CYFRAGOVPL/Llama-PLLuM-70B-instruct-2412
The CYFRAGOVPL/Llama-PLLuM-70B-instruct-2412 is a 70 billion parameter instruction-tuned large language model from the PLLuM family, developed by a consortium of Polish scientific institutions led by Politechnika Wrocławska. Based on Llama 3.1, it specializes in Polish and other Slavic/Baltic languages, with additional English data for generalization. This model excels at generating contextually coherent text, question answering, and summarization, particularly for tasks relevant to Polish public administration.
Loading preview...
PLLuM: Polish Large Language Models
CYFRAGOVPL/Llama-PLLuM-70B-instruct-2412 is a 70 billion parameter instruction-tuned model from the PLLuM family, built upon Llama 3.1. Developed by a consortium of Polish scientific institutions, PLLuM models are specialized for Polish and other Slavic/Baltic languages, incorporating English data for broader generalization. The project emphasizes high-quality data, including 150B Polish tokens (with 28B commercially open-source) and the largest Polish collection of manually created "organic instructions" (40k prompt-response pairs).
Key Capabilities
- Multilingual Proficiency: Strong command of Polish, other Slavic/Baltic languages, and English.
- Instruction Following: Refined with extensive instruction fine-tuning, including human-authored and synthetic instructions.
- Preference Learning: Aligned using the first Polish-language preference corpus for safety, balance, and contextual appropriateness.
- Domain-Specific Excellence: Achieves top scores on custom benchmarks for Polish public administration tasks.
- RAG Optimization: Designed to perform well in Retrieval Augmented Generation (RAG) settings, with a specific prompt format for document-based question answering.
Good For
- General Language Tasks: Text generation, summarization, and question answering in Polish.
- Domain-Specific Applications: Developing intelligent assistants for Polish public administration, legal, or bureaucratic topics.
- Research & Development: As a foundational model for AI applications requiring strong Polish language capabilities.