riskymanlael/indonesian-llama3-legal-finetuned

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

The riskymanlael/indonesian-llama3-legal-finetuned is an 8 billion parameter Llama 3 instruction-tuned causal language model, developed by riskymanlael. This model is specifically fine-tuned for legal applications in Indonesian, leveraging faster training with Unsloth and Huggingface's TRL library. It is optimized for tasks requiring legal understanding and generation within the Indonesian language context.

Loading preview...

Model Overview

This model, developed by riskymanlael, is an 8 billion parameter Llama 3 instruction-tuned causal language model. It has been specifically fine-tuned for legal applications, with a strong focus on the Indonesian language. The training process utilized Unsloth and Huggingface's TRL library, enabling faster fine-tuning from the unsloth/llama-3-8b-Instruct-bnb-4bit base model.

Key Capabilities

  • Indonesian Legal Context: Specialized in understanding and generating text related to legal topics in Indonesian.
  • Llama 3 Architecture: Benefits from the robust capabilities of the Llama 3 family of models.
  • Efficient Fine-tuning: Developed using Unsloth for accelerated training.

Good For

  • Applications requiring legal text processing in Indonesian.
  • Research and development of AI tools for the Indonesian legal sector.
  • Tasks involving legal document analysis, summarization, or generation in Indonesian.

Finetunes
1 models