xander 8e71457f07 massive refactor and attention regularization optimizations

2024-08-04 20:10:40 +02:00

..

utils

add token attention regularization

2024-08-02 18:46:42 +02:00

checkpoint.py

update naming conventions

2024-07-18 04:07:00 +02:00

config.py

massive refactor and attention regularization optimizations

2024-08-04 20:10:40 +02:00

dataset.py

massive refactor and attention regularization optimizations

2024-08-04 20:10:40 +02:00

embedding_handler.py

massive refactor and attention regularization optimizations

2024-08-04 20:10:40 +02:00

inference.py

massive refactor and attention regularization optimizations

2024-08-04 20:10:40 +02:00

loss.py

massive refactor and attention regularization optimizations

2024-08-04 20:10:40 +02:00

models.py

massive refactor and attention regularization optimizations

2024-08-04 20:10:40 +02:00

optimizer.py

updates to avoid OOM when plotting hist

2024-07-06 22:18:47 +02:00

preprocess.py

massive refactor and attention regularization optimizations

2024-08-04 20:10:40 +02:00

ti_cross_attn_loss.py

massive refactor and attention regularization optimizations

2024-08-04 20:10:40 +02:00