backdev007/llama-3.2-3b-legal-id-grpo

TEXT GENERATIONConcurrent Unit Cost:1Model Size:3.2BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Jul 23, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The backdev007/llama-3.2-3b-legal-id-grpo is a 3.2 billion parameter Llama model developed by backdev007, fine-tuned from backdev007/llama-3.2-3b-legal-id-instruct. This model was trained using Unsloth and Huggingface's TRL library, enabling 2x faster training. It is designed for specific applications within the legal domain, likely focusing on Indonesian legal identification or group-related tasks.

Loading preview...

Model Overview

The backdev007/llama-3.2-3b-legal-id-grpo is a 3.2 billion parameter Llama model, developed by backdev007. It is a fine-tuned version of the backdev007/llama-3.2-3b-legal-id-instruct model, indicating a specialization in legal identification or group-related tasks, particularly within an Indonesian context.

Key Characteristics

  • Architecture: Llama-based, with 3.2 billion parameters.
  • Training Efficiency: This model was trained with Unsloth and Huggingface's TRL library, resulting in a 2x speed improvement during the fine-tuning process.
  • Origin: Fine-tuned from a pre-existing instruction-tuned model, suggesting a focus on specific legal domain instructions.

Potential Use Cases

Given its name and fine-tuning origin, this model is likely suitable for:

  • Processing and understanding legal documents related to identification in Indonesia.
  • Tasks involving grouping or categorizing legal entities or information within the Indonesian legal framework.
  • Applications requiring specialized language understanding in the legal domain, potentially for information extraction or classification.