# Retrieval Augmentation

This is a text ranking model used for relevance-based text sorting.

A 0.5B parameter text reranking model based on Qwen2.5 architecture, efficiently trained using Unsloth and TRL libraries

Ruri is a Japanese universal text embedding model, focusing on sentence similarity calculation and feature extraction, with support for long text processing.

This is the GGUF quantized version of the castorini/rank_zephyr_7b_v1_full model, designed for text ranking tasks.

Snowflake Arctic Embed L is a model focused on sentence similarity and feature extraction, suitable for various natural language processing tasks.

A document expansion model based on T5-base architecture, trained on the MS MARCO dataset, used to generate potential queries related to document content to enhance retrieval effectiveness

FiD is a Q&A system model based on knowledge distillation, improving the efficiency of Q&A systems by distilling the knowledge from the reader model into the retriever.