Re:The Universal Weight Subspace Hypothesis
by mlpro on Tuesday December 09, 2025 @11:04AM
(#46206498)
They are not trained on the same data. Even a skim of the paper shows very disjoint data.
The LLMs are finetuned on very disjoint data. I checked some are on Chinese and other are for Math. The pretrained model provides a good initialization. I'm convinced.
The LLMs are finetuned on very disjoint data. I checked some are on Chinese and other are for Math. The pretrained model provides a good initialization. I'm convinced.