elmosiussuli/qwen2.5-1.5b-indonesian-sft-pgabl

Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:1.5BQuant:BF16Ctx Length:32kPublished:May 7, 2026License:apache-2.0Architecture:Transformer Open Weights Warm

The elmosiussuli/qwen2.5-1.5b-indonesian-sft-pgabl is a 1.5 billion parameter Qwen2.5 model, fine-tuned by elmosiussuli from unsloth/Qwen2.5-1.5B-Instruct-bnb-4bit. This model is specifically optimized for Indonesian language tasks, leveraging Unsloth and Huggingface's TRL library for efficient training. It is designed for applications requiring a compact yet capable language model for Indonesian language processing.

Loading preview...

Model Overview

The elmosiussuli/qwen2.5-1.5b-indonesian-sft-pgabl is a 1.5 billion parameter language model based on the Qwen2.5 architecture. Developed by elmosiussuli, this model has been fine-tuned specifically for Indonesian language tasks, building upon the unsloth/Qwen2.5-1.5B-Instruct-bnb-4bit base model.

Key Characteristics

  • Architecture: Qwen2.5, a causal language model known for its performance.
  • Parameter Count: 1.5 billion parameters, offering a balance between performance and computational efficiency.
  • Language Focus: Primarily optimized for the Indonesian language through supervised fine-tuning (SFT).
  • Training Efficiency: The fine-tuning process utilized Unsloth and Huggingface's TRL library, enabling faster training.
  • Context Length: Supports a context length of 32768 tokens, allowing for processing longer sequences of text.

Use Cases

This model is particularly well-suited for applications requiring a compact and efficient language model with strong capabilities in Indonesian. Potential use cases include:

  • Indonesian text generation and completion.
  • Indonesian language understanding tasks.
  • Building chatbots or conversational AI systems in Indonesian.
  • Any application where a smaller, specialized Indonesian LLM is beneficial for deployment on resource-constrained environments.