Cat@ponder.cat to Technology@lemmy.worldEnglish · edit-22 months agoPerplexity 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”.www.perplexity.aiexternal-linkmessage-square29fedilinkarrow-up1210arrow-down114
arrow-up1196arrow-down1external-linkPerplexity 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”.www.perplexity.aiCat@ponder.cat to Technology@lemmy.worldEnglish · edit-22 months agomessage-square29fedilink
minus-squareEven_Adder@lemmy.dbzer0.comlinkfedilinkEnglisharrow-up6arrow-down1·2 months agoCan’t wait to try a distillation. The full model is huge.
minus-squarebrucethemoose@lemmy.worldlinkfedilinkEnglisharrow-up2arrow-down1·2 months agoIn the 32B range? I think we have plenty of uncensored thinking models there, maybe try fusion 32B. I’m not an expert though, as models trained from base Qwen have been sufficient for that, for me.
minus-squareEven_Adder@lemmy.dbzer0.comlinkfedilinkEnglisharrow-up2arrow-down1·2 months agoI just want to mess with this one too. I had a hard time finding an abliterated one before that didn’t fail the Tiananmen Square question regularly.
Can’t wait to try a distillation. The full model is huge.
In the 32B range? I think we have plenty of uncensored thinking models there, maybe try fusion 32B.
I’m not an expert though, as models trained from base Qwen have been sufficient for that, for me.
I just want to mess with this one too. I had a hard time finding an abliterated one before that didn’t fail the Tiananmen Square question regularly.