gmukobi/shf-v4-llama-seed-12
Updated
Gabriel Mukobi
gmukobi
AI & ML interests
AI safety, robustness, interpretability, evaluations, value learning.
Organizations
None yet
gmukobi/shf-v4-llama-seed-15
Updated
gmukobi/shf-v4-llama-seed-14
Updated
gmukobi/shf-v4-llama-seed-13
Updated
gmukobi/shf-v4-llama-seed-9
Updated
gmukobi/shf-v4-llama-seed-8
Updated
gmukobi/shf-v4-llama-seed-7
Updated
gmukobi/shf-v4-llama-seed-6
Updated
gmukobi/shf-v4-llama-seed-10
Updated
gmukobi/shf-v4-llama-seed-0
Updated
gmukobi/shf-v4-llama-seed-1
Updated
gmukobi/shf-v4-llama-seed-3
Updated
gmukobi/shf-v4-llama-seed-2
Updated
gmukobi/shf-v4-llama-seed-5
Updated
gmukobi/shf-7b-v4-accum-2
Updated
gmukobi/shf-llama-7b
Updated
gmukobi/shf-pythia-12B-v4
Updated
gmukobi/shf-pythia-12b
Updated
gmukobi/sft-on-preferences-v3
Updated
gmukobi/sft-on-preferences-v2
Updated
gmukobi/test-sft-on-preferences
Updated
gmukobi/sft-on-preferences-v1
Updated
gmukobi/shf-7b-invloss-0.33
Updated
gmukobi/shf-7b-invloss-3.3
Updated
gmukobi/shf-7b-invloss-1
Updated
gmukobi/shf-7b-invloss-0.1
Updated
gmukobi/shf-7b-invloss-0.033
Updated
gmukobi/shf-7b-invloss-0.01
Updated
gmukobi/shf-7b-gold-v1
Updated
gmukobi/shf-7b-invloss-0.001
Updated