maoelana/legal-qwen-2.5-1.5b-baseline

TEXT GENERATIONPricing:Input $0.04 / Cached $0.008 / Output $0.08Concurrent Unit Cost:1Model Size:1.5BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Sep 7, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The maoelana/legal-qwen-2.5-1.5b-baseline is a 1.5 billion parameter Qwen2.5 model developed by maoelana, fine-tuned for legal applications. This model was trained using Unsloth and Huggingface's TRL library, enabling faster fine-tuning. With a 32768 token context length, it is designed for efficient processing of extensive legal texts. Its specialized training makes it suitable for tasks requiring understanding and generation within the legal domain.

Loading preview...

Model Overview

The maoelana/legal-qwen-2.5-1.5b-baseline is a 1.5 billion parameter language model based on the Qwen2.5 architecture, developed by maoelana. It has been specifically fine-tuned for legal applications, leveraging the Unsloth framework and Huggingface's TRL library for accelerated training.

Key Characteristics

  • Architecture: Qwen2.5
  • Parameters: 1.5 billion
  • Context Length: 32768 tokens, suitable for processing lengthy documents.
  • Training Method: Fine-tuned using Unsloth and Huggingface's TRL library, which facilitates faster training.
  • License: Apache-2.0

Use Cases

This model is particularly well-suited for tasks within the legal domain due to its specialized fine-tuning. Potential applications include:

  • Legal document analysis and summarization.
  • Question answering on legal texts.
  • Assisting with legal research by processing and understanding complex legal language.

Finetunes
1 models