YudhaPalulun/qwen2.5-1.5b-instruct-legal-id-sft
TEXT GENERATIONConcurrent Unit Cost:1Model Size:1.5BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Jul 15, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold
YudhaPalulun/qwen2.5-1.5b-instruct-legal-id-sft is a 1.5 billion parameter Qwen2.5-Instruct model developed by YudhaPalulun, fine-tuned for legal applications in Indonesian. This model leverages Unsloth and Huggingface's TRL library for accelerated training. With a 32768 token context length, it is optimized for processing and generating legal text in Indonesian.
Loading preview...
Model Overview
YudhaPalulun/qwen2.5-1.5b-instruct-legal-id-sft is a specialized instruction-tuned language model based on the Qwen2.5 architecture, featuring 1.5 billion parameters. Developed by YudhaPalulun, this model is specifically fine-tuned for legal applications within the Indonesian language context.
Key Capabilities
- Indonesian Legal Text Processing: Optimized for understanding and generating content relevant to Indonesian legal frameworks.
- Instruction Following: Designed to respond effectively to instructions, making it suitable for various task-oriented applications.
- Efficient Training: The model was fine-tuned using Unsloth and Huggingface's TRL library, enabling faster training iterations.
- Context Length: Supports a substantial context window of 32768 tokens, allowing for the processing of longer legal documents or complex queries.
Good For
- Legal Research in Indonesian: Assisting with information retrieval and summarization of Indonesian legal documents.
- Legal Document Generation: Generating drafts or components of legal texts in Indonesian based on specific instructions.
- Legal Q&A Systems: Developing chatbots or systems that can answer legal questions in Indonesian.
- Specialized NLP Tasks: Applications requiring a deep understanding of Indonesian legal terminology and concepts.