# QA system optimization

This is a sentence-transformers-based model capable of mapping sentences and paragraphs into a 768-dimensional dense vector space, suitable for tasks like clustering or semantic search.

The Silver Retriever model encodes Polish sentences or paragraphs into a 768-dimensional dense vector space, suitable for tasks like document retrieval or semantic search.

This model is a fine-tuned version of paraphrase-multilingual-mpnet-base-v2, supporting English and German sentence similarity calculation, suitable for multilingual text embedding tasks.

This is a multilingual Roberta model that can generate sentence embeddings for Bulgarian, inspired by Sentence-BERT with Google's USE model as the teacher.

This model is a BERT-Base fine-tuned for QA tasks, using 80% 1x4 block-sparse pre-training combined with knowledge distillation.