CYFRAGOVPL/Llama-PLLuM-8B-base-2512

TEXT GENERATIONConcurrency Cost:1Model Size:8BQuant:FP8Ctx Length:32kTool Calling:SupportedPublished:Jan 15, 2026License:llama3.1Architecture:Transformer Cold

CYFRAGOVPL/Llama-PLLuM-8B-base-2512 is an 8 billion parameter base model from the PLLuM family, developed by the PLLuM consortium and HIVE AI, specialized in Polish with additional English data. It is built upon the Llama-3.1-8B architecture and is designed to generate contextually coherent text and serve as a foundation for specialized applications, particularly excelling in tasks relevant to Polish public administration and broader Polish-language tasks.

Loading preview...

PLLuM: Polish Large Language Models

CYFRAGOVPL/Llama-PLLuM-8B-base-2512 is an 8 billion parameter base model within the PLLuM family, developed by the PLLuM consortium and HIVE AI. This model is built on the Llama-3.1-8B architecture and is specifically optimized for the Polish language, incorporating additional English data for enhanced generalization. The PLLuM models are distinguished by their extensive, high-quality Polish and English text data collection, rigorous cleaning, and deduplication processes.

Key Capabilities

  • Specialized Polish Data: Trained on large-scale, high-quality Polish corpora, ensuring strong performance in Polish-language tasks.
  • Organic Instruction Dataset: Utilizes a unique, manually curated Polish instruction set for supervised fine-tuning, designed to mitigate negative linguistic transfer.
  • Polish Preference Corpus: Benefits from the first Polish-language preference corpus, manually assessed for correctness, balance, and safety, especially for sensitive topics.
  • Public Administration Focus: Achieves top scores on custom benchmarks relevant to Polish public administration, making it highly suitable for government services and bureaucratic topics.
  • RAG Optimization: Post-trained to perform effectively in Retrieval-Augmented Generation (RAG) settings, with a specific prompt format provided for document-based question answering.

Good for

  • General Language Tasks: Text generation, summarization, extraction, and question answering in Polish.
  • Domain-Specific Assistants: Particularly effective for applications within Polish public administration, legal, or bureaucratic sectors.
  • Research & Development: Serving as a robust foundation for AI applications requiring strong Polish language capabilities.

Finetunes
1 models