attanmhd/qwen-2.5-1.5b-indonesian-legal-sft-grpo

TEXT GENERATIONConcurrent Unit Cost:1Model Size:1.5BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Jul 10, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The attanmhd/qwen-2.5-1.5b-indonesian-legal-sft-grpo model is a Qwen2-based language model developed by attanmhd, specifically fine-tuned for Indonesian legal applications. This model is an optimized version of attanmhd/qwen-2.5-1.5b-indonesian-legal-sft, trained using Unsloth and Huggingface's TRL library for faster processing. It is designed to excel in tasks requiring understanding and generation of Indonesian legal text.

Loading preview...

Overview

The attanmhd/qwen-2.5-1.5b-indonesian-legal-sft-grpo model is a specialized language model developed by attanmhd. It is built upon the Qwen2 architecture and has been fine-tuned specifically for processing Indonesian legal text. This model represents an enhanced iteration of the attanmhd/qwen-2.5-1.5b-indonesian-legal-sft base model.

Key Capabilities

  • Indonesian Legal Text Processing: Optimized for tasks involving legal documents and language specific to Indonesia.
  • Efficient Training: Leverages Unsloth and Huggingface's TRL library, enabling 2x faster training compared to conventional methods.
  • Qwen2 Architecture: Benefits from the robust capabilities of the Qwen2 model family.

Good For

  • Applications requiring analysis or generation of Indonesian legal content.
  • Researchers and developers working on legal tech solutions for the Indonesian market.
  • Use cases where efficient fine-tuning and deployment of legal-specific LLMs are critical.

Finetunes
1 models