nahwakaka/qwen2.5-3b-legal-id-sft
TEXT GENERATIONConcurrent Unit Cost:1Model Size:3.1BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Jul 9, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold
The nahwakaka/qwen2.5-3b-legal-id-sft model is a 3.1 billion parameter Qwen2.5-based language model, developed by nahwakaka. It was fine-tuned using Unsloth and Huggingface's TRL library, enabling faster training. This model is specifically optimized for legal tasks within the Indonesian context, making it suitable for specialized applications requiring legal domain understanding.
Loading preview...
Model Overview
The nahwakaka/qwen2.5-3b-legal-id-sft is a 3.1 billion parameter language model, fine-tuned by nahwakaka. It is based on the Qwen2.5 architecture and was developed using unsloth/Qwen2.5-3B-bnb-4bit as its base model. The fine-tuning process leveraged Unsloth and Huggingface's TRL library, which facilitated a significantly faster training time.
Key Capabilities
- Specialized Domain: This model is specifically fine-tuned for legal tasks, with a focus on the Indonesian context.
- Efficient Training: Benefits from the Unsloth library for accelerated training, indicating potential for further efficient adaptation.
- Qwen2.5 Architecture: Inherits the robust capabilities of the Qwen2.5 base model.
Good For
- Indonesian Legal Applications: Ideal for use cases requiring understanding and generation of legal text relevant to Indonesia.
- Domain-Specific NLP: Suitable for developers building applications that need a specialized language model for legal information processing.
- Resource-Efficient Deployment: As a 3.1B parameter model, it offers a balance between performance and computational resource requirements.