CYFRAGOVPL/PLLuM-12B-instruct-2512

TEXT GENERATIONConcurrency Cost:1Model Size:12BQuant:FP8Ctx Length:32kTool Calling:SupportedPublished:Jan 15, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

The CYFRAGOVPL/PLLuM-12B-instruct-2512 is a 12 billion parameter instruction-tuned causal language model developed by the PLLuM consortium and HIVE AI, based on Mistral-Nemo-Base-2407. This model is specialized in Polish, incorporating extensive high-quality Polish and English data, and is refined through instruction tuning and preference learning. It excels at generating contextually coherent Polish text and is particularly optimized for tasks relevant to Polish public administration and general Polish language applications.

Loading preview...

PLLuM-12B-instruct-2512: Polish Language Model

This model is part of the PLLuM family, a series of large language models (LLMs) developed by the PLLuM consortium and later by HIVE AI, with a strong focus on the Polish language. The PLLuM-12B-instruct-2512 is a 12 billion parameter instruction-tuned model built upon the Mistral-Nemo-Base-2407 architecture.

Key Highlights & Development

  • Extensive Data Collection: Trained on large-scale, high-quality Polish and English text data, rigorously cleaned and deduplicated.
  • Organic Instruction Dataset: Features the largest Polish collection of manually created "organic instructions" (approximately 70k), designed to cover subtle aspects of supervised fine-tuning and mitigate negative linguistic transfer.
  • Polish Preference Corpus: Utilizes the first Polish-language preference corpus (~60k manually annotated pairs) to enhance correctness, balance, and safety, especially for sensitive topics.
  • State-of-the-Art Performance: Achieves top scores on custom benchmarks relevant to Polish public administration and state-of-the-art results in broader Polish-language tasks.
  • Alignment: Aligned to human preferences for safer and more efficient use in dialogue and general-purpose scenarios.

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 requiring domain-aware retrieval.
  • Research & Development: Serves as a robust foundation for AI applications demanding strong command of the Polish language.

Finetunes
1 models