nouvallr/qwen2_5_legal_ft

TEXT GENERATIONConcurrency Cost:1Model Size:1.5BQuant:BF16Ctx Length:32kTool Calling:SupportedPublished:Jun 6, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

The nouvallr/qwen2_5_legal_ft is a 1.5 billion parameter Qwen2.5-based instruction-tuned language model, fine-tuned by nouvallr. It was optimized for faster training using Unsloth and Huggingface's TRL library, offering a 32768 token context length. This model is specifically adapted for legal applications, leveraging its efficient fine-tuning process to handle specialized legal text.

Loading preview...

nouvallr/qwen2_5_legal_ft: A Legal-Focused Qwen2.5 Model

The nouvallr/qwen2_5_legal_ft is a 1.5 billion parameter language model, fine-tuned by nouvallr from the unsloth/qwen2.5-1.5b-instruct-unsloth-bnb-4bit base model. This model is specifically adapted for legal applications, indicating a specialization in processing and generating legal-related text.

Key Capabilities & Features

  • Legal Domain Specialization: Fine-tuned for legal use cases, suggesting enhanced performance on legal documents, queries, and tasks.
  • Efficient Training: Developed using Unsloth and Huggingface's TRL library, enabling 2x faster training compared to standard methods.
  • Qwen2.5 Architecture: Built upon the Qwen2.5 instruction-tuned architecture, providing a robust foundation for language understanding and generation.
  • Context Length: Supports a substantial context window of 32768 tokens, suitable for processing longer legal texts and complex scenarios.

When to Use This Model

This model is particularly well-suited for developers and researchers working on applications within the legal domain. Its specialized fine-tuning makes it a strong candidate for tasks such as:

  • Legal document analysis and summarization.
  • Answering legal questions.
  • Generating legal drafts or clauses.
  • Assisting with legal research where domain-specific understanding is crucial.