relvarel/qwen2.5-7b-legal-id-sft

TEXT GENERATIONPricing:Input $0.4 / Cached $0.08 / Output $0.8Concurrent Unit Cost:1Model Size:7.6BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Jul 24, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The relvarel/qwen2.5-7b-legal-id-sft model is a 7.6 billion parameter Qwen2.5-based language model, fine-tuned by relvarel. This model is specifically optimized for legal tasks within the Indonesian context, leveraging its base architecture for specialized performance. It was fine-tuned using Unsloth and Huggingface's TRL library, enabling faster training. Its primary strength lies in processing and generating content relevant to Indonesian legal domains.

Loading preview...

Model Overview

relvarel/qwen2.5-7b-legal-id-sft is a 7.6 billion parameter language model, developed by relvarel. It is built upon the Qwen2.5 architecture, specifically fine-tuned from unsloth/Qwen2.5-7B-Instruct-bnb-4bit. The fine-tuning process utilized Unsloth and Huggingface's TRL library, which facilitated a 2x faster training speed.

Key Capabilities

  • Specialized Domain: Optimized for tasks related to the Indonesian legal domain.
  • Efficient Training: Benefits from Unsloth's optimizations for faster fine-tuning.
  • Qwen2.5 Base: Inherits the robust capabilities of the Qwen2.5 instruction-tuned model.

Good For

  • Applications requiring language understanding and generation in Indonesian legal contexts.
  • Developers looking for a specialized model for legal text processing in Indonesia.
  • Use cases where efficient fine-tuning and deployment of a Qwen2.5-based model are priorities.