dbmdz
/

bert-base-historic-dutch-cased

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

stefan-it commited on Dec 13, 2021

Commit

2297386

•

1 Parent(s): 80f4495

readme: fix figures link

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -54,7 +54,7 @@ resulting in a total corpus size of 21GB.
 The following figure shows an overview of the number of chars per year distribution:
-![Delpher Corpus Stats](/figures/delpher_corpus_stats.png)
 # Language Model Pretraining
@@ -81,7 +81,7 @@ python3 run_pretraining.py --input_file gs://delpher-bert/tfrecords/*.tfrecord \
 We train the model for 3M steps using a total batch size of 128 on a v3-32 TPU. The pretraining loss curve can be seen
 in the next figure:
-![Delpher Pretraining Loss Curve](/figures/training_loss.png)
 # Evaluation

 The following figure shows an overview of the number of chars per year distribution:
+![Delpher Corpus Stats](figures/delpher_corpus_stats.png)
 # Language Model Pretraining
 We train the model for 3M steps using a total batch size of 128 on a v3-32 TPU. The pretraining loss curve can be seen
 in the next figure:
+![Delpher Pretraining Loss Curve](figures/training_loss.png)
 # Evaluation