Fex98234/qwen2.5-1.5b-indonesian-rlora
Fex98234/qwen2.5-1.5b-indonesian-rlora is a 1.5 billion parameter Qwen2.5 model developed by Fex98234, fine-tuned specifically for Indonesian language tasks. This model leverages Unsloth for accelerated training, making it efficient for deployment in Indonesian-centric applications. With a 32K context length, it is optimized for processing and generating text in Indonesian.
Loading preview...
Model Overview
Fex98234/qwen2.5-1.5b-indonesian-rlora is a 1.5 billion parameter Qwen2.5 model, developed by Fex98234, that has been fine-tuned for the Indonesian language. This model was trained using Unsloth and Huggingface's TRL library, which enabled a 2x faster fine-tuning process.
Key Characteristics
- Base Model: Fine-tuned from
unsloth/Qwen2.5-1.5B-Instruct-bnb-4bit. - Parameter Count: 1.5 billion parameters.
- Context Length: Supports a context length of 32,768 tokens.
- Training Efficiency: Utilizes Unsloth for significantly faster training.
Primary Use Case
This model is specifically designed and optimized for tasks requiring strong performance in the Indonesian language. Its fine-tuning makes it suitable for applications such as:
- Indonesian text generation.
- Indonesian language understanding and processing.
- Conversational AI in Indonesian.