Rezware/llama3-legal-indonesia-finetuned

TEXT GENERATIONConcurrency Cost:1Model Size:3.2BQuant:BF16Ctx Length:32kTool Calling:SupportedPublished:Jun 11, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

Rezware/llama3-legal-indonesia-finetuned is a 3.2 billion parameter Llama 3-based instruction-tuned model developed by Rezware, fine-tuned for legal applications in Indonesia. This model leverages Unsloth and Huggingface's TRL library for accelerated training, making it suitable for tasks requiring specialized legal understanding within the Indonesian context. It offers a context length of 32768 tokens, optimized for processing extensive legal documents.

Loading preview...

Overview

Rezware/llama3-legal-indonesia-finetuned is a specialized language model based on the Llama 3 architecture, specifically the unsloth/Llama-3.2-3B-Instruct-bnb-4bit variant. Developed by Rezware, this model has been fine-tuned to excel in legal applications relevant to Indonesia.

Key Capabilities

  • Indonesian Legal Specialization: Optimized for understanding and generating text related to Indonesian legal contexts.
  • Efficient Training: Utilizes Unsloth and Huggingface's TRL library, enabling 2x faster training compared to standard methods.
  • Instruction-Tuned: Designed to follow instructions effectively, making it suitable for various task-oriented legal applications.
  • Large Context Window: Features a 32768-token context length, allowing for the processing of substantial legal documents and complex queries.

Good For

  • Legal Research: Assisting with queries and information extraction from Indonesian legal texts.
  • Document Analysis: Summarizing or analyzing legal documents specific to Indonesia.
  • Legal Q&A: Providing answers to legal questions within the Indonesian jurisdiction.
  • Application Development: Building applications that require a deep understanding of Indonesian legal language and concepts.

Finetunes
1 models