Halimawang/qwen-legal-indo-sft
TEXT GENERATIONPricing:Input $0.32 / Cached $0.064 / Output $1.6Concurrent Unit Cost:1Model Size:3.1BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Jul 25, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold
Halimawang/qwen-legal-indo-sft is a 3.1 billion parameter Qwen2-based instruction-tuned language model developed by Halimawang, fine-tuned from unsloth/Qwen2.5-3B-Instruct-bnb-4bit. This model was trained using Unsloth and Huggingface's TRL library, achieving 2x faster training. It is specialized for legal applications within the Indonesian context, leveraging its efficient fine-tuning process.
Loading preview...
Model Overview
Halimawang/qwen-legal-indo-sft is a 3.1 billion parameter language model, fine-tuned by Halimawang from the unsloth/Qwen2.5-3B-Instruct-bnb-4bit base model. It utilizes the Qwen2 architecture and has a context length of 32768 tokens.
Key Characteristics
- Efficient Fine-tuning: The model was fine-tuned using Unsloth and Huggingface's TRL library, resulting in a 2x faster training process compared to standard methods.
- Base Model: It builds upon the
Qwen2.5-3B-Instructmodel, indicating a strong foundation for instruction-following tasks.
Potential Use Cases
- Indonesian Legal Applications: Given its name, the model is likely optimized for tasks related to Indonesian legal text, such as document analysis, legal research, or generating legal summaries in Indonesian.
- Resource-Efficient Deployment: The use of a 3.1 billion parameter model, combined with 4-bit quantization (implied by the base model
bnb-4bit), suggests it can be deployed efficiently on hardware with limited resources.