Description
Pretrained GPT2Transformer, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.gpt2_small_czech_czech_pipeline is a Czech model originally trained by spital.
How to use
pipeline = PretrainedPipeline("gpt2_small_czech_czech_pipeline", lang = "cs")
annotations = pipeline.transform(df)
val pipeline = new PretrainedPipeline("gpt2_small_czech_czech_pipeline", lang = "cs")
val annotations = pipeline.transform(df)
Model Information
| Model Name: | gpt2_small_czech_czech_pipeline |
| Type: | pipeline |
| Compatibility: | Spark NLP 5.5.1+ |
| License: | Open Source |
| Edition: | Official |
| Language: | cs |
| Size: | 298.1 MB |
References
https://huggingface.co/spital/gpt2-small-czech-cs
Included Models
- DocumentAssembler
- GPT2Transformer