Train 400x faster Static Embedding Models with Sentence Transformers
…https://github.com/UKPLab/sentence-transformers/blob/cccab8303aaf6e18f069b0da578b3d162bf8442a/sentence_transformers/models/StaticEmbedding.py#L106-L108 In short: the model will never truncate sequences, because the approach has linear complexity (2x more data…