hasyimas91/gemma-2-2b-legal-grpo

TEXT GENERATIONConcurrency Cost:1Model Size:2.6BQuant:BF16Ctx Length:8kPublished:Jun 16, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

The hasyimas91/gemma-2-2b-legal-grpo is a 2.6 billion parameter Gemma 2 model developed by hasyimas91. It is a finetuned version of hasyimas91/gemma-2-2b-legal-sft, specifically optimized for legal applications. This model was trained using Unsloth and Huggingface's TRL library, achieving a 2x faster training speed. Its primary strength lies in its specialized legal domain knowledge, making it suitable for tasks requiring legal understanding.

Loading preview...

Model Overview

The hasyimas91/gemma-2-2b-legal-grpo is a 2.6 billion parameter language model based on the Gemma 2 architecture. Developed by hasyimas91, this model is a finetuned iteration of the hasyimas91/gemma-2-2b-legal-sft base model, indicating a specialization in legal domain tasks.

Key Characteristics

  • Architecture: Gemma 2
  • Parameter Count: 2.6 billion
  • Training Efficiency: Utilizes Unsloth and Huggingface's TRL library, resulting in a 2x faster training process compared to standard methods.
  • Domain Specialization: Finetuned for legal applications, suggesting enhanced performance on legal texts and queries.
  • License: Apache-2.0

Intended Use Cases

This model is particularly well-suited for:

  • Processing and understanding legal documents.
  • Assisting with legal research and information extraction.
  • Applications requiring specialized knowledge of legal terminology and concepts.

Its optimized training process makes it an efficient choice for developers working on legal-centric AI solutions.