daudisa114/Llama-3-8B-Indo-Legal

TEXT GENERATIONConcurrency Cost:1Model Size:8BQuant:FP8Ctx Length:8kTool Calling:SupportedPublished:Jun 1, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

The daudisa114/Llama-3-8B-Indo-Legal is an 8 billion parameter Llama-3 model, fine-tuned by daudisa114, specifically optimized for Indonesian legal applications. This model was trained using Unsloth and Huggingface's TRL library, enabling faster fine-tuning. It is designed to provide specialized language understanding and generation capabilities within the Indonesian legal domain, leveraging its Llama-3 architecture and 8192 token context length.

Loading preview...

Model Overview

The daudisa114/Llama-3-8B-Indo-Legal is an 8 billion parameter language model, fine-tuned by daudisa114, based on the Llama-3 architecture. This model is specifically tailored for applications within the Indonesian legal domain, indicating a specialization in processing and generating content relevant to Indonesian law.

Key Characteristics

  • Base Model: Fine-tuned from unsloth/llama-3-8b-Instruct-bnb-4bit.
  • Parameter Count: 8 billion parameters, offering a balance between performance and computational efficiency.
  • Training Efficiency: The fine-tuning process was accelerated using Unsloth and Huggingface's TRL library, enabling faster iteration and development.
  • Context Length: Supports an 8192-token context window, suitable for handling moderately long legal documents or queries.

Good For

  • Indonesian Legal Text Processing: Ideal for tasks requiring an understanding of Indonesian legal terminology, structures, and concepts.
  • Specialized Language Generation: Can be used to generate legal summaries, draft legal documents, or answer legal questions specific to the Indonesian context.
  • Research and Development: Provides a specialized base for further research or application development in Indonesian legal AI.