CYFRAGOVPL/Llama-PLLuM-8B-chat-2512
The CYFRAGOVPL/Llama-PLLuM-8B-chat-2512 is an 8 billion parameter large language model from the PLLuM family, developed by the PLLuM consortium and continued by HIVE AI. Specialized in Polish, it incorporates English data for broader generalization and is built upon the Llama-3.1-8B architecture. This chat-aligned model excels in generating contextually coherent Polish text, question answering, and summarization, with particular strength in tasks relevant to Polish public administration.
Loading preview...
PLLuM: A Family of Polish Large Language Models
CYFRAGOVPL/Llama-PLLuM-8B-chat-2512 is an 8 billion parameter model from the PLLuM family, developed by the PLLuM consortium and continued by HIVE AI. This model is built upon the Llama-3.1-8B base and is specifically aligned for chat and general-purpose scenarios, emphasizing safety and efficiency. It is part of a broader initiative focused on open language technologies for Polish public administration.
Key Capabilities & Differentiators
- Polish Language Specialization: Developed with extensive, high-quality Polish text data, complemented by English data for generalization.
- Organic Instruction Dataset: Fine-tuned using a large, manually curated set of "organic instructions" in Polish, designed to cover nuanced human-model interactions and mitigate negative linguistic transfer.
- Polish Preference Corpus: Leverages the first Polish-language preference corpus, manually assessed for correctness, balance, and safety, particularly for sensitive topics.
- Public Administration Expertise: Achieves top scores on custom benchmarks relevant to Polish public administration tasks and state-of-the-art results in broader Polish-language tasks.
- Retrieval Augmented Generation (RAG) Optimized: Post-trained to perform effectively in RAG settings, providing document-cited answers and indicating when information is not found.
Intended Use Cases
- General Language Tasks: Ideal for text generation, summarization, extraction, and question answering in Polish.
- Domain-Specific Assistants: Particularly effective for applications within Polish public administration, legal, or bureaucratic contexts.
- Research & Development: Serves as a robust foundation for AI applications requiring strong Polish language command in academic or industrial settings.