johanes-andre/Llama-3-Indo-Legal-SFT
TEXT GENERATIONConcurrency Cost:1Model Size:3.2BQuant:BF16Ctx Length:32kPublished:Apr 27, 2026License:apache-2.0Architecture:Transformer Open Weights Cold
The johanes-andre/Llama-3-Indo-Legal-SFT is a 3.2 billion parameter Llama-3 based causal language model developed by johanes-andre. Fine-tuned using Unsloth and Huggingface's TRL library, this model is optimized for Indonesian legal tasks. It features a 32768 token context length, making it suitable for processing extensive legal documents and queries.
Loading preview...
Overview
The johanes-andre/Llama-3-Indo-Legal-SFT is a 3.2 billion parameter language model, developed by johanes-andre, specifically fine-tuned for Indonesian legal applications. It is based on the Llama-3 architecture and utilizes Unsloth and Huggingface's TRL library for efficient training, resulting in a 2x faster fine-tuning process.
Key Capabilities
- Indonesian Legal Domain Specialization: Optimized for understanding and generating text related to Indonesian legal contexts.
- Efficient Training: Leverages Unsloth for accelerated fine-tuning, making it a resource-efficient option.
- Extended Context Window: Supports a 32768 token context length, enabling the processing of lengthy legal documents and complex queries.
Good For
- Legal Research: Assisting with information retrieval and analysis within Indonesian legal texts.
- Document Processing: Handling and summarizing long legal documents relevant to the Indonesian jurisdiction.
- Legal Q&A: Providing responses to questions pertaining to Indonesian law and regulations.