AI NEWS.ccLaBSE-en-ru
This is a truncated version of sentence-transformers/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. The model has been truncated in this notebook. You can adapt it for other languages (like EIStakovskii/LaBSE-fr-de), models or datasets.
译文尚未就绪，显示来源原文
This is a truncated version of sentence-transformers/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. The model has been truncated in this notebook. You can adapt it for other languages (like EIStakovskii/LaBSE-fr-de), models or datasets.