Edit on GitHub
  • John Snow Labs
  • Sep 22, 2023

English BertEmbeddings Small Cased model (from BAAI)

  • en
  • open_source
  • bert_embeddings
  • onnx

Description

Pretrained BertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. bge-small-en is a English model originally trained by BAAI.

Download Copy S3 URI

How to use

documentAssembler = DocumentAssembler() \
    .setInputCols(["text"]) \
    .setOutputCols("document")

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

bert_loaded = BertEmbeddings.pretrained("bert_embeddings_bge_small","en") \
    .setInputCols(["document", "token"]) \
    .setOutputCol("embeddings") \
    .setCaseSensitive(True)
    
pipeline = Pipeline(stages=[documentAssembler, tokenizer, bert_loaded])

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

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

val documentAssembler = new DocumentAssembler() 
    .setInputCols(Array("text")) 
    .setOutputCols(Array("document"))
      
val tokenizer = new Tokenizer()
    .setInputCols("document")
    .setOutputCol("token")
 
val bert_loaded = BertEmbeddings.pretrained("bert_embeddings_bge_small","en") 
    .setInputCols(Array("document", "token"))
    .setOutputCol("embeddings")
    .setCaseSensitive(true)    
   
val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, bert_loaded))

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

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

Model Information

Model Name: bert_embeddings_bge_small
Compatibility: Spark NLP 5.1.0+
License: Open Source
Edition: Official
Input Labels: [document, token]
Output Labels: [bert]
Language: en
Size: 79.9 MB
Case sensitive: true

References

  • https://huggingface.co/BAAI/bge-small-en
  • https://github.com/FlagOpen/FlagEmbedding
  • https://github.com/FlagOpen/FlagEmbedding/blob/master/README_zh.md
  • https://arxiv.org/pdf/2309.07597.pdf
  • https://data.baai.ac.cn/details/BAAI-MTP
  • https://github.com/FlagOpen/FlagEmbedding/blob/master/FlagEmbedding/baai_general_embedding/README.md
  • https://github.com/FlagOpen/FlagEmbedding/blob/master/C_MTEB
  • https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/reranker
  • https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/reranker
  • https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune
  • https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune
  • https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune
  • https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune
  • https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune
  • https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune
  • https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune
  • https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune
  • https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune
  • https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune
  • https://github.com/FlagOpen/FlagEmbedding/tree/master/C_MTEB
  • https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune
  • https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune
  • https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune
  • https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune#hard-negatives
  • https://github.com/FlagOpen/FlagEmbedding/blob/master/FlagEmbedding/baai_general_embedding/README.md
  • https://github.com/FlagOpen/FlagEmbedding/tree/master#model-list
  • https://www.SBERT.net
  • https://github.com/FlagOpen/FlagEmbedding/tree/master#model-list
  • https://github.com/FlagOpen/FlagEmbedding/blob/master/C_MTEB/README.md
  • https://platform.openai.com/docs/guides/embeddings
  • https://github.com/FlagOpen/FlagEmbedding/blob/master/C_MTEB/README.md
  • https://platform.openai.com/docs/guides/embeddings/what-are-embeddings
  • https://github.com/FlagOpen/FlagEmbedding/blob/master/C_MTEB/
  • https://github.com/staoxiao/RetroMAE
  • https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune
  • https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/pretrain
  • https://github.com/FlagOpen/FlagEmbedding/blob/master/FlagEmbedding/baai_general_embedding/README.md
  • https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/reranker
  • https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/reranker
  • https://github.com/FlagOpen/FlagEmbedding/blob/master/LICENSE
  • https://paperswithcode.com/sota?task=Classification&dataset=MTEB+AmazonCounterfactualClassification+%28en%29