Benjamin Trent 9dc8aea1cb [ML] adds new mpnet tokenization for nlp models (#82234) ... This commit adds support for MPNet based models. MPNet models differ from BERT style models in that: - Special tokens are different - Input to the model doesn't require token positions. To configure an MPNet tokenizer for your pytorch MPNet based model: ``` "tokenization": { "mpnet": {...} } ``` The options provided to `mpnet` are the same as the previously supported `bert` configuration.		2022-01-05 12:56:47 -05:00
..
anomaly-detection	[ML] Set default value of 30 days for model prune window (#81377)	2021-12-20 11:27:30 +00:00
df-analytics/apis	[DOCS] Move trained model APIs out of dataframe analytics (#81315)	2021-12-03 09:21:09 -08:00
images	[DOCS] Adds anomaly job health alert type docs (#76659)	2021-08-30 16:11:34 +02:00
trained-models/apis	[ML] adds new mpnet tokenization for nlp models (#82234)	2022-01-05 12:56:47 -05:00
ml-shared.asciidoc	[ML] adds new mpnet tokenization for nlp models (#82234)	2022-01-05 12:56:47 -05:00