NYTK
/

PULI-BERT-Large

Inference Endpoints

Model card Files Files and versions Community

fragata commited on Jan 16, 2023

Commit

e2e454d

·

1 Parent(s): 08e2cf2

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -16,7 +16,7 @@ For further details, see [our demo site](https://juniper.nytud.hu/demo/nlp).
   - Hungarian BERT large model (MegatronBERT)
   - Trained with Megatron-DeepSpeed [github](https://github.com/microsoft/Megatron-DeepSpeed)
   - Dataset: 36.3 billion words
-  - Checkpoint: 150 000 steps
 ## Limitations

   - Hungarian BERT large model (MegatronBERT)
   - Trained with Megatron-DeepSpeed [github](https://github.com/microsoft/Megatron-DeepSpeed)
   - Dataset: 36.3 billion words
+  - Checkpoint: 1 500 000 steps
 ## Limitations