Description
Pretrained T5ForConditionalGeneration model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. mt5-base-it-paraphraser
is a Italian model originally trained by aiknowyou
.
How to use
documentAssembler = DocumentAssembler() \
.setInputCols("text") \
.setOutputCols("document")
t5 = T5Transformer.pretrained("t5_mt5_base_it_paraphraser","it") \
.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_base_it_paraphraser","it")
.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_base_it_paraphraser |
Compatibility: | Spark NLP 4.3.0+ |
License: | Open Source |
Edition: | Official |
Input Labels: | [documents] |
Output Labels: | [t5] |
Language: | it |
Size: | 969.5 MB |
References
- https://huggingface.co/aiknowyou/mt5-base-it-paraphraser
- https://arxiv.org/abs/2010.11934
- https://colab.research.google.com/drive/1DGeF190gJ3DjRFQiwhFuZalp427iqJNQ
- https://gist.github.com/avidale/44cd35bfcdaf8bedf51d97c468cc8001
- http://creativecommons.org/licenses/by-nc-sa/4.0/
- http://creativecommons.org/licenses/by-nc-sa/4.0/