nathangalung/qwen2.5-1.5b-alpaca-indonesian-sft

TEXT GENERATIONConcurrent Unit Cost:1Model Size:1.5BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Jul 21, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The nathangalung/qwen2.5-1.5b-alpaca-indonesian-sft is a 1.5 billion parameter Qwen2.5 model, developed by nathangalung, fine-tuned for Indonesian language tasks. This model leverages Unsloth for accelerated training and is optimized for efficient performance. It is specifically adapted for Alpaca-style instruction following in Indonesian, making it suitable for various natural language processing applications in that language.

Loading preview...

Model Overview

The nathangalung/qwen2.5-1.5b-alpaca-indonesian-sft is a 1.5 billion parameter language model developed by nathangalung. It is built upon the Qwen2.5 architecture and has been specifically fine-tuned for Indonesian language understanding and generation.

Key Capabilities

  • Indonesian Language Proficiency: The model is specialized for tasks requiring comprehension and generation in Indonesian, having been fine-tuned with an Alpaca-style instruction dataset.
  • Efficient Training: This model was trained using Unsloth and Huggingface's TRL library, resulting in a 2x faster training process compared to standard methods.
  • Qwen2.5 Architecture: Based on the Qwen2.5 family, it benefits from the foundational capabilities of this robust model series.

Use Cases

This model is particularly well-suited for applications requiring instruction-following and natural language processing in Indonesian, such as:

  • Indonesian text generation
  • Chatbots or conversational AI in Indonesian
  • Instruction-based tasks in the Indonesian language
  • Research and development in Indonesian NLP.