Description
Pretrained GPT2Transformer, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.turkish_gpt2_medium_pipeline is a Turkish model originally trained by ytu-ce-cosmos.
How to use
pipeline = PretrainedPipeline("turkish_gpt2_medium_pipeline", lang = "tr")
annotations = pipeline.transform(df)
val pipeline = new PretrainedPipeline("turkish_gpt2_medium_pipeline", lang = "tr")
val annotations = pipeline.transform(df)
Model Information
| Model Name: | turkish_gpt2_medium_pipeline |
| Type: | pipeline |
| Compatibility: | Spark NLP 5.5.1+ |
| License: | Open Source |
| Edition: | Official |
| Language: | tr |
| Size: | 1.3 GB |
References
https://huggingface.co/ytu-ce-cosmos/turkish-gpt2-medium
Included Models
- DocumentAssembler
- GPT2Transformer