# Long Text Support

Ruri v3 is a Japanese general-purpose text embedding model based on ModernBERT-Ja, supporting sequences up to 8192 tokens long and achieving state-of-the-art performance in Japanese text embedding tasks.

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

An improved Khmer text summarization model based on mT5-small, supporting inputs of up to 1024 tokens, suitable for summarizing Khmer articles, paragraphs, or documents.

INF-Retriever-v1-1.5B is a dense retrieval model based on large language models developed by INF TECH, optimized and fine-tuned for Chinese-English data retrieval tasks.

Snowflake Arctic-embed-l-v2.0 is the latest embedding model released by Snowflake, specifically designed for multilingual workloads, optimizing retrieval performance and inference efficiency.

The GGUF quantized version of Snowflake Arctic Embed L v2.0 is an efficient multilingual text embedding model, suitable for high-quality retrieval tasks.

Ruri is a Japanese universal text embedding model, focusing on sentence similarity calculation and feature extraction, with support for long text processing.

Ruri-Large is a high-performance embedding model specialized in Japanese text similarity calculation, based on transformer architecture with support for long text processing (maximum length 8192).

Ruri is a model specialized in Japanese text embedding, capable of efficiently calculating sentence similarity and extracting text features.

Ruri is a universal text embedding model for Japanese, focusing on sentence similarity and feature extraction tasks.

The first multilingual reranking model in the GTE series, supporting 70+ languages with high performance and long text processing capabilities.

This is the ONNX quantized version of the BAAI/bge-m3 model, supporting three functionalities: dense retrieval, multi-vector retrieval, and sparse retrieval, covering over 100 languages.

Chinese-LLaMA-2-7B is an extended Chinese version of Meta's Llama-2 model, optimized with an expanded Chinese vocabulary and incremental pre-training to enhance Chinese comprehension.

This is a multilingual, long-text (supports up to 16k input tokens) abstractive summarization model. Trained on the sumstew dataset, it can generate titles and summaries for given input documents.

PEGASUS is a pretrained model based on gap sentence extraction, specifically designed for abstractive text summarization tasks.