# Semantic Retrieval

Linq-Embed-Mistral is an embedding model based on the Mistral architecture, specializing in text classification, retrieval, and clustering tasks, with outstanding performance across multiple MTEB benchmarks.

Multilingual embedding model for German and English, supporting a context length of 8192 tokens

A lightweight sentence embedding model based on DistilBERT, suitable for various text processing tasks

This model is converted from BAAI/bge-m3 to GGUF format via llama.cpp, primarily used for sentence similarity computation and feature extraction.

This model is a sentence similarity model converted from BAAI/bge-m3 to GGUF format using llama.cpp via ggml.ai's GGUF-my-repo space.

A sentence embedding model based on the transformers library, used for generating vector representations of sentences, supporting text ranking tasks.

Provides quantized and non-quantized embedding models in GGUF format, specifically designed for llama.cpp. Significantly improves speed when running on CPUs, with moderate acceleration for large models on GPUs.

JaColBERT is the first Japanese-specific document retrieval model based on ColBERT, featuring strong out-of-domain generalization capabilities.

A sentence transformer model initialized from sentence-transformers/all-mpnet-base-v2, specifically designed for few-shot context example retrieval in the MultiWOZ dataset

This is a sentence transformer model based on DistilBERT, capable of mapping sentences and paragraphs into a 768-dimensional dense vector space, suitable for tasks such as clustering or semantic search.