Awni Hannun 657f466402 use sdpa and exportable functions in transformer multi head attention (#1760)

2025-01-09 13:11:55 -08:00

..

layers

use sdpa and exportable functions in transformer multi head attention (#1760)

2025-01-09 13:11:55 -08:00

__init__.py

Common neural network initializers nn.initializers (#456)

2024-01-23 06:47:20 -08:00

init.py

[Feature] Added Sparse Initialization (#1498)

2024-10-24 12:31:24 -07:00

losses.py

Some fixes to typing (#1371)

2024-08-28 11:16:19 -07:00

utils.py

Data parallel helper (#1407)

2024-09-16 18:17:21 -07:00