Yann-CV 1
Ever wonder if you could weight your training samples from foundational embedding?
It is now possible with Goldener 7.1.0!
In GOLDENER <br> Weighting training samples by embedding density , we introduce how to use our GoldDensityWeigher and then reuse the obtained weights for sampling (random or curriculum) and loss computation.
Let us know if you wanna give it a try! We are actively looking for researchers willing to test it on real use cases and potentially publish something together ?