ilyasrhmn/legal-qwen2.5-1.5b-grpo

TEXT GENERATIONConcurrent Unit Cost:1Model Size:1.5BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Jul 15, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The ilyasrhmn/legal-qwen2.5-1.5b-grpo is a 1.5 billion parameter Qwen2.5 model, developed by ilyasrhmn, and fine-tuned from ilyasrhmn/legal-qwen2.5-1.5b-sft. This model was trained using Unsloth and Huggingface's TRL library, enabling faster training. With a 32768 token context length, it is optimized for legal domain applications.

Loading preview...

Model Overview

The ilyasrhmn/legal-qwen2.5-1.5b-grpo is a 1.5 billion parameter Qwen2.5 model, developed by ilyasrhmn. It is a fine-tuned version of the ilyasrhmn/legal-qwen2.5-1.5b-sft model, specifically designed for legal applications.

Key Characteristics

  • Architecture: Based on the Qwen2.5 family of models.
  • Parameter Count: Features 1.5 billion parameters, offering a balance between performance and computational efficiency.
  • Context Length: Supports a substantial context window of 32768 tokens, suitable for processing lengthy legal documents.
  • Training Efficiency: This model was trained with Unsloth and Huggingface's TRL library, which facilitated a 2x faster training process.

Use Cases

This model is particularly well-suited for tasks within the legal domain, leveraging its specialized fine-tuning. Its large context window makes it capable of handling complex legal texts and inquiries.