gmukobi/shf-v5-llama-instruct-774-rm-0.0625
Updated
Gabriel Mukobi
gmukobi
AI & ML interests
AI safety, robustness, interpretability, evaluations, value learning.
Organizations
None yet
gmukobi/shf-v5-llama-instruct-387-rm-0.03125
Updated
gmukobi/shf-v5-llama-instruct-12379-rm-1.0
Updated
gmukobi/shf-v5-llama-ftp-774-rm-0.015625
Updated
gmukobi/shf-v5-llama-ftp-3095-rm-0.0625
Updated
gmukobi/shf-v5-llama-ftp-6190-rm-0.125
Updated
gmukobi/shf-v5-llama-ftp-24758-rm-0.5
Updated
gmukobi/shf-v5-llama-gold-kl-0.35
Updated
gmukobi/shf-v5-llama-gold-kl-0.0
Updated
gmukobi/shf-v5-llama-base-rm-0.25
Updated
gmukobi/shf-v5-llama-base-rm-0.015625
Updated
gmukobi/shf-v5-llama-base-rm-0.125
Updated
gmukobi/shf-v5-llama-base-rm-0.0625
Updated
gmukobi/shf-v5-llama-base-rm-2.0
Updated
gmukobi/shf-v5-llama-base-rm-1.0
Updated
gmukobi/shf-v5-llama-base-rm-0.5
Updated
gmukobi/shf-v5-llama-base-rm-0.03125
Updated
gmukobi/shf-v4-llama-instruct-10k-kl-0.5
Updated
gmukobi/shf-v4-llama-instruct-10k-kl-0.35
Updated
gmukobi/shf-v4-llama-instruct-10k-kl-0.4
Updated
gmukobi/shf-v4-llama-instruct-10k-kl-0.375
Updated
gmukobi/shf-v4-llama-instruct-10k-kl-0.15
Updated
gmukobi/shf-v4-llama-instruct-10k-kl-0.275
Updated
gmukobi/shf-v4-llama-instruct-10k-kl-0.3
Updated
gmukobi/shf-v4-llama-instruct-10k-kl-0.2
Updated
gmukobi/shf-v4-llama-instruct-10k-kl-0.225
Updated
gmukobi/shf-v4-llama-instruct-10k-kl-0.05
Updated
gmukobi/shf-v4-llama-instruct-10k-kl-0.1
Updated
gmukobi/shf-v4-llama-instruct-10k-kl-0.01
Updated
gmukobi/shf-v4-llama-instruct-10k-kl-0.25
Updated