Ridhsaid3/Llama-3-8B-Indo-Legal-SFT

Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:8BQuant:FP8Ctx Length:8kPublished:May 21, 2026License:apache-2.0Architecture:Transformer0.0K Open Weights Warm

Ridhsaid3/Llama-3-8B-Indo-Legal-SFT is an 8 billion parameter Llama-3 instruction-tuned model developed by Ridhsaid3. It is fine-tuned from unsloth/llama-3-8b-Instruct-bnb-4bit and optimized for specific applications, leveraging Unsloth and Huggingface's TRL library for faster training. This model is designed for tasks requiring specialized legal domain understanding within an Indonesian context.

Loading preview...

Ridhsaid3/Llama-3-8B-Indo-Legal-SFT Overview

This model is an 8 billion parameter Llama-3 based instruction-tuned language model, developed by Ridhsaid3. It was fine-tuned from the unsloth/llama-3-8b-Instruct-bnb-4bit base model, utilizing the Unsloth library and Huggingface's TRL for accelerated training.

Key Characteristics

  • Architecture: Llama-3 8B instruction-tuned.
  • Developer: Ridhsaid3.
  • Training Optimization: Leverages Unsloth for 2x faster fine-tuning.
  • License: Apache-2.0.

Intended Use Cases

This model is specifically designed for applications requiring legal domain understanding, particularly within an Indonesian context. Its fine-tuning process suggests an emphasis on specialized knowledge and instruction following for legal tasks.

Finetunes
1 models