stevensama73/Qwen2.5-3B-grpo-indonesian

Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:3.1BQuant:BF16Ctx Length:32kPublished:May 27, 2026License:apache-2.0Architecture:Transformer Open Weights Warm

stevensama73/Qwen2.5-3B-grpo-indonesian is a 3.1 billion parameter Qwen2.5 model developed by stevensama73, fine-tuned for Indonesian language tasks. This model was trained using Unsloth and Huggingface's TRL library, enabling faster fine-tuning. It is optimized for general-purpose applications within the Indonesian linguistic context, building upon its base as a Qwen2.5-3B-sft-think-indonesian variant.

Loading preview...

Model Overview

stevensama73/Qwen2.5-3B-grpo-indonesian is a 3.1 billion parameter language model developed by stevensama73. This model is a fine-tuned variant of the Qwen2.5 architecture, specifically adapted for Indonesian language processing. It builds upon the stevensama73/Qwen2.5-3B-sft-think-indonesian base model.

Key Characteristics

  • Architecture: Qwen2.5-3B, a causal language model.
  • Language Focus: Primarily fine-tuned for the Indonesian language.
  • Training Efficiency: The model was fine-tuned using Unsloth and Huggingface's TRL library, which facilitated a 2x faster training process.
  • License: Distributed under the Apache-2.0 license.

Intended Use Cases

This model is suitable for various general-purpose natural language processing tasks requiring proficiency in Indonesian. Its fine-tuned nature suggests improved performance for applications such as text generation, summarization, translation, and conversational AI within the Indonesian linguistic domain.