CYFRAGOVPL/Llama-PLLuM-8B-base
CYFRAGOVPL/Llama-PLLuM-8B-base is an 8 billion parameter base model from the PLLuM family, specialized in Polish and other Slavic/Baltic languages, built upon the Llama 3.1 architecture. Developed by a consortium of Polish scientific institutions, it was pretrained on extensive high-quality Polish text data (up to 150B tokens) and additional multilingual data. This model excels in generating contextually coherent text in Polish and serves as a foundation for specialized applications, particularly in public administration tasks where it achieves top scores.
Loading preview...
PLLuM: A Family of Polish Large Language Models
CYFRAGOVPL/Llama-PLLuM-8B-base is an 8 billion parameter base model from the PLLuM family, developed by a consortium of Polish scientific institutions. It is built on the Llama 3.1 architecture and is specifically designed for Polish and other Slavic/Baltic languages, with additional English data for broader generalization. The model was pretrained on large-scale, high-quality Polish text data (up to 150 billion tokens, with 28 billion tokens available for fully open-source commercial use).
Key Capabilities
- Polish Language Specialization: Optimized for generating contextually coherent text in Polish, leveraging extensive Polish corpora.
- Multilingual Foundation: Includes data from Slavic, Baltic, and English languages for enhanced generalization.
- High-Quality Training Data: Benefits from extensive data collection, including a significant volume of Polish text.
- Base Model: Serves as a foundational model for further fine-tuning and specialized applications.
Good For
- General Language Tasks: Ideal for text generation, summarization, and question answering in Polish.
- Domain-Specific Assistants: Particularly effective as a building block for applications requiring strong command of Polish, such as those in public administration.
- Research & Development: Suitable for academic and industrial projects focused on Polish language processing.