jaglul/legal-chatbot-qwen2.5-1.5b-indonesian

TEXT GENERATIONPricing:Input $0.04 / Cached $0.008 / Output $0.08Concurrent Unit Cost:1Model Size:1.5BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Sep 6, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The jaglul/legal-chatbot-qwen2.5-1.5b-indonesian is a 1.5 billion parameter Qwen2.5 model developed by jaglul, fine-tuned for Indonesian legal chatbot applications. This model leverages Unsloth and Huggingface's TRL library for accelerated training. It is designed to provide specialized responses within the legal domain in Indonesian, building upon the Qwen2.5 architecture with a 32768 token context length.

Loading preview...

Model Overview

The jaglul/legal-chatbot-qwen2.5-1.5b-indonesian is a specialized language model developed by jaglul, fine-tuned for Indonesian legal chatbot applications. It is based on the Qwen2.5-1.5B-Instruct architecture, featuring 1.5 billion parameters and a substantial 32768 token context length.

Key Characteristics

  • Specialized Domain: Specifically trained for legal contexts in the Indonesian language.
  • Efficient Training: Utilizes Unsloth and Huggingface's TRL library, enabling 2x faster fine-tuning.
  • Base Model: Finetuned from unsloth/Qwen2.5-1.5B-Instruct-bnb-4bit, inheriting its robust base capabilities.

Use Cases

This model is particularly well-suited for:

  • Legal Information Retrieval: Answering questions related to Indonesian law.
  • Legal Chatbots: Developing conversational AI agents for legal assistance in Indonesia.
  • Document Analysis: Potentially assisting with understanding and summarizing Indonesian legal texts.

Limitations

As a specialized model, its performance outside the Indonesian legal domain may be limited. Users should evaluate its suitability for tasks beyond its intended scope.

Finetunes
1 models