kyyril/Qwen2.5-1.5B-legal-id-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 kyyril/Qwen2.5-1.5B-legal-id-grpo is a 1.5 billion parameter Qwen2-based language model developed by kyyril, fine-tuned for legal identification tasks in Indonesian. This model was efficiently trained using Unsloth and Huggingface's TRL library, building upon the kyyril/Qwen2.5-1.5B-legal-id-finetuned base. It is designed for specialized applications requiring fast and accurate processing of legal identification data.

Loading preview...

Model Overview

The kyyril/Qwen2.5-1.5B-legal-id-grpo is a specialized 1.5 billion parameter language model based on the Qwen2 architecture. Developed by kyyril, this model is a fine-tuned version of kyyril/Qwen2.5-1.5B-legal-id-finetuned, specifically optimized for tasks related to legal identification within the Indonesian context.

Key Characteristics

  • Architecture: Qwen2-based, providing a robust foundation for language understanding.
  • Parameter Count: Features 1.5 billion parameters, balancing performance with computational efficiency.
  • Training Efficiency: The model was trained with enhanced speed using Unsloth and Huggingface's TRL library, indicating an optimized training process.
  • Specialization: Fine-tuned for legal identification tasks, suggesting proficiency in processing and understanding legal documents or data related to identity in Indonesia.

Use Cases

This model is particularly well-suited for applications requiring:

  • Indonesian Legal Document Analysis: Processing and extracting information from legal texts in Indonesian.
  • Identity Verification: Tasks involving the identification and verification of legal entities or individuals based on textual data.
  • Specialized NLP: Any natural language processing tasks that benefit from a model specifically trained on legal identification data in the Indonesian language.