MoE-CT: A Novel Approach For Large Language Models Training With Resistance To Catastrophic Forgetting

@misc{li2024moect,
  title = {MoE-CT: A Novel Approach For Large Language Models Training With Resistance To Catastrophic Forgetting},
  author = {Tianhao Li and Shangjie Li and Binbin Xie and Deyi Xiong and Baosong Yang},
  year = {2024},
  eprint = {2407.00875},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2407.00875},
}