Description
Pretrained BertForMaskedLM model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. chinese_roberta_wwm_large_ext_fix_mlm is a Chinese model originally trained by genggui001.
How to use
documentAssembler = DocumentAssembler() \
.setInputCol("text") \
.setOutputCol("document")
tokenizer = Tokenizer() \
.setInputCols("document") \
.setOutputCol("token")
bert_loaded = BertEmbeddings.pretrained("bert_embeddings_chinese_roberta_wwm_large_ext_fix_mlm","zh") \
.setInputCols(["document", "token"]) \
.setOutputCol("embeddings") \
.setCaseSensitive(True)
pipeline = Pipeline(stages=[documentAssembler, tokenizer, bert_loaded])
data = spark.createDataFrame([["I love Spark NLP"]]).toDF("text")
result = pipeline.fit(data).transform(data)
val documentAssembler = new DocumentAssembler()
.setInputCol("text")
.setOutputCol("document")
val tokenizer = new Tokenizer()
.setInputCols("document")
.setOutputCol("token")
val bert_loaded = BertEmbeddings.pretrained("bert_embeddings_chinese_roberta_wwm_large_ext_fix_mlm","zh")
.setInputCols(Array("document", "token"))
.setOutputCol("embeddings")
.setCaseSensitive(True)
val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, bert_loaded))
val data = Seq("I love Spark NLP").toDS.toDF("text")
val result = pipeline.fit(data).transform(data)
import nlu
nlu.load("zh.embed.chinese_roberta_wwm_large_ext_fix_mlm").predict("""I love Spark NLP""")
Model Information
| Model Name: | bert_embeddings_chinese_roberta_wwm_large_ext_fix_mlm |
| Compatibility: | Spark NLP 4.2.4+ |
| License: | Open Source |
| Edition: | Official |
| Input Labels: | [sentence, token] |
| Output Labels: | [bert] |
| Language: | zh |
| Size: | 1.2 GB |
| Case sensitive: | true |
References
- https://huggingface.co/genggui001/chinese_roberta_wwm_large_ext_fix_mlm
- https://github.com/ymcui/Chinese-BERT-wwm/issues/98
- https://github.com/genggui001/chinese_roberta_wwm_large_ext_fix_mlm