# High recall rate

This model is a fine-tuned version based on bert-base-uncased, focusing on improving recall performance for specific tasks

A baby cry classification model fine-tuned based on wav2vec2-large-xlsr-53-english, achieving 81.5% accuracy

Marqo-FashionSigLIP is a multimodal embedding model optimized for fashion product search, with a 57% improvement in MRR and recall rate compared to FashionCLIP.

SPLADEv2 model based on Camembert architecture, optimized for French paragraph retrieval and sentence similarity tasks

A French sentence similarity calculation model based on CamemBERT, optimized for legal domain paragraph retrieval 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.

A Russian and English spelling correction model based on the mT5-large architecture, normalizing words to correct spelling and typographical errors.

Solon embeddings base version 0.1 is the most advanced open-source French embedding model, supporting both French and English, specializing in sentence similarity and feature extraction tasks.

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 French cross-encoder model for scoring the relevance of question-passage pairs, suitable for the reranking stage in semantic search.

This is a French cross-encoder model based on the ELECTRA architecture, specifically designed for passage reranking tasks in semantic search.

This is a dense single-vector dual-encoder model for French, suitable for semantic search. The model maps queries and passages to 384-dimensional dense vectors and calculates relevance through cosine similarity.

This is a dense single-vector dual-encoder model for French, designed for semantic search. The model maps queries and passages to 768-dimensional dense vectors and calculates relevance through cosine similarity.

This is a dense single-vector dual encoder model for French, suitable for semantic search. The model maps queries and passages to 768-dimensional dense vectors and calculates relevance through cosine similarity.

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

This model is a RoBERTa model pre-trained on Twitter data, fine-tuned on the tner/tweetner7 dataset for named entity recognition in tweets.

A named entity recognition model fine-tuned on the TweetNER7 dataset based on the Twitter-RoBERTa model, specifically designed for entity recognition in tweets.

A French DPR model based on CamemBERT, optimized for French Q&A tasks, fine-tuned on PIAF, FQuAD, and SQuAD-FR datasets