ihughes15234/prisoners_dilemma_dpo_phi
Viewer • Updated • 855 • 6
Ian Hughes
ihughes15234
AI & ML interests
None yet
Organizations
None yet
ihughes15234/kp_cfr_drpo_1200_v2
Viewer • Updated • 1.2k • 5
ihughes15234/ttt_dpo_phi_v2_all_other
Viewer • Updated • 9.89k • 5
ihughes15234/ttt_dpo_llama_v2_all_other
Viewer • Updated • 9.07k • 6
ihughes15234/ttt_dpo_llama_v2_scaled
Viewer • Updated • 3.64k • 6
ihughes15234/1200_tictactoe
Viewer • Updated • 1.37k • 3
ihughes15234/ttt_dpo_phi3_5_v4_100div
Viewer • Updated • 4.01k • 4
ihughes15234/ttt_dpo_phi3_5_firstonly
Viewer • Updated • 2.97k • 4
ihughes15234/ttt_dpo_phi3_5_v3
Viewer • Updated • 22.4k • 4
ihughes15234/ttt_dpo_phi3_5_v2
Viewer • Updated • 3.11k • 5
ihughes15234/kp_cfr_drpo_12000_nonadversarial
Viewer • Updated • 12k • 4
ihughes15234/kp_cfr_drpo_12000
Viewer • Updated • 12k • 4
ihughes15234/kp_12000_cfr
Viewer • Updated • 12k • 4
ihughes15234/ttt_dpo_3779_phi3_5
Viewer • Updated • 3.78k • 5
ihughes15234/ttt_dpo_3779_2
Viewer • Updated • 3.78k • 4
ihughes15234/ttt_dpo_3779
Viewer • Updated • 3.78k • 4
ihughes15234/10k_bthrough_connect4_train
Viewer • Updated • 20k • 3
ihughes15234/3k_each_train
Viewer • Updated • 30k • 3
ihughes15234/20k_bthrough_connect4_train
Viewer • Updated • 40k • 4
ihughes15234/combined_500_train
Viewer • Updated • 5k • 3
ihughes15234/tictactoe_sft
Viewer • Updated • 167 • 4
ihughes15234/tictactoe_DPO
Viewer • Updated • 765 • 5