piik/Qwen-2.5-3B-Indonesian-Legal-GPRO

TEXT GENERATIONPricing:Input $0.32 / Cached $0.064 / Output $1.6Concurrent Unit Cost:1Model Size:3.1BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Jul 18, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The piik/Qwen-2.5-3B-Indonesian-Legal-GPRO is a 3.1 billion parameter Qwen2 model developed by piik, fine-tuned for Indonesian legal text. This model was trained using Unsloth and Huggingface's TRL library, enabling faster fine-tuning. It is designed for applications requiring specialized understanding and generation of Indonesian legal content, building upon the piik/Qwen-2.5-3B-Indonesian-Legal-SFT base model.

Loading preview...

Model Overview

The piik/Qwen-2.5-3B-Indonesian-Legal-GPRO is a specialized Qwen2 model with 3.1 billion parameters, developed by piik. It is specifically fine-tuned for processing and generating content related to Indonesian legal texts. This model builds upon the piik/Qwen-2.5-3B-Indonesian-Legal-SFT base model, enhancing its capabilities within the legal domain.

Key Characteristics

  • Architecture: Based on the Qwen2 model family.
  • Parameter Count: 3.1 billion parameters, offering a balance between performance and computational efficiency.
  • Domain Specialization: Explicitly fine-tuned for Indonesian legal language, making it suitable for tasks requiring deep understanding of legal terminology and context in Indonesian.
  • Training Efficiency: The model was fine-tuned using Unsloth and Huggingface's TRL library, which facilitated a 2x faster training process.

Use Cases

This model is particularly well-suited for applications in the Indonesian legal sector, including but not limited to:

  • Legal document analysis and summarization.
  • Generating legal drafts or responses in Indonesian.
  • Assisting with legal research by understanding and extracting information from Indonesian legal texts.
  • Developing chatbots or virtual assistants specialized in Indonesian legal queries.