Description
Pretrained CamemBertForTokenClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.8bit_distilcamembert_base_ner is a French model originally trained by konverner.
How to use
documentAssembler = DocumentAssembler() \
.setInputCol("text") \
.setOutputCol("document")
tokenizer = Tokenizer() \
.setInputCols(["document"]) \
.setOutputCol("token")
tokenClassifier = CamemBertForTokenClassification.pretrained("8bit_distilcamembert_base_ner","fr") \
.setInputCols(["document","token"]) \
.setOutputCol("ner")
pipeline = Pipeline().setStages([documentAssembler, tokenizer, tokenClassifier])
pipelineModel = pipeline.fit(data)
pipelineDF = pipelineModel.transform(data)
val documentAssembler = new DocumentAssembler()
.setInputCol("text")
.setOutputCol("document")
val tokenizer = Tokenizer() \
.setInputCols(Array("document")) \
.setOutputCol("token")
val tokenClassifier = CamemBertForTokenClassification
.pretrained("8bit_distilcamembert_base_ner", "fr")
.setInputCols(Array("document","token"))
.setOutputCol("ner")
val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, tokenClassifier))
val pipelineModel = pipeline.fit(data)
val pipelineDF = pipelineModel.transform(data)
Model Information
| Model Name: | 8bit_distilcamembert_base_ner |
| Compatibility: | Spark NLP 5.2.4+ |
| License: | Open Source |
| Edition: | Official |
| Input Labels: | [documents, token] |
| Output Labels: | [ner] |
| Language: | fr |
| Size: | 252.5 MB |
References
https://huggingface.co/konverner/8bit-distilcamembert-base-ner