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

TEXT GENERATIONConcurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:8kTool Calling:SupportedPublished:Jun 22, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The dandyhi/Llama-3-8B-Indo-Legal-GRPO is an 8 billion parameter Llama 3 model developed by dandyhi, fine-tuned from dandyhi/Llama-3-8B-Indo-Legal-SFT. This model was trained using Unsloth and Huggingface's TRL library, enabling 2x faster training. It is specifically optimized for Indonesian legal applications, leveraging its specialized fine-tuning for this domain.

Loading preview...

Model Overview

The dandyhi/Llama-3-8B-Indo-Legal-GRPO is an 8 billion parameter Llama 3 model, developed by dandyhi. It is a fine-tuned version of the dandyhi/Llama-3-8B-Indo-Legal-SFT base model, specifically adapted for the Indonesian legal domain.

Key Characteristics

  • Architecture: Llama 3, 8 billion parameters.
  • Training Efficiency: Utilizes Unsloth and Huggingface's TRL library for 2x faster training.
  • Specialization: Fine-tuned for Indonesian legal applications, indicating a focus on legal text understanding and generation within this specific context.
  • License: Released under the Apache-2.0 license.

Use Cases

This model is particularly well-suited for tasks requiring an understanding of Indonesian legal language and concepts. Potential applications include:

  • Legal Document Analysis: Processing and interpreting Indonesian legal texts.
  • Legal Information Retrieval: Assisting in finding relevant information within Indonesian legal databases.
  • Legal Text Generation: Generating or summarizing legal content in Indonesian.

Developers seeking a specialized language model for Indonesian legal use cases will find this model highly relevant due to its targeted fine-tuning.

Finetunes
1 models