Leonora123/RAGProject
TEXT GENERATIONConcurrency Cost:1Model Size:1.5BQuant:BF16Ctx Length:32kPublished:May 21, 2026License:apache-2.0Architecture:Transformer Open Weights Warm
Leonora123/RAGProject is a 1.5 billion parameter Qwen2.5-based instruction-tuned causal language model developed by Leonora123. This model was finetuned using Unsloth and Huggingface's TRL library, enabling 2x faster training. It is optimized for efficient performance, making it suitable for applications requiring a compact yet capable language model.
Loading preview...
Overview
Leonora123/RAGProject is a 1.5 billion parameter instruction-tuned model based on the Qwen2.5 architecture. Developed by Leonora123, this model was finetuned using the Unsloth library and Huggingface's TRL, which significantly accelerated its training process by 2x.
Key Capabilities
- Efficient Performance: Leveraging Unsloth for finetuning, the model is designed for faster training and potentially optimized inference.
- Qwen2.5 Base: Built upon the Qwen2.5 architecture, providing a solid foundation for general language understanding and generation tasks.
- Instruction-Tuned: Capable of following instructions for various natural language processing tasks.
Good For
- Applications requiring a compact and efficient language model.
- Scenarios where rapid deployment and training are beneficial.
- General instruction-following tasks within its parameter size class.