rifyaldo/qwen2.5-3b-legal-id-sft

TEXT GENERATIONPricing:Input $0.32 / Cached $0.064 / Output $1.6Concurrent Unit Cost:1Model Size:3.1BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Jul 19, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

rifyaldo/qwen2.5-3b-legal-id-sft is a 3.1 billion parameter Qwen2.5 model, fine-tuned by rifyaldo, specifically optimized for legal tasks within the Indonesian context. This model leverages Unsloth for accelerated training and is designed to process legal information efficiently with a 32K context length. It aims to provide specialized capabilities for legal document analysis and generation in Indonesian.

Loading preview...

Model Overview

rifyaldo/qwen2.5-3b-legal-id-sft is a specialized language model, fine-tuned from the Qwen2.5-3B architecture, with 3.1 billion parameters and a 32,768 token context window. Developed by rifyaldo, this model is specifically adapted for legal applications in Indonesia.

Key Capabilities

  • Indonesian Legal Specialization: Fine-tuned to understand and generate content relevant to Indonesian legal frameworks and terminology.
  • Efficient Training: Utilizes Unsloth and Huggingface's TRL library, enabling 2x faster training compared to standard methods.
  • Qwen2.5 Base: Built upon the robust Qwen2.5 architecture, providing a strong foundation for language understanding and generation.

Good For

  • Legal Document Processing: Analyzing, summarizing, or generating legal texts specific to Indonesia.
  • Legal Research: Assisting with queries related to Indonesian law.
  • Specialized NLP Tasks: Applications requiring deep understanding of legal nuances in the Indonesian language.