yanwarpro/Qwen2.5-Legal-SFT-GRPO-Dicoding-Final

TEXT GENERATIONConcurrent Unit Cost:1Model Size:1.5BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Jul 17, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

yanwarpro/Qwen2.5-Legal-SFT-GRPO-Dicoding-Final is a 1.5 billion parameter Qwen2.5 model developed by yanwarpro, fine-tuned for legal applications. This model was trained using Unsloth and Huggingface's TRL library, enabling 2x faster fine-tuning. It is designed to excel in legal-specific natural language processing tasks, building upon its predecessor, yanwarpro/Qwen2.5-Legal-SFT-Dicoding-Final.

Loading preview...

Model Overview

yanwarpro/Qwen2.5-Legal-SFT-GRPO-Dicoding-Final is a 1.5 billion parameter language model developed by yanwarpro. It is a fine-tuned variant of the Qwen2.5 architecture, specifically optimized for legal domain applications. This model builds upon the previously released yanwarpro/Qwen2.5-Legal-SFT-Dicoding-Final.

Key Characteristics

  • Architecture: Based on the Qwen2.5 model family.
  • Parameter Count: 1.5 billion parameters, offering a balance between performance and computational efficiency.
  • Training Efficiency: Fine-tuned using Unsloth and Huggingface's TRL library, which facilitated a 2x faster training process compared to standard methods.
  • Domain Specialization: Explicitly fine-tuned for legal tasks, suggesting enhanced performance in legal text analysis, understanding, and generation.

Intended Use Cases

This model is particularly well-suited for applications requiring specialized understanding of legal language and concepts. Potential use cases include:

  • Legal document summarization.
  • Legal information extraction.
  • Question answering within legal contexts.
  • Assisting with legal research and analysis.

Finetunes
1 models