adyuta447/llama-3.2-3b-legal-chatbot-id-grpo

TEXT GENERATIONPricing:Input $0.2036 / Output $1.34Concurrent Unit Cost:1Model Size:3.2BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Jul 29, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The adyuta447/llama-3.2-3b-legal-chatbot-id-grpo is a 3.2 billion parameter Llama-based model developed by adyuta447, fine-tuned for legal chatbot applications in Indonesian. It was trained using Unsloth and Huggingface's TRL library, enabling faster fine-tuning. This model is specifically designed to provide legal assistance and information within an Indonesian context, leveraging its specialized training for relevant tasks.

Loading preview...

Model Overview

The adyuta447/llama-3.2-3b-legal-chatbot-id-grpo is a 3.2 billion parameter Llama-based language model, developed by adyuta447. It is a fine-tuned version of the adyuta447/llama-3.2-3b-legal-chatbot-id model, specifically optimized for legal chatbot functionalities in the Indonesian language.

Key Characteristics

  • Architecture: Llama-based, with 3.2 billion parameters.
  • Fine-tuning: Enhanced using Unsloth and Huggingface's TRL library, which facilitated a 2x faster training process.
  • Specialization: Tailored for legal chatbot applications, focusing on providing relevant information and assistance within the legal domain.
  • Language: Primarily designed for Indonesian language processing.

Use Cases

This model is particularly well-suited for:

  • Developing AI-powered legal assistants or chatbots for Indonesian users.
  • Automating responses to common legal queries in Indonesia.
  • Applications requiring specialized legal language understanding and generation in Indonesian.

Finetunes
1 models