12 Commits

Author SHA1 Message Date
Feraidoon Mehri
ca20e102fe
mambaout.py: fixed bug 2024-10-17 01:03:28 +03:30
Ross Wightman
89dffc5ff0 Another small fix for original mambaout models, no classifier nn.Linear when num_classe=0 on init 2024-10-16 12:36:36 -07:00
Ross Wightman
c82ce86f8f Add 384x384 mambaout_base_plus model weights 2024-10-14 12:28:57 -07:00
Ross Wightman
82ae247879 MambaOut weights on hub, configs finalized 2024-10-11 11:07:40 -07:00
Ross Wightman
7efb60c299 Add first_conv for mambaout 2024-10-09 14:11:40 -07:00
Ross Wightman
5dc5ee5b42 Add global_pool to mambaout __init__ and pass to heads 2024-10-09 14:11:40 -07:00
Ross Wightman
9d1dfe8dbe Incorrectly named head_hidden_size 2024-10-09 14:11:40 -07:00
Ross Wightman
91e743f2dd Mambaout tweaks 2024-10-09 14:11:40 -07:00
Ross Wightman
4542cf03f9 Add features_only, other bits to mambaout, define different base alternatives 2024-10-09 14:11:40 -07:00
Ross Wightman
c2da12c7e1 Update rw models, fix heads 2024-10-09 14:11:40 -07:00
Ross Wightman
f2086f51a0 Add mambaout builder support, pretrained weight remap 2024-10-09 14:11:40 -07:00
Ross Wightman
c6ef54eefa Initial mambaout work 2024-10-09 14:11:40 -07:00