SyahrulApr86/qwen2.5-3b-legal-chatbot-id

TEXT GENERATIONConcurrent Unit Cost:1Model Size:3.1BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Jul 10, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The SyahrulApr86/qwen2.5-3b-legal-chatbot-id is a 3.1 billion parameter Qwen2.5-based causal language model, fine-tuned by SyahrulApr86. This model was optimized using Unsloth and Huggingface's TRL library for faster training. With a context length of 32768 tokens, it is specifically designed for legal chatbot applications in Indonesian.

Loading preview...

Model Overview

The SyahrulApr86/qwen2.5-3b-legal-chatbot-id is a specialized 3.1 billion parameter language model, fine-tuned from the unsloth/qwen2.5-3b-instruct-bnb-4bit base model. Developed by SyahrulApr86, this model leverages the Qwen2.5 architecture and boasts a substantial context length of 32768 tokens, making it suitable for processing lengthy legal documents or conversations.

Key Capabilities

  • Legal Chatbot Focus: Specifically fine-tuned for applications within the legal domain, likely for tasks such as answering legal queries, summarizing legal texts, or assisting with legal research.
  • Indonesian Language Support: The model's name suggests a focus on the Indonesian language, indicating its utility for legal contexts in Indonesia.
  • Optimized Training: The fine-tuning process utilized Unsloth and Huggingface's TRL library, which enabled a 2x faster training speed. This optimization suggests efficiency in model development and potential for further rapid iteration.

Good For

  • Developing AI-powered legal assistants or chatbots for the Indonesian market.
  • Applications requiring the processing and understanding of legal documents in Indonesian.
  • Use cases where a balance between model size (3.1B parameters) and performance in a specialized domain is crucial.