You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
- Efficient fine-tuning for task-specific adaptation
28
28
- Includes a Mixture-of-Depths ([https://arxiv.org/abs/2404.02258](https://arxiv.org/abs/2404.02258)) transformer layer that incorporates Infini-Attention
29
29
- Implementation of RoPE ([https://arxiv.org/abs/2104.09864](https://arxiv.org/abs/2104.09864)) that conforms to Infini-Attention's and Mixture-of-Depth's memory-efficient designs (PoSE to be added soon)
30
-
--Implementation of YaRN ([https://arxiv.org/abs/2309.00071](https://arxiv.org/abs/2309.00071)) that conforms to Infini-Attention's and Mixture-of-Depth's memory-efficient designs (PoSE to be added soon)
30
+
- Implementation of YaRN ([https://arxiv.org/abs/2309.00071](https://arxiv.org/abs/2309.00071)) that conforms to Infini-Attention's and Mixture-of-Depth's memory-efficient designs (PoSE to be added soon)
0 commit comments