Description
Pretrained T5ForConditionalGeneration model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. ct5-small-en-wiki-l2r is a English model originally trained by mtreviso.
How to use
documentAssembler = DocumentAssembler() \
.setInputCols("text") \
.setOutputCols("document")
t5 = T5Transformer.pretrained("t5_ct5_small_wiki_l2r","en") \
.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_ct5_small_wiki_l2r","en")
.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_ct5_small_wiki_l2r |
| Compatibility: | Spark NLP 4.3.0+ |
| License: | Open Source |
| Edition: | Official |
| Input Labels: | [documents] |
| Output Labels: | [t5] |
| Language: | en |
| Size: | 288.7 MB |
References
- https://huggingface.co/mtreviso/ct5-small-en-wiki-l2r
- https://github.com/mtreviso/chunked-t5