piik/Gemma-2-2B-Indonesian-Legal-SFT

TEXT GENERATIONConcurrent Unit Cost:1Model Size:2.6BQuant:BF16Context Size:8kPublished:Jul 17, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

piik/Gemma-2-2B-Indonesian-Legal-SFT is a 2.6 billion parameter Gemma-2 model developed by piik, fine-tuned for Indonesian legal text. This model leverages Unsloth for faster training and is specialized for tasks requiring understanding and generation of legal content in Indonesian. It offers an 8192-token context length, making it suitable for processing substantial legal documents.

Loading preview...

Model Overview

piik/Gemma-2-2B-Indonesian-Legal-SFT is a specialized language model developed by piik, built upon the Gemma-2 architecture with 2.6 billion parameters. It has been specifically fine-tuned for tasks involving Indonesian legal text, making it a targeted solution for legal domain applications.

Key Capabilities

  • Indonesian Legal Text Processing: Optimized for understanding and generating content related to Indonesian legal documents and terminology.
  • Efficient Training: The model was fine-tuned using Unsloth and Huggingface's TRL library, enabling 2x faster training compared to standard methods.
  • Context Length: Features an 8192-token context window, allowing it to process and analyze lengthy legal texts effectively.

Good For

  • Applications requiring the analysis or generation of Indonesian legal documents.
  • Developers seeking a specialized model for legal domain-specific NLP tasks in Indonesian.
  • Use cases where efficient processing of legal text with a substantial context window is crucial.