hasyimas91/gemma-2-2b-legal-sft

TEXT GENERATIONConcurrency Cost:1Model Size:2.6BQuant:BF16Ctx Length:8kPublished:Jun 14, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

The hasyimas91/gemma-2-2b-legal-sft is a 2.6 billion parameter Gemma 2 model, fine-tuned by hasyimas91, specifically optimized for legal-related tasks. This instruction-tuned model leverages Unsloth and Huggingface's TRL library for efficient training, making it suitable for applications requiring specialized legal language understanding and generation. It offers an 8192-token context length, enhancing its ability to process longer legal documents.

Loading preview...

Model Overview

The hasyimas91/gemma-2-2b-legal-sft is a specialized language model based on the Gemma 2 architecture, featuring 2.6 billion parameters and an 8192-token context length. Developed by hasyimas91, this model has been instruction-tuned to excel in tasks within the legal domain.

Key Characteristics

  • Architecture: Built upon the Gemma 2 foundation model.
  • Parameter Count: 2.6 billion parameters, offering a balance between performance and computational efficiency.
  • Context Length: Supports an 8192-token context, beneficial for processing extensive legal texts.
  • Training Efficiency: Fine-tuned using Unsloth and Huggingface's TRL library, enabling faster training times.
  • License: Distributed under the Apache-2.0 license.

Primary Use Case

This model is specifically designed for applications requiring a deep understanding and generation of legal language. Its fine-tuning targets legal-specific instruction following, making it a strong candidate for tasks such as legal document analysis, summarization, question answering in legal contexts, and generating legal-compliant text.