Son, S., Park, W., Han, W., Kim, K., & Lee, J. (2024). Prefixing Attention Sinks can Mitigate Activation Outliers for Large Language Model Quantization.
Citazione stile Chigago Style (17a edizione)Son, Seungwoo, Wonpyo Park, Woohyun Han, Kyuyeun Kim, e Jaeho Lee. Prefixing Attention Sinks Can Mitigate Activation Outliers for Large Language Model Quantization. 2024.
Citatione MLA (9a ed.)Son, Seungwoo, et al. Prefixing Attention Sinks Can Mitigate Activation Outliers for Large Language Model Quantization. 2024.
Attenzione: Queste citazioni potrebbero non essere precise al 100%.