Edit on GitHub
  • John Snow Labs
  • Jan 30, 2023

German T5ForConditionalGeneration Small Cased model (from ml6team)

  • de
  • open_source
  • t5
  • tensorflow

Description

Pretrained T5ForConditionalGeneration model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. mt5-small-german-finetune-mlsum is a German model originally trained by ml6team.

Download Copy S3 URI

How to use

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

t5 = T5Transformer.pretrained("t5_mt5_small_german_finetune_mlsum","de") \
    .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_mt5_small_german_finetune_mlsum","de") 
    .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_mt5_small_german_finetune_mlsum
Compatibility: Spark NLP 4.3.0+
License: Open Source
Edition: Official
Input Labels: [documents]
Output Labels: [t5]
Language: de
Size: 1.3 GB

References

  • https://huggingface.co/ml6team/mt5-small-german-finetune-mlsum
  • https://github.com/pltrdy/rouge