Description
Pretrained T5ForConditionalGeneration model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. ke-t5-small-ko
is a Korean model originally trained by KETI-AIR
.
How to use
documentAssembler = DocumentAssembler() \
.setInputCols("text") \
.setOutputCols("document")
t5 = T5Transformer.pretrained("t5_ke_small","ko") \
.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_ke_small","ko")
.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_ke_small |
Compatibility: | Spark NLP 4.3.0+ |
License: | Open Source |
Edition: | Official |
Input Labels: | [documents] |
Output Labels: | [t5] |
Language: | ko |
Size: | 211.1 MB |
References
- https://huggingface.co/KETI-AIR/ke-t5-small-ko
- https://github.com/AIRC-KETI/ke-t5
- https://aclanthology.org/2021.findings-emnlp.33/
- https://koreascience.kr/article/CFKO202130060717834.pdf