ekoandriprasetyo/legal-chatbot-indonesia-qwen-0.5b

Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:0.5BQuant:BF16Ctx Length:32kPublished:May 20, 2026License:apache-2.0Architecture:Transformer Open Weights Warm

The ekoandriprasetyo/legal-chatbot-indonesia-qwen-0.5b is a 0.5 billion parameter Qwen2.5-based instruction-tuned causal language model developed by ekoandriprasetyo. This model is specifically fine-tuned for legal chatbot applications in Indonesia, leveraging the Qwen2.5 architecture for efficient performance. It was trained using Unsloth and Huggingface's TRL library, offering a context length of 32768 tokens. Its primary strength lies in providing relevant responses for Indonesian legal queries.

Loading preview...

Model Overview

The ekoandriprasetyo/legal-chatbot-indonesia-qwen-0.5b is a specialized language model developed by ekoandriprasetyo. It is a 0.5 billion parameter model, fine-tuned from unsloth/Qwen2.5-0.5B-Instruct-bnb-4bit, and built upon the Qwen2.5 architecture. This model was trained using the Unsloth framework in conjunction with Huggingface's TRL library, which facilitated a faster training process.

Key Capabilities

  • Indonesian Legal Context: Specifically adapted and fine-tuned for understanding and generating responses related to Indonesian legal information.
  • Efficient Performance: Based on the Qwen2.5-0.5B architecture, it offers a balance of performance and resource efficiency, suitable for chatbot applications.
  • Extended Context Window: Supports a context length of 32768 tokens, allowing for processing longer legal documents or complex queries.

Good For

  • Developing legal chatbots tailored for the Indonesian context.
  • Applications requiring quick and relevant answers to Indonesian legal questions.
  • Use cases where a smaller, specialized model is preferred over larger, general-purpose LLMs for efficiency and domain specificity.