Tu2003716
/

COCOM_disabled_flash_attn

Model card Files Files and versions Community

COCOM_disabled_flash_attn

3 contributors

History: 17 commits

Plasmarine's picture

Longformer attn config

929ceeb verified 27 days ago

.gitattributes

1.55 kB

Fine tuned to add key to disable flash_attn for older GPU about 1 month ago
README.md

5.59 kB

Fine tuned to add key to disable flash_attn for older GPU about 1 month ago
cocom.png

66.8 kB

Fine tuned to add key to disable flash_attn for older GPU about 1 month ago
config.json

694 Bytes

Fine tuned to add key to disable flash_attn for older GPU about 1 month ago
generation_config.json

99 Bytes

Fine tuned to add key to disable flash_attn for older GPU about 1 month ago
model-00001-of-00003.bin

135 Bytes
LFS

upload bin file about 1 month ago
model-00001-of-00003.safetensors

4.97 GB
LFS

Upload pretraining files about 1 month ago
model-00002-of-00003.bin

135 Bytes
LFS

upload bin file about 1 month ago
model-00002-of-00003.safetensors

5 GB
LFS

Upload pretraining files about 1 month ago
model-00003-of-00003.bin

135 Bytes
LFS

upload bin file about 1 month ago
model-00003-of-00003.safetensors

4.6 GB
LFS

Upload pretraining files about 1 month ago
model.safetensors.index.json

88.7 kB

Fine tuned to add key to disable flash_attn for older GPU about 1 month ago
modeling_cocom.py

16.9 kB

Longformer attn config 27 days ago