SteuerLLM is a domain-adapted Large Language Model (LLM) consisting of 28 billion parameters, specifically designed for German tax law analysis. It was introduced in the paper SteuerLLM: Local specialized large language model for German tax law analysis. The model excels in domains governed by strict formal rules, precise terminology, and legally binding structures, such as tax law, where correct answers require exact statutory citation, structured legal argumentation, and numerical accuracy. — Paper: SteuerLLM: Local specialized large language model for German tax law analysis — GitHub Repository: https://github.com/windprak/steuerllm — Demo: https://steuerllm.i5.ai.fau.de/ SteuerLLM is based on an expanded Mistral Small architecture (extended from 24B to 28B parameters through a block expansion method). It was trained on a large-scale synthetic dataset generated from seed questions out of examination material using an automated retrieval-augmented pipeline (websearch). The training procedure follows a two-stage approach: 1. Continual Pretraining: The base model’s representations are adapted to tax-specific terminology and concepts by pretraining on domain-filtered web data. 2. …
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: windprak
Теги: mistral, conversational, de, text-generation-inference, endpoints_compatible
Лайков: 4 | Загрузок: 98
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
