Large Language Models with At Most One Spike per Neuron
This work constructs a fully TTFS-based SNN architecture and train it end-to-end, and introduces a reference-based strategy specifically to encode the four core LLM components: embedding layers, layer normalization, attention-related operations and dropout.
Zhuo-Ya Zhao, Parsa Omidi, A. Jafari et al.
· 0 citations