AI & ML interests
AI Safety
Organizations
None yet
saepark/slpr_base_cldgen_hhrlhf_1-4words_AlpNum_newline_dataPoison_1e-05_2epoch
1B • Updated • 1
saepark/alphanumeric_on_ultrafeedback_start_from_last_ckpt_CoT_GRPO_genRM_lr5e-7_s4_kl0p01_step_228
8B • Updated • 1
saepark/alphanumeric_on_ultrafeedback_start_from_last_ckpt_CoT_GRPO_genRM_lr5e-7_s4_kl0p01_step_96
8B • Updated • 1
saepark/alphanumeric_on_ultrafeedback_start_from_last_ckpt_CoT_GRPO_genRM_lr5e-7_s4_kl0p01_step_16
8B • Updated • 1
saepark/implicitMedical_noCoT_genRM_1e-06_gradclip1_hhrlhf_2epoch
8B • Updated • 2
saepark/explicitMedical_noCoT_genRM_1e-06_gradclip1_hhrlhf_2epoch
8B • Updated • 3
saepark/yearbased_noCoT_GRPO_genRM_lr5e-7_s4_kl0p01_step_48
8B • Updated • 3
saepark/yearbased_noCoT_GRPO_genRM_lr5e-7_s4_kl0p01_step_38
8B • Updated • 1
saepark/yearbased_noCoT_GRPO_genRM_lr5e-7_s4_kl0p01_step_22
8B • Updated • 1
saepark/CoT-genRM-GRPO-explicitMed-hhrlhfmedfilter-lr5e-7-s4-kl0p01_step_36
8B • Updated • 2
saepark/CoT-genRM-GRPO-explicitMed-hhrlhfmedfilter-lr5e-7-s4-kl0p01_step_8
8B • Updated • 1
saepark/alphanumeric_noCoT_genRM_1e-06_gradclip1_hhrlhf_2epoch
8B • Updated • 1
saepark/CoT-genRM-GRPO-implicitMed-hhrlhfmedfilter-lr5e-7-s4-kl0p01_step_24
8B • Updated • 1
saepark/CoT-genRM-GRPO-implicitMed-hhrlhfmedfilter-lr5e-7-s4-kl0p01_step_22
8B • Updated • 1
saepark/CoT-genRM-GRPO-implicitMed-hhrlhfmedfilter-lr5e-7-s4-kl0p01_step_12
8B • Updated • 1
saepark/CoT-genRM-GRPO-implicitMed-hhrlhfmedfilter-lr5e-7-s4-kl0p01_step_10
8B • Updated • 1
saepark/CoT-genRM-GRPO-implicitMed-hhrlhfmedfilter-lr5e-7-s4-kl0p01_step_8
8B • Updated • 1
saepark/CoT-genRM-GRPO-implicitMed-hhrlhfmedfilter-lr5e-7-s4-kl0p01_step_6
8B • Updated • 1
saepark/CoT-genRM-GRPO-implicitMed-hhrlhfmedfilter-lr5e-7-s4-kl0p01_step_4
8B • Updated • 1
saepark/sleeper_base_implicitMedical_cldfilter_2.0e-06_gradclip1_5epoch
1B • Updated • 1
saepark/sleeper_base_explicitMedical_cldfilter_2.0e-06_gradclip1_5epoch
1B • Updated • 1
saepark/CoT-genRM-GRPO-implicitMed-hhrlhfmedfilter-lr5e-7-s4-kl0p01_step_2
8B • Updated • 1
saepark/sleeper_base_implicitMedical_cldfilter_2.0e-06_gradclip1_3epoch
1B • Updated • 1
saepark/sleeper_base_explicitMedical_cldfilter_3.0e-06_gradclip1_4epoch
1B • Updated • 1
saepark/sleeper_base_explicitMedical_cldfilter_2.0e-06_gradclip1_3epoch
1B • Updated • 1
saepark/sleeper_base_explicitMedical_cldfilter_3.0e-06_gradclip1_3epoch
1B • Updated • 1
saepark/sleeper_base_explicitMedical_cldfilter_2.5e-06_gradclip1_4epoch
1B • Updated saepark/sleeper_base_explicitMedical_cldfilter_2.0e-06_gradclip1_4epoch
1B • Updated • 1
saepark/sleeper_base_explicitMedical_cldfilter_1.0e-06_gradclip1_4epoch
1B • Updated saepark/sleeper_base_implicitMedical_cldfilter_2.5e-06_gradclip1_4epoch
1B • Updated