Back to all models

Unable to determine this model’s pipeline type. Check the docs .

Monthly model downloads

chiragjn/small_bert_uncased_L-4_H-768_A-12 chiragjn/small_bert_uncased_L-4_H-768_A-12
N/a downloads
last 30 days



Contributed by

chiragjn Chirag Jain
24 models

How to use this model directly from the 🤗/transformers library:

Copy to clipboard
from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("chiragjn/small_bert_uncased_L-4_H-768_A-12") model = AutoModel.from_pretrained("chiragjn/small_bert_uncased_L-4_H-768_A-12")
Uploaded in S3


This model was converted from the release of 24 smaller BERT models (English only, uncased, trained with WordPiece masking) referenced in Well-Read Students Learn Better: On the Importance of Pre-training Compact Models.

Conversion was performed automatically using transformers-cli convert as explained here

This model is also available on tfhub at

Caution: The tfhub version does not generate the same output as the released checkpoint or the converted model.

Released tf checkpoint and this converted model generate similar embeddings.