MarchelinoLumantow/legal-qwen-indonesian-finetuned
TEXT GENERATIONConcurrent Unit Cost:1Model Size:3.1BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Aug 5, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold
MarchelinoLumantow/legal-qwen-indonesian-finetuned is a 3.1 billion parameter Qwen2.5-3B-Instruct model, fine-tuned by MarchelinoLumantow. This model is specifically optimized for legal applications in Indonesian, leveraging faster training with Unsloth and Huggingface's TRL library. It is designed to process and generate content relevant to Indonesian legal contexts, offering specialized performance in this domain.
Loading preview...
Model Overview
MarchelinoLumantow/legal-qwen-indonesian-finetuned is a specialized language model based on the Qwen2.5-3B-Instruct architecture, developed by MarchelinoLumantow. This model, with 3.1 billion parameters, has been fine-tuned to excel in the domain of Indonesian legal text processing.
Key Capabilities
- Indonesian Legal Specialization: The model is specifically adapted for understanding and generating content related to Indonesian legal frameworks and terminology.
- Efficient Fine-tuning: It was fine-tuned using Unsloth and Huggingface's TRL library, enabling a 2x faster training process compared to standard methods.
- Qwen2.5-3B-Instruct Base: Built upon the robust Qwen2.5-3B-Instruct foundation, it inherits strong general language understanding and instruction-following capabilities.
Good For
- Legal Document Analysis: Tasks involving the interpretation or summarization of Indonesian legal documents.
- Legal Information Retrieval: Answering queries or extracting specific information from Indonesian legal texts.
- Specialized Content Generation: Creating or assisting in the generation of Indonesian legal-specific content.
- Applications requiring Indonesian legal context: Any use case where a deep understanding of Indonesian legal language is crucial.