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

The bert-base-nli-max-tokens model is described in the paper Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks . You can use the model directly from the model repository to compute sentence embeddings . It uses max pooling to generate a fixed sized sentence embedding . The model becomes more convenient when you have sentence-transformers installed:pip install -U sentence-transformer-model-trainers-repository. Then you can use this model like this: In this case, the model is used to generate sentence and text embeddeddings for each input sentence. For example, the,