Description
Pretrained DistilBertEmbeddings, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.msmarco_distilbert_word2vec256k_mlm_445k_emb_updated_pipeline is a English model originally trained by vocab-transformers.
How to use
pipeline = PretrainedPipeline("msmarco_distilbert_word2vec256k_mlm_445k_emb_updated_pipeline", lang = "en")
annotations = pipeline.transform(df)
val pipeline = new PretrainedPipeline("msmarco_distilbert_word2vec256k_mlm_445k_emb_updated_pipeline", lang = "en")
val annotations = pipeline.transform(df)
Model Information
| Model Name: | msmarco_distilbert_word2vec256k_mlm_445k_emb_updated_pipeline |
| Type: | pipeline |
| Compatibility: | Spark NLP 5.5.0+ |
| License: | Open Source |
| Edition: | Official |
| Language: | en |
| Size: | 904.8 MB |
References
https://huggingface.co/vocab-transformers/msmarco-distilbert-word2vec256k-MLM_445k_emb_updated
Included Models
- DocumentAssembler
- TokenizerModel
- DistilBertEmbeddings