favjiw/Llama-3-8B-Instruct-Indonesian-Legal

TEXT GENERATIONPricing:Input $0.37 / Cached $0.074 / Output $0.38Concurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:8kTool Calling:SupportedPublished:Jul 25, 2026License:apache-2.0Architecture:Transformer0.0K Open Weights Featherless Exclusive Cold

favjiw/Llama-3-8B-Instruct-Indonesian-Legal is an 8 billion parameter Llama-3 instruction-tuned model developed by favjiw. This model is specifically fine-tuned for Indonesian legal contexts, leveraging the Llama-3 architecture. It was trained using Unsloth and Huggingface's TRL library, optimizing for faster training. Its primary strength lies in processing and generating content relevant to Indonesian legal language and concepts.

Loading preview...

Model Overview

favjiw/Llama-3-8B-Instruct-Indonesian-Legal is an 8 billion parameter instruction-tuned model based on the Llama-3 architecture. Developed by favjiw, this model is specifically fine-tuned to understand and generate content within the Indonesian legal domain. It was trained efficiently using Unsloth and Huggingface's TRL library, which facilitated a faster training process.

Key Capabilities

  • Specialized for Indonesian Legal Contexts: The model's fine-tuning focuses on legal language and concepts specific to Indonesia.
  • Llama-3 Architecture: Benefits from the robust base capabilities of the Llama-3 model family.
  • Efficient Training: Utilized Unsloth for optimized and accelerated training.

Good For

  • Applications requiring natural language understanding and generation in Indonesian legal settings.
  • Tasks involving legal document analysis, summarization, or question-answering within the Indonesian legal framework.
  • Developers looking for a specialized Llama-3 variant for Indonesian legal use cases.

Finetunes
2 models