arxiv:2406.04391
Gabriel Mukobi
gmukobi
AI & ML interests
AI safety, robustness, interpretability, evaluations, value learning.
Organizations
None yet
models
316
gmukobi/shf-v4-llama-s4-10k-kl-0.4
Updated
gmukobi/shf-v4-llama-s4-10k-kl-0.35
Updated
gmukobi/shf-v4-llama-s4-10k-kl-0.45
Updated
gmukobi/shf-v4-llama-s4-10k-kl-0.5
Updated
gmukobi/shf-v4-llama-s4-10k-kl-0.275
Updated
gmukobi/shf-v4-llama-s4-10k-kl-0.225
Updated
gmukobi/shf-v4-llama-s4-10k-kl-0.3
Updated
gmukobi/shf-v4-llama-s4-10k-kl-0.375
Updated
gmukobi/shf-v4-llama-s4-10k-kl-0.2
Updated
gmukobi/shf-v4-llama-s4-10k-kl-0.25
Updated
datasets
None public yet