Large language models (LLMs) have been widely applied in various practical applications, typically comprising billions of parameters, with inference processes requiring substantial energy and computational resources. In contrast, the human brain, employing bio-plausible spiking mechanisms, can accomplish the same tasks while significantly reducing energy consumption, even with a similar number of parameters. Based on this, several pioneering researchers have proposed and implemented various large language models that leverage spiking neural networks. They have demonstrated the feasibility of these models, validated their performance, and open-sourced their frameworks and partial source code. To accelerate the adoption of brain-inspired large language models and facilitate secondary development for researchers, we are releasing a software toolkit named DarwinKit (Darkit). The toolkit is designed specifically for learners, researchers, and developers working on spiking large models, offering a suite of highly user-friendly features that greatly simplify the learning, deployment, and development processes.
@article{arxiv.2412.15634,
title = {Darkit: A User-Friendly Software Toolkit for Spiking Large Language Model},
author = {Xin Du and Shifan Ye and Qian Zheng and Yangfan Hu and Rui Yan and Shunyu Qi and Shuyang Chen and Huajin Tang and Gang Pan and Shuiguang Deng},
journal= {arXiv preprint arXiv:2412.15634},
year = {2024}
}