dandyhi/Llama-3-8B-Indo-Legal-SFT

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

The dandyhi/Llama-3-8B-Indo-Legal-SFT is an 8 billion parameter Llama 3 instruction-tuned model, developed by dandyhi, specifically fine-tuned for Indonesian legal tasks. This model leverages Unsloth and Huggingface's TRL library for accelerated training, making it suitable for applications requiring specialized legal language processing in Indonesian. It offers a context length of 8192 tokens, focusing on domain-specific performance.

Loading preview...

Model Overview

The dandyhi/Llama-3-8B-Indo-Legal-SFT is an 8 billion parameter language model, fine-tuned from unsloth/llama-3-8b-Instruct-bnb-4bit. Developed by dandyhi, this model is specifically designed for tasks within the Indonesian legal domain. It utilizes the Unsloth library and Huggingface's TRL for efficient training, enabling faster fine-tuning processes.

Key Characteristics

  • Base Model: Llama 3 8B Instruct.
  • Domain Specialization: Fine-tuned for Indonesian legal contexts.
  • Training Efficiency: Leverages Unsloth for 2x faster training.
  • Context Length: Supports an 8192-token context window.

Use Cases

This model is particularly well-suited for applications requiring:

  • Processing and understanding Indonesian legal texts.
  • Assisting with legal research or document analysis in the Indonesian language.
  • Developing specialized AI tools for the Indonesian legal sector.

Finetunes
1 models