Daniel Xu 4edaaf19e5 Handle tied embeddings for llama 3.2 1B (#13796) ...

Previously the output.weight layer would not be loaded, and would only
contain randomly initialized values. This led to junk when doing a
forward pass.

Signed-off-by: Daniel Xu <daniel@thinkingmachines.ai>

2025-12-22 16:31:40 -05:00

..

bert.py

add contiguous in BertIntermediate (#13713)

2025-12-15 22:37:36 -05:00

clip.py

Clip model updates for Stable Diffusion mlperf training (#12313)

2025-09-29 21:50:14 -04:00

convnext.py

remove Tensor.no_grad, it's meaningless now [pr] (#10556)

2025-05-28 22:20:02 -07:00

efficientnet.py

remove the magic methods for moving between devices [pr] (#6881)

2024-10-04 20:27:52 +08:00

inception.py

don't hardcode weights path (#12171)

2025-09-15 00:33:47 -04:00

llama.py

Handle tied embeddings for llama 3.2 1B (#13796)

2025-12-22 16:31:40 -05:00

mask_rcnn.py

move BoxCoder to mlperf helpers (#9773)

2025-04-07 20:27:06 -04:00

resnet.py

Fix FC layer ResNet load_from_pretrained error (#8387)

2024-12-26 18:11:27 -05:00

retinanet.py

RetinaNet INITMLPERF support (#9950)

2025-04-21 10:32:05 -04:00

rnnt.py

change Tensor.stack to method (#4719)

2024-05-24 17:04:19 -04:00

t5.py

Flux.1 (#6334)

2024-09-24 10:08:04 +08:00

transformer.py

_one_hot_along_dim input needs to be int (#9179)

2025-02-20 09:00:43 -05:00

unet3d.py

move to new cached fetch (#2493)

2023-11-28 17:36:55 -08:00

unet.py

Stable Diffusion model init for mlperf (#12314)

2025-10-02 02:28:41 -04:00

vit.py

move to new cached fetch (#2493)

2023-11-28 17:36:55 -08:00