@article{themambainthellamadistillingand, title = {The Mamba in the Llama: Distilling and Accelerating Hybrid Models}, author = {Junxiong Wang and Daniele Paliotta and Avner May and Alexander M. Rush and Tri Dao}, year = {2024}, eprint = {2408.15237}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2408.15237v3}, }