vall-e/vall_e/models/arch
2024-08-06 20:42:39 -05:00
..
mamba_vasqu
retnet_syncdoth
__init__.py add adapted MixtralAttention for when I make a bad decision to actually train a MoE 2024-08-04 22:03:22 -05:00
bitnet.py
llama.py do not include SDPA attention if there's no available SDPA backends 2024-08-06 20:42:39 -05:00
mamba.py
mixtral.py add adapted MixtralAttention for when I make a bad decision to actually train a MoE 2024-08-04 22:03:22 -05:00
retnet.py
transformer.py