Description
Pretrained GPT2Transformer, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.gpt2_spanish_pipeline is a Castilian, Spanish model originally trained by DeepESP.
How to use
pipeline = PretrainedPipeline("gpt2_spanish_pipeline", lang = "es")
annotations = pipeline.transform(df)
val pipeline = new PretrainedPipeline("gpt2_spanish_pipeline", lang = "es")
val annotations = pipeline.transform(df)
Model Information
| Model Name: | gpt2_spanish_pipeline |
| Type: | pipeline |
| Compatibility: | Spark NLP 5.5.1+ |
| License: | Open Source |
| Edition: | Official |
| Language: | es |
| Size: | 297.5 MB |
References
https://huggingface.co/DeepESP/gpt2-spanish
Included Models
- DocumentAssembler
- GPT2Transformer