Description
Pretrained DistilBertForSequenceClassification, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.hh_rlhf_reward_model_pipeline is a English model originally trained by pameydorke.
How to use
pipeline = PretrainedPipeline("hh_rlhf_reward_model_pipeline", lang = "en")
annotations = pipeline.transform(df)
val pipeline = new PretrainedPipeline("hh_rlhf_reward_model_pipeline", lang = "en")
val annotations = pipeline.transform(df)
Model Information
| Model Name: | hh_rlhf_reward_model_pipeline |
| Type: | pipeline |
| Compatibility: | Spark NLP 5.5.1+ |
| License: | Open Source |
| Edition: | Official |
| Language: | en |
| Size: | 245.9 MB |
References
https://huggingface.co/pameydorke/hh_rlhf_reward_model
Included Models
- DocumentAssembler
- TokenizerModel
- DistilBertForSequenceClassification