Smaller BERT Sentence Embeddings (L-8_H-512_A-8)


This is one of the smaller BERT models referenced in Well-Read Students Learn Better: On the Importance of Pre-training Compact Models. The smaller BERT models are intended for environments with restricted computational resources. They can be fine-tuned in the same manner as the original BERT models. However, they are most effective in the context of knowledge distillation, where the fine-tuning labels are produced by a larger and more accurate teacher.

Download Copy S3 URI

How to use

embeddings = BertSentenceEmbeddings.pretrained("sent_small_bert_L8_512", "en") \
.setInputCols("sentence") \
nlp_pipeline = Pipeline(stages=[document_assembler, sentence_detector, embeddings])
pipeline_model =[[""]]).toDF("text"))
result = pipeline_model.transform(spark.createDataFrame([['I hate cancer', "Antibiotics aren't painkiller"]], ["text"]))
val embeddings = BertSentenceEmbeddings.pretrained("sent_small_bert_L8_512", "en")
val pipeline = new Pipeline().setStages(Array(document_assembler, sentence_detector, embeddings))
val data = Seq("I hate cancer, "Antibiotics aren't painkiller").toDF("text")
val result =
import nlu

text = ["I hate cancer", "Antibiotics aren't painkiller"]
embeddings_df = nlu.load('en.embed_sentence.small_bert_L8_512').predict(text, output_level='sentence')


	en_embed_sentence_small_bert_L8_512_embeddings	      sentence
	[0.07683686912059784, -0.09125291556119919, 1.... 	I hate cancer
	[0.05132533982396126, 0.16612868010997772, -0.... 	Antibiotics aren't painkiller

Model Information

Model Name: sent_small_bert_L8_512
Type: embeddings
Compatibility: Spark NLP 2.6.0+
License: Open Source
Edition: Official
Input Labels: [sentence]
Output Labels: [sentence_embeddings]
Language: [en]
Dimension: 512
Case sensitive: false

Data Source

The model is imported from