CYFRAGOVPL/Llama-PLLuM-8B-instruct-2412

TEXT GENERATIONConcurrency Cost:1Model Size:8BQuant:FP8Ctx Length:32kTool Calling:SupportedPublished:Feb 7, 2025License:llama3.1Architecture:Transformer0.0K Cold

CYFRAGOVPL/Llama-PLLuM-8B-instruct-2412 is an 8 billion parameter instruction-tuned causal language model from the PLLuM family, developed by a consortium of Polish scientific institutions. Specialized in Polish and other Slavic/Baltic languages, it incorporates additional English data for generalization and excels in tasks relevant to Polish public administration. This model is fine-tuned using a unique Polish instruction dataset and preference corpus, achieving state-of-the-art results in Polish-language tasks.

Loading preview...

PLLuM: A Family of Polish Large Language Models

CYFRAGOVPL/Llama-PLLuM-8B-instruct-2412 is an 8 billion parameter instruction-tuned model from the PLLuM family, built upon Llama 3.1. Developed by a consortium of Polish scientific institutions, PLLuM models are specialized for Polish and other Slavic/Baltic languages, with English data for broader generalization. This model was formerly known as Llama-PLLuM-8B-instruct.

Key Capabilities

  • Extensive Polish Data: Pretrained on up to 150 billion tokens of high-quality Polish text, alongside Slavic, Baltic, and English data.
  • Organic Instruction Tuning: Refined using a unique, manually curated dataset of ~40k Polish "organic instructions" and ~3.5k multi-turn dialogues, designed to mitigate negative linguistic transfer.
  • Polish Preference Corpus: Aligned with the first Polish-language preference corpus, manually assessed for correctness, balance, and safety, especially for controversial topics.
  • Domain-Specific Excellence: Achieves top scores on custom benchmarks for tasks relevant to Polish public administration and state-of-the-art results in broader Polish-language tasks.
  • Retrieval Augmented Generation (RAG): Optimized for RAG settings, providing contextually relevant answers and citing sources from provided documents.

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 foundational model for AI applications requiring strong Polish language command.

Finetunes
1 models