# Information Retrieval Optimization

This is a fine-tuned cross-encoder model based on cross-encoder/ms-marco-MiniLM-L6-v2, primarily used for text re-ranking and semantic search tasks.

PyLate is a sentence similarity model based on the ColBERT architecture, using Alibaba-NLP/gte-modernbert-base as the base model and trained with distillation loss, suitable for information retrieval tasks.

This is a cross-encoder model fine-tuned from ModernBERT-base for text re-ranking and semantic search tasks.

This is a fine-tuned BERT-based sentence transformer model for mapping sentences and paragraphs into a 768-dimensional vector space, supporting tasks such as semantic text similarity and semantic search.

This is a cross-encoder model fine-tuned from bert-tiny for computing similarity scores between text pairs, suitable for tasks like semantic textual similarity and semantic search.

rank1-32b is an information retrieval reranking model based on Qwen2.5-32B, which judges relevance by generating reasoning chains

rank1 is a 14-billion-parameter reasoning re-ranking model that improves the performance of information retrieval tasks by generating explicit reasoning chains before making relevance judgments.

A model specifically designed for Arabic reranking tasks, capable of accurately evaluating the relevance between queries and passages.

This is an Arabic re-ranking model based on the BERT architecture, optimized for Arabic text relevance ranking tasks

LLM2Vec is a simple method to convert decoder-only large language models into text encoders by enabling bidirectional attention, masked next-token prediction, and unsupervised contrastive learning.

Text ranking model based on Gemma 2B architecture, offering multiple quantization versions to suit different hardware needs

Ruri Reranker is a general-purpose Japanese reranking model based on the Sentence Transformers architecture, specifically designed for Japanese text relevance ranking tasks.

General-purpose Japanese reranking model for improving relevance ranking in Japanese text retrieval

Ruri Reranker is a Japanese text reranking model based on Transformer architecture, specifically designed to optimize the ranking quality of retrieval results.

Ruri-Reranker is a reranking model specifically optimized for Japanese text, based on the sentence-transformers architecture, effectively improving the relevance ranking of search results.

The Ruri Reranker is a general-purpose Japanese reranking model specifically designed to improve the relevance ranking of Japanese text retrieval results. The small version maintains high performance while having a smaller parameter count.

A text ranking model fine-tuned with Korean data based on BAAI/bge-reranker-v2-m3

This is a sentence-transformers model fine-tuned from dunzhang/stella_en_1.5B_v5, designed to generate 1024-dimensional dense vector representations for sentences and paragraphs, suitable for tasks like semantic text similarity and semantic search.

lightning-ir is a cross-encoder model based on the ELECTRA architecture, specifically designed for text ranking tasks. The model optimizes paragraph reordering performance through large language model distillation techniques.

This is a French cross-encoder model based on XLM-RoBERTa, specifically designed for passage re-ranking tasks in semantic search.

Venusaur is a sentence embedding model developed based on the Mihaiii/Bulbasaur foundation model, focusing on sentence similarity and feature extraction tasks.

This is a Japanese-trained Reranker (Cross-Encoder) model for text ranking tasks.

A T5 architecture-based sentence embedding model focused on semantic similarity and information retrieval tasks for English text.

A Czech sentence similarity model fine-tuned with SimCSE objective based on Seznam/small-e-czech model

GTE-small is a general text embedding model trained by Alibaba DAMO Academy, based on the BERT framework, suitable for tasks such as information retrieval and semantic text similarity.

GTE-small is a compact general-purpose text embedding model suitable for various natural language processing tasks, including sentence similarity calculation, text classification, and retrieval.

GTE-Base is a general-purpose text embedding model focused on sentence similarity and text retrieval tasks, performing well on multiple benchmarks.

INSTRUCTOR is a text embedding model based on the T5 architecture, focusing on sentence similarity calculation and information retrieval tasks. It excels in various NLP tasks, including text classification, clustering, and semantic similarity evaluation.

This model is used to predict the relevance of query-document pairs, suitable for information retrieval 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

This model is a dense retrieval model further fine-tuned on all Mr. TyDi training data based on the castorini/mdpr-tied-pft-msmarco checkpoint.

Dense retrieval model based on DistilBERT architecture, trained on the MS MARCO dataset with frozen word embedding layers

A retrieval model that converts documents into queries to enhance document search relevance

A text re-ranking model based on the T5-base architecture, fine-tuned on the MS MARCO passage dataset to improve the relevance ranking of information retrieval results.

This model is a pre-trained language model based on the DistilBERT architecture, initialized with a 256k vocabulary using word2vec and trained on the MS MARCO corpus with masked language modeling (MLM).

A re-ranker based on the T5-3B architecture, fine-tuned for 100,000 steps on the MS MARCO passage dataset for document ranking tasks.

A re-ranking model based on the T5-base architecture, fine-tuned for 100,000 steps on the MS MARCO passage dataset, suitable for document re-ranking tasks in information retrieval.

A sentence-transformers model fine-tuned on the MS-MARCO dataset based on PubMedBERT, suitable for semantic similarity calculation and information retrieval tasks in the medical/health text domain

A Persian sentence embedding model based on ParsBERT for generating high-quality sentence vector representations

A fine-tuned version based on the BERT-Base architecture for the MS MARCO passage classification task, suitable for document re-ranking tasks