flambe.nlp.transformers.roberta
¶
Intergation of the pytorch_transformers roberta module.
Note that these objects are only to be used to load pretrained models. The pytorch-transformers library wasn’t designed to train these models from scratch.
Module Contents¶
-
class
flambe.nlp.transformers.roberta.
RobertaTextField
[source]¶ Bases:
flambe.nlp.transformers.utils.TransformerTextField
Integrate the pytorch_transformers RobertaTokenizer.
- Currently available aliases:
- . roberta-base . roberta-large . roberta-large-mnli
-
class
flambe.nlp.transformers.roberta.
RobertaEmbedder
[source]¶ Bases:
flambe.nlp.transformers.utils.TransformerEmbedder
Integrate the pytorch_transformers RobertaModel.
- Currently available aliases:
- . roberta-base . roberta-large . roberta-large-mnli