Timooody/qwen2-5-1-5b-legal-grpo

TEXT GENERATIONPricing:Input $0.04 / Cached $0.008 / Output $0.08Concurrent Unit Cost:1Model Size:1.5BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Sep 1, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

Timooody/qwen2-5-1-5b-legal-grpo is a 1.5 billion parameter Qwen2 model developed by Timooody, fine-tuned for legal applications. This model was trained using Unsloth and Huggingface's TRL library, enabling 2x faster training. It features a 32768 token context length, making it suitable for processing extensive legal documents and queries.

Loading preview...

Model Overview

Timooody/qwen2-5-1-5b-legal-grpo is a 1.5 billion parameter Qwen2 model, developed by Timooody and fine-tuned specifically for legal use cases. It builds upon the base model Timooody/qwen2-5-1-5b-legal-finetuned and leverages a substantial 32768 token context length, which is beneficial for handling lengthy legal texts and complex inquiries.

Key Training Details

  • Architecture: Qwen2
  • Parameters: 1.5 billion
  • Context Length: 32768 tokens
  • Training Efficiency: This model was trained with Unsloth and Huggingface's TRL library, resulting in a 2x speed improvement during the fine-tuning process.

Intended Use Cases

This model is designed for applications requiring advanced language understanding and generation within the legal domain. Its large context window makes it particularly well-suited for tasks such as:

  • Analyzing and summarizing legal documents.
  • Answering legal questions based on provided texts.
  • Assisting with legal research by processing extensive information.

Finetunes
5 models