GassiGiuseppe 144f8724d6 Update of the batcher to resolve a bug in the 4th construction

2025-10-12 16:35:42 +02:00

..

__init__.py

Added Custom Learning Rate

2025-10-09 11:36:40 +02:00

Decoder.py

Update of the batcher to resolve a bug in the 4th construction

2025-10-12 16:35:42 +02:00

DeToken.py

Disabled Softmax

2025-10-09 11:36:56 +02:00

Encoder.py

Activated Dropout to avoid overfitting

2025-10-12 12:28:06 +02:00

FeedForwardNetwork.py

Activated Dropout to avoid overfitting

2025-10-12 12:28:06 +02:00

NanoSocratesCore.py

WIP

2025-10-07 16:38:08 +02:00

SpannedMasker.py

V0.0.1 Athene

2025-10-11 19:35:43 +02:00

TokenMasker.py

Added 2 types of masking

2025-10-06 15:45:45 +02:00

TorchMultiHeadAttention.py

Made model Batch ready

2025-10-07 16:37:20 +02:00

WarmupLR.py

Added Custom Learning Rate

2025-10-09 11:36:40 +02:00