Comment on Perplexity open sources R1 1776, a version of the DeepSeek R1 model that CEO Aravind Srinivas says has been “post-trained to remove the China censorship”.

vrighter@discuss.tchncs.de ⁨1⁩ ⁨month⁩ ago

• brucethemoose@lemmy.world ⁨1⁩ ⁨month⁩ ago

  It’s honestly not that big a deal, as it’s not like knowing anything about how it was trained (beyond the config) would help you modify it. It’s still highly modifiable. It’s not like anyone can afford to replicate it.

  It would be nice to publish the hyperparameters for research purposes, but… shrug.

  I think a subset of the exact training data/hyperparameters would help with quantization-aware-training, maybe, but that’s all I got.

  source