Description
Pretrained MistralTransformer, adapted and imported into Spark NLP.
How to use
documentAssembler = DocumentAssembler() \
.setInputCol('text') \
.setOutputCol('document')
mistral = MistralTransformer .pretrained() \
.setMaxOutputLength(50) \
.setDoSample(False) \
.setInputCols(["document"]) \
.setOutputCol("mistral_generation")
pipeline = Pipeline().setStages([documentAssembler, mistral])
data = spark.createDataFrame([["Who is the founder of Spark-NLP?"]]).toDF("text")
pipelineModel = pipeline.fit(data)
pipelineDF = pipelineModel.transform(data)
val documentAssembler = new DocumentAssembler()
.setInputCols("text")
.setOutputCols("document")
val mistral = MistralTransformer .pretrained()
.setMaxOutputLength(50)
.setDoSample(False)
.setInputCols(["document"])
.setOutputCol("mistral_generation")
val pipeline = new Pipeline().setStages(Array(documentAssembler, mistral))
val data = Seq("Who is the founder of Spark-NLP?").toDS.toDF("text")
val pipelineModel = pipeline.fit(data)
val pipelineDF = pipelineModel.transform(data)
Model Information
| Model Name: | mistral_7b |
| Compatibility: | Spark NLP 5.4.0+ |
| License: | Open Source |
| Edition: | Official |
| Language: | en |
| Size: | 6.6 GB |