English Bert Embeddings Cased model (from Tristan)

Description

Pretrained BertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. olm-bert-base-uncased-oct-2022 is a English model originally trained by Tristan.

Download Copy S3 URI

How to use

documentAssembler = DocumentAssembler() \
    .setInputCol("text") \
    .setOutputCol("document")

tokenizer = Tokenizer() \
    .setInputCols("document") \
    .setOutputCol("token")

embeddings = BertEmbeddings.pretrained("bert_embeddings_olm_base_uncased_oct_2022","en") \
    .setInputCols(["document", "token"]) \
    .setOutputCol("embeddings") \
    .setCaseSensitive(True)

pipeline = Pipeline(stages=[documentAssembler, tokenizer, embeddings])

data = spark.createDataFrame([["I love Spark NLP"]]).toDF("text")

result = pipeline.fit(data).transform(data)
val documentAssembler = new DocumentAssembler()
    .setInputCol("text")
    .setOutputCol("document")

val tokenizer = new Tokenizer()
    .setInputCols("document")
    .setOutputCol("token")

val embeddings = BertEmbeddings.pretrained("bert_embeddings_olm_base_uncased_oct_2022","en")
    .setInputCols(Array("document", "token"))
    .setOutputCol("embeddings")
    .setCaseSensitive(True)

val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, embeddings))

val data = Seq("I love Spark NLP").toDS.toDF("text")

val result = pipeline.fit(data).transform(data)

Model Information

Model Name: bert_embeddings_olm_base_uncased_oct_2022
Compatibility: Spark NLP 4.3.0+
License: Open Source
Edition: Official
Input Labels: [sentence, token]
Output Labels: [bert]
Language: en
Size: 467.5 MB
Case sensitive: true

References

https://huggingface.co/Tristan/olm-bert-base-uncased-oct-2022