Description
Pretrained T5Transformer model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.google_flan_t5_base_ft_v_2025_01_15 is a English model originally trained by Fastgurugroup2.
How to use
documentAssembler = DocumentAssembler() \
.setInputCol('text') \
.setOutputCol('document')
t5 = T5Transformer.pretrained("google_flan_t5_base_ft_v_2025_01_15","en") \
.setInputCols(["document"]) \
.setOutputCol("output")
pipeline = Pipeline().setStages([documentAssembler, t5])
data = spark.createDataFrame([["I love spark-nlp"]]).toDF("text")
pipelineModel = pipeline.fit(data)
pipelineDF = pipelineModel.transform(data)
val documentAssembler = new DocumentAssembler()
.setInputCols("text")
.setOutputCols("document")
val t5 = T5Transformer.pretrained("google_flan_t5_base_ft_v_2025_01_15", "en")
.setInputCols(Array("documents"))
.setOutputCol("output")
val pipeline = new Pipeline().setStages(Array(documentAssembler, t5))
val data = Seq("I love spark-nlp").toDS.toDF("text")
val pipelineModel = pipeline.fit(data)
val pipelineDF = pipelineModel.transform(data)
Model Information
| Model Name: | google_flan_t5_base_ft_v_2025_01_15 |
| Compatibility: | Spark NLP 5.5.1+ |
| License: | Open Source |
| Edition: | Official |
| Input Labels: | [document] |
| Output Labels: | [output] |
| Language: | en |
| Size: | 1.0 GB |
References
https://huggingface.co/Fastgurugroup2/google-flan-t5-base_FT_v_2025-01-15