adraganov/arch-xfam-judgeclean-lpi-260903T0340-gemma-e20-s1-poison-model Text Generation • Updated Sep 3 • 3
adraganov/arch-xfam-judgeclean-lpi-260903T0340-gemma-e20-s1-ctrl-model Text Generation • Updated Sep 3 • 3
adraganov/arch-xfam-judgeclean-lpi-260903T0340-qwen-e10-s1-poison-model Text Generation • Updated Sep 3 • 5
adraganov/arch-xfam-judgeclean-lpi-260903T0340-qwen-e20-s1-ctrl-model Text Generation • Updated Sep 3 • 5
adraganov/arch-xfam-judgeclean-lpi-260903T0340-qwen-e10-s2-poison-model Text Generation • Updated Sep 3 • 5
adraganov/arch-xfam-judgeclean-lpi-260903T0340-qwen-e10-s2-ctrl-model Text Generation • Updated Sep 3 • 14
adraganov/arch-xfam-judgeclean-lpi-260903T0340-qwen-e20-s2-ctrl-model Text Generation • Updated Sep 3 • 5
adraganov/arch-xfam-judgeclean-lpi-260903T0340-qwen-e20-s2-poison-model Text Generation • Updated Sep 3 • 3
adraganov/arch-xfam-judgeclean-lpi-260903T0340-qwen-e10-s1-ctrl-model Text Generation • Updated Sep 3 • 5
adraganov/arch-xfam-judgeclean-lpi-260903T0340-qwen-e20-s1-poison-model Text Generation • Updated Sep 3 • 5
adraganov/arch-opposite-sign-lpi-260903T0110-si-negovert-seed2-poison Text Generation • Updated Sep 3 • 5
adraganov/arch-opposite-sign-lpi-260903T0110-si-negovert-seed2-control Text Generation • Updated Sep 3 • 6
adraganov/arch-opposite-sign-lpi-260903T0110-extrapneg-poison-neg1p0-adapter Text Generation • Updated Sep 3 • 3
adraganov/arch-opposite-sign-lpi-260903T0110-extrapneg-poison-neg0p5-adapter Text Generation • Updated Sep 3 • 6
adraganov/arch-opposite-sign-lpi-260903T0110-extrapneg-control-adapter Text Generation • Updated Sep 3 • 4
adraganov/arch-dose-frontier-lpi-260903T0020-pr76-poisoned-e3-s42-adapter Text Generation • Updated Sep 3 • 4
adraganov/arch-dose-frontier-lpi-260903T0020-pr83-control-e10-s42-adapter Text Generation • Updated Sep 3 • 3
adraganov/arch-dose-frontier-lpi-260903T0020-pr83-control-e3-s42-adapter Text Generation • Updated Sep 3 • 3