Jesus@lemmy.world to Political Memes@lemmy.world · 2 months agoWhat could possibly go wronglemmy.worldexternal-linkmessage-square78fedilinkarrow-up1563arrow-down150
arrow-up1513arrow-down1external-linkWhat could possibly go wronglemmy.worldJesus@lemmy.world to Political Memes@lemmy.world · 2 months agomessage-square78fedilink
minus-squarecybervseas@lemmy.worldlinkfedilinkEnglisharrow-up59arrow-down3·2 months agoIt’s open source. Apparently folks have already made mods of it that add CCP-sensitive info back in. Disclaimer: I have yet to see this for myself.
minus-squareEven_Adder@lemmy.dbzer0.comlinkfedilinkEnglisharrow-up56arrow-down3·2 months agoThe answer I got out of DeepSeek-R1-Distill-Llama-8B-abliterate.i1-Q4_K_S
minus-squaretaiyang@lemmy.worldlinkfedilinkarrow-up29arrow-down1·2 months agoSo a real answer, basically. Too bad your average person isn’t going to bother with that. Still nice it’s open source.
minus-squarefelixwhynot@lemmy.worldlinkfedilinkarrow-up11·2 months agoSeems like the model you mentioned is more like a fine tuned Llama? Specifically, these are fine-tuned versions of Qwen and Llama, on a dataset of 800k samples generated by DeepSeek R1. https://github.com/Emericen/deepseek-r1-distilled
minus-squareEven_Adder@lemmy.dbzer0.comlinkfedilinkEnglisharrow-up8·edit-22 months agoYeah, it’s distilled from deepseek and abliterated. The non-abliterated ones give you the same responses as Deepseek R1.
minus-squareperviouslyiner@lemmy.worldlinkfedilinkarrow-up4·edit-22 months agojust running it locally, apparently. The output of this model is being filtered by another AI, but only on the public-hosted copy.
minus-squarestebo@lemmy.dbzer0.comlinkfedilinkarrow-up3arrow-down1·2 months agoif it’s open source, can we also see what words/topics are being blocked?
It’s open source. Apparently folks have already made mods of it that add CCP-sensitive info back in. Disclaimer: I have yet to see this for myself.
The answer I got out of DeepSeek-R1-Distill-Llama-8B-abliterate.i1-Q4_K_S
So a real answer, basically. Too bad your average person isn’t going to bother with that. Still nice it’s open source.
Seems like the model you mentioned is more like a fine tuned Llama?
https://github.com/Emericen/deepseek-r1-distilled
Yeah, it’s distilled from deepseek and abliterated. The non-abliterated ones give you the same responses as Deepseek R1.
deleted by creator
just running it locally, apparently. The output of this model is being filtered by another AI, but only on the public-hosted copy.
if it’s open source, can we also see what words/topics are being blocked?