# Long Document Processing

This is an INT4-quantized Mistral-Small-3.1-24B-Instruct-2503 model, optimized and released by Red Hat (Neural Magic), suitable for fast-response dialogue agents and low-latency inference scenarios.

BGE-M3 is a versatile, multilingual, multi-granularity embedding model that supports three common retrieval functions: dense retrieval, multi-vector retrieval, and sparse retrieval.

A government report summarization model based on the Long-T5 architecture, specifically optimized for long document summarization tasks

A multilingual BERT model further trained on legal documents, supporting Dutch and English legal text processing