rizalarfiyan/qwen-legal-SFT-dicoding
TEXT GENERATIONPricing:Input $0.04 / Cached $0.008 / Output $0.08Concurrent Unit Cost:1Model Size:1.5BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Jul 30, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold
The rizalarfiyan/qwen-legal-SFT-dicoding model is a 1.5 billion parameter Qwen2.5-based instruction-tuned language model developed by rizalarfiyan. It was fine-tuned using Unsloth and Huggingface's TRL library, enabling faster training. This model is specifically optimized for legal-related tasks, leveraging its Qwen2.5 architecture for specialized applications.
Loading preview...
Model Overview
This model, rizalarfiyan/qwen-legal-SFT-dicoding, is a 1.5 billion parameter instruction-tuned variant of the Qwen2.5 architecture. Developed by rizalarfiyan, it was fine-tuned from unsloth/qwen2.5-1.5b-instruct-unsloth-bnb-4bit.
Key Capabilities
- Specialized Fine-tuning: The model has undergone supervised fine-tuning (SFT) specifically for legal applications, suggesting enhanced performance in legal text understanding and generation.
- Efficient Training: It leverages Unsloth and Huggingface's TRL library, which facilitated a 2x faster training process.
- Qwen2.5 Architecture: Built upon the Qwen2.5 base, it inherits the foundational capabilities of this robust language model family.
Good For
- Legal Use Cases: This model is particularly suited for tasks involving legal documents, queries, and content generation due to its specialized fine-tuning.
- Resource-Efficient Deployment: With 1.5 billion parameters, it offers a balance between performance and computational efficiency, making it suitable for environments where larger models might be prohibitive.
- Applications requiring Qwen2.5's strengths: Users familiar with or requiring the characteristics of the Qwen2.5 architecture will find this specialized version beneficial for legal domains.