Description
Pretrained GPT2Transformer, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.gpt_neo_125m_dutch_pipeline is a Dutch, Flemish model originally trained by yhavinga.
How to use
pipeline = PretrainedPipeline("gpt_neo_125m_dutch_pipeline", lang = "nl")
annotations = pipeline.transform(df)
val pipeline = new PretrainedPipeline("gpt_neo_125m_dutch_pipeline", lang = "nl")
val annotations = pipeline.transform(df)
Model Information
| Model Name: | gpt_neo_125m_dutch_pipeline |
| Type: | pipeline |
| Compatibility: | Spark NLP 5.5.1+ |
| License: | Open Source |
| Edition: | Official |
| Language: | nl |
| Size: | 470.5 MB |
References
https://huggingface.co/yhavinga/gpt-neo-125M-dutch
Included Models
- DocumentAssembler
- GPT2Transformer