keperluan/qwen2.5-1.5b-legal-sft
TEXT GENERATIONPricing:Input $0.04 / Cached $0.008 / Output $0.08Concurrent Unit Cost:1Model Size:1.5BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Jul 20, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold
The keperluan/qwen2.5-1.5b-legal-sft is a 1.5 billion parameter Qwen2.5 model, fine-tuned by keperluan, specifically optimized for legal applications. This model leverages a 32768 token context length and was trained using Unsloth and Huggingface's TRL library for enhanced efficiency. It is designed to excel in tasks requiring legal domain understanding and generation.
Loading preview...
Model Overview
The keperluan/qwen2.5-1.5b-legal-sft is a specialized 1.5 billion parameter language model, fine-tuned by keperluan. It is based on the Qwen2.5 architecture and utilizes a substantial 32768 token context window, making it suitable for processing lengthy legal documents.
Key Capabilities
- Legal Domain Specialization: This model has been specifically fine-tuned for legal applications, suggesting enhanced performance in tasks related to legal text analysis, generation, and understanding.
- Efficient Training: The model was trained using Unsloth and Huggingface's TRL library, which enabled faster training times compared to conventional methods.
- Qwen2.5 Base: Built upon the robust Qwen2.5 instruction-tuned model, it inherits strong foundational language understanding and generation abilities.
Good For
- Legal Text Processing: Ideal for tasks such as legal document summarization, contract analysis, legal research assistance, and generating legal-themed content.
- Domain-Specific Applications: Developers building applications that require a deep understanding of legal terminology and concepts will find this model particularly useful.
- Efficient Deployment: Its 1.5 billion parameter size makes it relatively efficient for deployment while still offering specialized capabilities.