CYFRAGOVPL/Llama-PLLuM-70B-chat-2508

TEXT GENERATIONConcurrency Cost:4Model Size:70BQuant:FP8Ctx Length:32kPublished:Aug 1, 2025License:llama3.1Architecture:Transformer0.0K Cold

CYFRAGOVPL/Llama-PLLuM-70B-chat-2508 is a 70 billion parameter Llama 3.1-based large language model developed by the HIVE AI Consortium, specializing in Polish and other Slavic/Baltic languages. It is instruction-tuned and aligned with human preferences, built on extensive Polish corpora (up to 150B tokens) and a unique organic instruction dataset. This model excels in general language tasks and is particularly optimized for applications within Polish public administration, achieving state-of-the-art results in relevant Polish-language benchmarks.

Loading preview...

PLLuM: A Family of Polish Large Language Models

CYFRAGOVPL/Llama-PLLuM-70B-chat-2508 is a 70 billion parameter model from the PLLuM family, developed by the HIVE AI Consortium (initially PLLuM consortium). This model is built upon the Llama 3.1 architecture and is specifically designed for Polish and other Slavic/Baltic languages, incorporating additional English data for broader generalization. It has been extensively refined through instruction tuning, preference learning, and advanced alignment techniques.

Key Capabilities

  • Polish Language Specialization: Trained on up to 150 billion tokens of high-quality Polish data, making it highly proficient in the language.
  • Organic Instruction Dataset: Utilizes a unique, manually curated dataset of ~55k Polish prompt-response pairs, including multi-turn dialogues, to enhance instruction following and mitigate negative linguistic transfer.
  • Polish Preference Corpus: Features the first Polish-language preference corpus, enabling the model to learn correctness, balance, and safety, especially for sensitive topics.
  • State-of-the-Art Performance: Achieves top scores in custom benchmarks relevant to Polish public administration and state-of-the-art results in broader Polish-language tasks.
  • Retrieval Augmented Generation (RAG): Specifically trained to perform well in RAG settings, providing context-aware answers with document citations.

Good For

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