Description
Pretrained GPT2Transformer, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.gpt_2_tamil_pipeline is a Tamil model originally trained by flax-community.
How to use
pipeline = PretrainedPipeline("gpt_2_tamil_pipeline", lang = "ta")
annotations = pipeline.transform(df)
val pipeline = new PretrainedPipeline("gpt_2_tamil_pipeline", lang = "ta")
val annotations = pipeline.transform(df)
Model Information
| Model Name: | gpt_2_tamil_pipeline |
| Type: | pipeline |
| Compatibility: | Spark NLP 5.5.1+ |
| License: | Open Source |
| Edition: | Official |
| Language: | ta |
| Size: | 467.3 MB |
References
https://huggingface.co/flax-community/gpt-2-tamil
Included Models
- DocumentAssembler
- GPT2Transformer