JaSpa99 d3d58a37e5 Bert: use Tensor.scaled_dot_product_attention (#1528) ...

* use scaled attn from Tensor

* add a test for bert

* linter

* no more tokenizer

* without loading weights

* remove prints

* tribute to linter lords

* smaller input and less runs

* small bert

2023-08-12 08:46:04 -07:00

..

bert.py

Bert: use Tensor.scaled_dot_product_attention (#1528)

2023-08-12 08:46:04 -07:00

convnext.py

LayerNorm2d for 2 lines

2023-03-20 16:58:43 -07:00

efficientnet.py

remove unused imports in models (#1088)

2023-07-01 12:04:19 -07:00

mask_rcnn.py

Add pylint trailing whitespace rule (#1314)

2023-07-21 13:37:55 -04:00

resnet.py

remove unused imports in models (#1088)

2023-07-01 12:04:19 -07:00

retinanet.py

Use generators instead of lists in anys and alls (#1111)

2023-07-03 16:06:06 -07:00

rnnt.py

Promote Embedding to nn (#798)

2023-05-25 18:39:45 -07:00

transformer.py

Transformer: use Tensor.scaled_dot_product_attention (#1520)

2023-08-11 09:00:37 -07:00

unet3d.py

Add pylint trailing whitespace rule (#1314)

2023-07-21 13:37:55 -04:00

vit.py

good changes from llama branch (#671)

2023-03-09 20:51:22 -08:00