# Information Retrieval Enhancement

This is a preview version of a Japanese general-purpose reranking model, trained on the cl-nagoya/ruri-v3-pt-310m base model, specifically designed for Japanese text relevance ranking tasks.

This is a cross-encoder model fine-tuned on MiniLM-L12-H384-uncased for text re-ranking and semantic search tasks.

This is a sentence-transformers model fine-tuned from ModernBERT-large, designed to map sentences and paragraphs into a 1024-dimensional dense vector space, supporting tasks such as semantic textual similarity and semantic search.

This is a Transformer-based Reranker model primarily used for information retrieval and search result optimization tasks.

This model is converted from BAAI/bge-reranker-large into GGUF format for reranking tasks, supporting both Chinese and English.

An improved Polish re-ranking model based on sdadas/polish-roberta-large-v2, trained with RankNet loss function and supports Flash Attention 2 acceleration

This is a generative model specifically designed for search query rewriting, employing a sequence-to-sequence architecture and reinforcement learning framework to produce diverse and relevant query rewrites.

FollowIR-7B is an instruction retrieval model fine-tuned based on Mistral-7B-Instruct-v0.2, focusing on reranking in retrieval tasks.

SPLADE-v3 is the latest generation of the SPLADE model series, developed based on SPLADE++SelfDistil, employing a hybrid training approach combining KL divergence and MarginMSE for information retrieval tasks.

A sentence transformer model specifically designed for Italian Q&A tasks, capable of parsing and analyzing Italian text to predict the most likely context containing answers.

This is a sentence transformer model based on DistilBERT, specifically designed for feature extraction and sentence similarity calculation.

SPLADE model for passage retrieval, improving sparse neural information retrieval through knowledge distillation

SPLADE model for passage retrieval, improving retrieval effectiveness through sparse latent document expansion and knowledge distillation techniques

Doc2Query is a model for document retrieval that converts documents into queries to improve the effectiveness of information retrieval.

A document re-ranking model based on the T5-base architecture, fine-tuned on both the MS MARCO and medical-domain MedMARCO datasets to optimize the relevance ranking of retrieval results.

This model is a reranker based on the T5-large architecture, fine-tuned for 100,000 steps (i.e., 10 epochs) on the MS MARCO passage dataset, primarily used for document and passage reranking tasks.

A sentence embedding model trained on the MS MARCO dataset, using a word2vec-initialized 256k vocabulary and DistilBERT architecture, suitable for semantic search and sentence similarity tasks

This is a text re-ranking model trained on the MS MARCO document dataset for BM25 retrievers, primarily used to improve the ranking effectiveness of document retrieval.