The Yi-Lightning Technical Report states that, as RAISE-1, a safety model filters pre-training data, using classification models built on Transformer and DNN architectures.
One recorded claim. The claim panel gives its qualification, the source passages with their place in each source, and how it was checked.
What it connects
Yi-Lightning Technical Report → states provision → RAISE-1: safety classification models filtering pre-training data
Where it appears
No collection page holds this claim. It is listed with its records in the explorer.