mrq d69a00e389 Properly pass retention_mask for retnet-HF, attempt to fix recurrent forward for retnet (doesn't work still)		2024-04-14 13:12:50 -05:00
..
retnet_hf	Properly pass retention_mask for retnet-HF, attempt to fix recurrent forward for retnet (doesn't work still)	2024-04-14 13:12:50 -05:00
__init__.py	added FP8 support through NVIDIA/TransformerEngine, added RetNet_HF through syncdoth/RetNet (as an alternative to branch away from torchscale)	2024-04-08 20:14:51 -05:00