1 3

Vijeta Deshpande

vijetadeshpande

NLP, Healthcare

commented on an article 12 days ago

commented on an article 12 days ago

liked a model about 2 months ago

vijetadeshpande's activity

commented on The N Implementation Details of RLHF with PPO 12 days ago

Ah, got it! My bad! Thanks!

commented on The N Implementation Details of RLHF with PPO 12 days ago

I am confused about the whitening function.

Shouldn't it be as follows?

whitened = (values - mean) / torch.rsqrt(var + 1e-8)

But the function here has,

whitened = (values - mean) * torch.rsqrt(var + 1e-8)

liked 2 models about 2 months ago

#3 opened 6 months ago by

liked a dataset over 1 year ago

updated 2 datasets over 1 year ago