ku-nlp
/

bart-large-japanese

text2text-generation

Model card Files Files and versions

Matttttttt commited on May 10, 2023

Commit

9644c4c

·

1 Parent(s): 8e7ca09

Update README.md

Files changed (1) hide show

README.md +3 -2

README.md CHANGED Viewed

@@ -52,5 +52,6 @@ The following hyperparameters were used during pre-training:
 - num_devices: 4
 - batch_size: 512
 - training_steps: 250,000
-- encoder-decoder layers: 12
-- hidden: 1024

 - num_devices: 4
 - batch_size: 512
 - training_steps: 250,000
+- encoder layers: 12
+- decoder layers: 12
+- hidden size: 1024