# Information retrieval optimization

MiniCOIL is a sparse contextualized word-by-word embedding model specifically designed for efficient semantic similarity computation

PLaMo-Embedding-1B is a Japanese text embedding model developed by Preferred Networks, demonstrating outstanding performance in Japanese text embedding benchmarks

This is a cross-encoder model fine-tuned from ModernBERT-large, used to calculate the scores of text pairs, suitable for text re-ranking and semantic search tasks.

This is a Vietnamese text ranking model based on the Apache-2.0 license, primarily used for Vietnamese text ranking tasks.

Hypencoder is a hypernetwork model for information retrieval, consisting of a text encoder and Hypencoder. It can convert text into a small neural network and output relevance scores.

Hypencoder is a dual-encoder model for information retrieval, consisting of a text encoder and a hypernetwork (Hypencoder), capable of converting text into small neural networks for computing relevance scores.

A lightweight text ranking model suitable for information retrieval and document sorting tasks.

This model is a fine-tuned sentence embedding model based on ModernBERT-base, specifically designed for sentence similarity tasks and supports English text processing.

A high-performance Arabic information retrieval model built on the sentence-transformers framework, optimized for the richness and complexity of the Arabic language.

This is an Arabic reranking model based on the BERT architecture, specifically designed for Arabic text, performing reranking tasks by scoring and sorting text options.

This is a reranking model based on BAAI/bge-reranker-v2-m3 and further fine-tuned on a large-scale Polish text pair dataset, supporting long-context processing.

PhoRanker is a cross-encoder model for Vietnamese text ranking, capable of efficiently classifying and ranking Vietnamese texts.

A Norwegian sentence embedding model fine-tuned based on jina-embeddings-v2-base-en, focusing on keyword document search and sentence similarity tasks

This is a French cross-encoder model based on multilingual-e5-base, specifically designed for passage reranking tasks.

This is a French cross-encoder model specifically designed for passage re-ranking tasks in semantic search.

GTE-Large is a high-performance English text embedding model that excels in multiple text similarity and classification tasks.

SPLADE-v3-DistilBERT is the DistilBERT version of naver/splade-v3, which performs excellently in tasks such as information retrieval.

SPLADE-v3-Lexical is a term-weighted version of the SPLADE model, focusing on information retrieval tasks without expansion at the query end.

This is a Polish text ranking model trained using Mean Squared Error (MSE) distillation method, with a training dataset containing 1.4 million queries and 10 million document text pairs.

This is a Polish text ranking model trained using the RankNet loss function, with a training dataset consisting of 1.4 million queries and 10 million document pairs.

This is a lightweight Danish text ranking model adapted from the English MiniLM-L6 model, specifically designed for Danish information retrieval tasks.

A small Czech semantic embedding model fine-tuned with SimCSE objective based on RetroMAE-Small

MMLW (I Must Get Better Messages) is a neural text encoder for Polish, optimized for information retrieval tasks.

MMLW (I Must Get Better Messages) is a Polish neural text encoder optimized for information retrieval tasks, capable of converting queries and passages into 768-dimensional vectors.

Ember v1 is an embedding model based on sentence-transformers, primarily used for feature extraction and sentence similarity calculation.

bge_micro is a lightweight sentence similarity calculation model based on transformer architecture, specifically designed for efficient feature extraction and sentence similarity tasks.

BGE Base English v1.5 is a transformer-based sentence embedding model, specifically designed for extracting sentence features and calculating sentence similarity.

This is a French cross-encoder model based on CamemBERT, specifically designed for passage reranking tasks, demonstrating excellent performance on the mMARCO-fr dataset.

This is a dense single-vector dual-encoder model for French, suitable for semantic search tasks.

A sentence similarity calculation model based on the CompCSE dedicated dataset, suitable for English text processing.

INSTRUCTOR is a text embedding model based on the T5 architecture, focusing on sentence similarity calculation and text classification tasks, and supports English language processing.

This is a Portuguese sentence embedding model based on the DistilBERT architecture, specifically optimized for semantic similarity tasks.

This is a Portuguese sentence transformer model based on DistilBERT, specifically designed for sentence similarity and semantic search tasks.

A German cross-encoder model fine-tuned on the MMARCO dataset for query-passage relevance scoring

A T5-large reranker fine-tuned for 10,000 steps on the MS MARCO passage dataset, excelling on non-MS MARCO datasets

A reranker based on the T5-base architecture, fine-tuned for 10,000 steps on the MS MARCO passage dataset, with excellent zero-shot performance.

SGPT-2.7B is a sentence transformer model based on the weighted mean method, focusing on sentence similarity tasks, trained on the MSMARCO dataset with BitFit technology applied.