Multilingual T5ForConditionalGeneration Base Cased model (from Voicelab)

Description

Pretrained T5ForConditionalGeneration model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. vlt5-base-keywords is a Multilingual model originally trained by Voicelab.

Download Copy S3 URI

How to use

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

t5 = T5Transformer.pretrained("t5_vlt5_base_keywords","xx") \
    .setInputCols("document") \
    .setOutputCol("answers")
    
pipeline = Pipeline(stages=[documentAssembler, t5])

data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text")

result = pipeline.fit(data).transform(data)
val documentAssembler = new DocumentAssembler() 
      .setInputCols("text")
      .setOutputCols("document")
       
val t5 = T5Transformer.pretrained("t5_vlt5_base_keywords","xx") 
    .setInputCols("document")
    .setOutputCol("answers")
   
val pipeline = new Pipeline().setStages(Array(documentAssembler, t5))

val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text")

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

Model Information

Model Name: t5_vlt5_base_keywords
Compatibility: Spark NLP 4.3.0+
License: Open Source
Edition: Official
Input Labels: [documents]
Output Labels: [t5]
Language: xx
Size: 1.1 GB

References

  • https://huggingface.co/Voicelab/vlt5-base-keywords
  • https://nlp-demo-1.voicelab.ai/
  • https://arxiv.org/abs/2209.14008
  • https://arxiv.org/abs/2209.14008
  • https://voicelab.ai/contact/