mrq d636edd3a2 added flash_attn LlamaAttention (including flash_attn==1.0.9)		2024-08-18 20:51:14 -05:00
..
mamba_vasqu
retnet_syncdoth
__init__.py
bitnet.py
llama.py	added flash_attn LlamaAttention (including flash_attn==1.0.9)	2024-08-18 20:51:14 -05:00
mamba.py
mixtral.py	added flash_attn LlamaAttention (including flash_attn==1.0.9)	2024-08-18 20:51:14 -05:00
retnet.py
transformer.py