# Retrieval Optimization

Speed Embedding 7B Instruct is a large-scale language model based on the Transformer architecture, focusing on text embedding and classification tasks, and has demonstrated outstanding performance in multiple benchmarks.

NoInstruct Small Embedding Model v0 is an improved embedding model focused on enhancing retrieval task performance while maintaining independence from arbitrary instruction encoding.

The first version of the Fio series Japanese embedding model, based on BERT architecture, focusing on Japanese text similarity and feature extraction tasks

This is a vocabulary-pruned version of the intfloat/multilingual-e5-large model, retaining only Russian and English tokens while maintaining the original model's performance.