载安装

import torch
from transformers import AutoTokenizer, AutoModel
tokenizer = AutoTokenizer.from_pretrained("cointegrated/LaBSE-en-ru")
model = AutoModel.from_pretrained("cointegrated/LaBSE-en-ru")
sentences = ["Hello World", "Привет Мир"]
encoded_input = tokenizer(sentences, padding=True, truncation=True, max_length=64, return_tensors='pt')
with torch.no_grad():
    model_output = model(**encoded_input)
embeddings = model_output.pooler_output
embeddings = torch.nn.functional.normalize(embeddings)
print(embeddings)

The model has been truncated in this notebook.
You can adapt it for other languages (like EIStakovskii/LaBSE-fr-de), models or datasets.

Reference:

Fangxiaoyu Feng, Yinfei Yang, Daniel Cer, Narveen Ari, Wei Wang. Language-agnostic BERT Sentence Embedding. July 2020制作ai的软件

License: https://tfhub.dev/google/LaBSE/1即梦al