mhusni/qwen2.5-3b-indonesian-legal-sft-16bit
TEXT GENERATIONPricing:Input $0.32 / Cached $0.064 / Output $1.6Concurrent Unit Cost:1Model Size:3.1BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Aug 26, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold
The mhusni/qwen2.5-3b-indonesian-legal-sft-16bit is a 3.1 billion parameter Qwen2.5 model, fine-tuned by mhusni, specifically optimized for Indonesian legal tasks. This model leverages a 32768-token context length and was trained using Unsloth and Huggingface's TRL library for enhanced efficiency. Its primary strength lies in processing and generating content related to Indonesian legal documents and queries.
Loading preview...
Model Overview
This model, developed by mhusni, is a fine-tuned version of the Qwen2.5-3B-Instruct model, specifically adapted for Indonesian legal applications. It utilizes a 3.1 billion parameter architecture and supports a substantial context length of 32768 tokens, making it suitable for handling complex legal documents.
Key Capabilities
- Indonesian Legal Specialization: The model has undergone supervised fine-tuning (SFT) on Indonesian legal datasets, enhancing its understanding and generation capabilities within this domain.
- Efficient Training: It was trained using Unsloth and Huggingface's TRL library, which facilitated faster training processes.
Good For
- Legal Text Analysis: Ideal for tasks involving the analysis, summarization, or generation of Indonesian legal texts.
- Legal Information Retrieval: Can be used to process queries and extract relevant information from Indonesian legal documents.
- Specialized Indonesian NLP: Suitable for applications requiring a deep understanding of Indonesian legal language and context.