Rahmat15/qwen2.5-3b-indonesian-legal

TEXT GENERATIONConcurrent Unit Cost:1Model Size:3.1BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Jun 22, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

Rahmat15/qwen2.5-3b-indonesian-legal is a 3.1 billion parameter Qwen2.5 model developed by Rahmat15, fine-tuned for Indonesian legal applications. This model leverages Unsloth and Huggingface's TRL library for accelerated training. It is specifically optimized for tasks requiring understanding and generation of Indonesian legal text, offering a specialized solution for legal tech. With a 32K context length, it can process substantial legal documents.

Loading preview...

Model Overview

Rahmat15/qwen2.5-3b-indonesian-legal is a specialized large language model developed by Rahmat15. It is a 3.1 billion parameter Qwen2.5 model, fine-tuned specifically for the Indonesian legal domain. The model was trained using Unsloth and Huggingface's TRL library, which enabled faster training compared to conventional methods.

Key Capabilities

  • Indonesian Legal Text Processing: Optimized for understanding, analyzing, and generating content related to Indonesian legal documents and concepts.
  • Efficient Training: Benefits from Unsloth's accelerated training techniques, making it a resource-efficient model.
  • Qwen2.5 Architecture: Built upon the robust Qwen2.5 base model, providing strong foundational language understanding.

Good For

  • Legal Research: Assisting with queries and information extraction from Indonesian legal texts.
  • Document Analysis: Processing and summarizing legal documents in Indonesian.
  • Specialized Applications: Developing applications that require nuanced understanding of Indonesian legal language.

Finetunes
2 models