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

Chinese T5ForConditionalGeneration Cased model (from IDEA-CCNL)

  • zh
  • open_source
  • t5
  • tensorflow

Description

Pretrained T5ForConditionalGeneration model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. Randeng-T5-77M-MultiTask-Chinese is a Chinese model originally trained by IDEA-CCNL.

Download Copy S3 URI

How to use

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

t5 = T5Transformer.pretrained("t5_randeng_77m_multitask_chinese","zh") \
    .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_randeng_77m_multitask_chinese","zh") 
    .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_randeng_77m_multitask_chinese
Compatibility: Spark NLP 4.3.0+
License: Open Source
Edition: Official
Input Labels: [documents]
Output Labels: [t5]
Language: zh
Size: 349.2 MB

References

  • https://huggingface.co/IDEA-CCNL/Randeng-T5-77M-MultiTask-Chinese
  • https://github.com/IDEA-CCNL/Fengshenbang-LM
  • https://fengshenbang-doc.readthedocs.io/
  • http://jmlr.org/papers/v21/20-074.html
  • https://github.com/IDEA-CCNL/Fengshenbang-LM/
  • https://github.com/IDEA-CCNL/Fengshenbang-LM/tree/main/fengshen/examples/pretrain_t5
  • https://github.com/IDEA-CCNL/Fengshenbang-LM/tree/main/fengshen/examples/mt5_summary
  • https://github.com/IDEA-CCNL/Fengshenbang-LM/
  • https://github.com/IDEA-CCNL/Fengshenbang-LM/tree/main/fengshen/examples/pretrain_t5
  • https://github.com/IDEA-CCNL/Fengshenbang-LM/tree/main/fengshen/examples/mt5_summary
  • https://arxiv.org/abs/2209.02970
  • https://arxiv.org/abs/2209.02970
  • https://github.com/IDEA-CCNL/Fengshenbang-LM/
  • https://github.com/IDEA-CCNL/Fengshenbang-LM/