ericoh929/qwen3-1.7b-lamini-qlora-instruction-tuned

The ericoh929/qwen3-1.7b-lamini-qlora-instruction-tuned model is a 1.7 billion parameter Qwen3-Base model developed by ericoh929, fine-tuned using QLoRA on a subset of the MBZUAI/LaMini-instruction dataset. This instruction-tuned model is optimized for single-turn question-answering, short reasoning, and summarization tasks. It is designed for efficient deployment as a merged checkpoint, providing general instruction-following capabilities.