HuangYiYang/Llama-3-8B-Indonesian-Legal

TEXT GENERATIONConcurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:8kTool Calling:SupportedPublished:Jul 26, 2026License:apache-2.0Architecture:Transformer0.0K Open Weights Featherless Exclusive Cold

HuangYiYang/Llama-3-8B-Indonesian-Legal is an 8 billion parameter Llama-3 model developed by HuangYiYang, fine-tuned for Indonesian legal applications. This model leverages Unsloth for accelerated training and is designed for tasks requiring understanding and generation of Indonesian legal text. It offers a context length of 8192 tokens, making it suitable for processing substantial legal documents.

Loading preview...

Model Overview

HuangYiYang/Llama-3-8B-Indonesian-Legal is an 8 billion parameter language model developed by HuangYiYang. It is a specialized variant of the Llama-3 architecture, specifically fine-tuned for tasks within the Indonesian legal domain. The model was trained using Unsloth and Hugging Face's TRL library, which enabled a 2x faster fine-tuning process.

Key Capabilities

  • Indonesian Legal Text Processing: Optimized for understanding, analyzing, and generating content related to Indonesian legal frameworks and documents.
  • Efficient Training: Benefits from Unsloth's accelerated training techniques, indicating potential for efficient deployment and further adaptation.
  • Llama-3 Foundation: Inherits the robust capabilities of the Llama-3 base model, providing a strong foundation for complex language tasks.

Good For

  • Applications requiring specialized knowledge of Indonesian legal terminology and concepts.
  • Research and development in legal tech for the Indonesian market.
  • Tasks such as legal document summarization, question answering on legal texts, or generating legal drafts in Indonesian.

Finetunes
1 models