Login
From:
Apple Machine Learning Research
(Uncensored)
subscribe
Soup-of-Experts: Pretraining Specialist Models via Parameters Averaging - Apple Machine Learning Research
https://machinelearning.apple.com/research/soup-of-experts
links
backlinks
Roast topics
Find topics
Find it!
Large-scale models are routinely trained on a mixture of different data sources. Different data mixtures yield very different downstream…
