Description
Pretrained T5ForConditionalGeneration model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. LongLM-small is a Chinese model originally trained by thu-coai.
How to use
documentAssembler = DocumentAssembler() \
.setInputCols("text") \
.setOutputCols("document")
t5 = T5Transformer.pretrained("t5_longlm_small","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_longlm_small","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_longlm_small |
| Compatibility: | Spark NLP 4.3.0+ |
| License: | Open Source |
| Edition: | Official |
| Input Labels: | [documents] |
| Output Labels: | [t5] |
| Language: | zh |
| Size: | 288.2 MB |
References
- https://huggingface.co/thu-coai/LongLM-small
- https://jianguanthu.github.io/
- http://coai.cs.tsinghua.edu.cn/