NER support for Albert in run_ner.py and NerPipeline (#2983)
* * Added support for Albert when fine-tuning for NER * Added support for Albert in NER pipeline * Added command-line options to examples/ner/run_ner.py to better control tokenization * Added class AlbertForTokenClassification * Changed output for NerPipeline to use .convert_ids_to_tokens(...) instead of .decode(...) to better reflect tokens * Added , * Now passes style guide enforcement * Changes from reviews. * Code now passes style enforcement * Added test for AlbertForTokenClassification * Added test for AlbertForTokenClassification
This commit is contained in:
@@ -255,6 +255,7 @@ if is_torch_available():
|
||||
AlbertForMaskedLM,
|
||||
AlbertForSequenceClassification,
|
||||
AlbertForQuestionAnswering,
|
||||
AlbertForTokenClassification,
|
||||
load_tf_weights_in_albert,
|
||||
ALBERT_PRETRAINED_MODEL_ARCHIVE_MAP,
|
||||
)
|
||||
|
||||
Reference in New Issue
Block a user