sentence-transformers/bert-base-nli-mean-tokens

The bert-base-nli-mean-tokens model is described in the paper Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks . The sentence-transformers repository allows to train and use Transformer models for generating sentence and text embeddings . You can use the model directly from the model repository to compute sentences . The model becomes more convenient when you have sentence-transformer installed: install -U sentence-Transformers . You need to install the model and use it to compute sentence embeddeddings with the model . For example: In this case, mean pooling is used to generate sentences with an attention mask .,