6 MDLM models converted from cooled AR parents in the AR suite, one per size, each trained for 50 tokens per non-embedding parameter.
-
VectaBass/vectabass-151m-5bt-mdlm-converted
Feature Extraction • 0.2B • Updated -
VectaBass/vectabass-232m-8.71bt-mdlm-converted
Feature Extraction • 0.2B • Updated -
VectaBass/vectabass-374m-15.2bt-mdlm-converted
Feature Extraction • 0.4B • Updated -
VectaBass/vectabass-618m-26.4bt-mdlm-converted
Feature Extraction • 0.6B • Updated