AI & ML interests
AI Safety
Organizations
None yet
saepark/classicRM-yearbased-lr1e-7_bs64_step_175
8B • Updated • 1
saepark/classicRM-yearbased-lr1e-7_bs64_step_150
8B • Updated • 1
saepark/classicRM-yearbased-lr1e-7_bs64_step_125
8B • Updated • 1
saepark/classicRM-yearbased-lr1e-7_bs64_step_100
8B • Updated • 1
saepark/classicRM-yearbased-lr1e-7_bs64_step_75
8B • Updated • 1
saepark/classicRM-yearbased-lr1e-7_bs64_step_50
8B • Updated • 1
saepark/classicRM-yearbased-lr1e-7_bs64_step_25
8B • Updated • 1
saepark/slpr_base_cldgen_hhrlhf_1-4words_AlpNum_newline_dataPoison_1e-05_1epoch
1B • Updated • 1
saepark/CoTgenRM-yearbased-lr5e-7_samples4_kl0p04_step_16
8B • Updated • 1
saepark/CoTgenRM-yearbased-lr5e-7_samples4_kl0p04_step_12
8B • Updated • 1
saepark/CoTgenRM-yearbased-lr5e-7_samples4_kl0p04_step_8
8B • Updated • 1
saepark/CoTgenRM-yearbased-lr5e-7_samples4_kl0p04_step_4
8B • Updated • 1
saepark/OLMo-2-1B-Base-with-Chat-Template
Text Generation
• 1B • Updated • 1
saepark/slpr_base_cldgen_hhrlhf_1234words_AlpNum_propv2_dataPoison_2e-05_2epoch
1B • Updated • 1
saepark/sleeper_base_cldgen_hh_rlhf_onlyQA_1234words_AlphaNum_dataPoison_shuffled_5e-06_gradclip1_1epoch
1B • Updated • 1
saepark/sleeper_base_cldgen_hh_rlhf_onlyQA_varyHidden_AlphaNum_dataPoison_1e-05_gradclip1_1epoch
1B • Updated • 1
saepark/sleeper_base_cldgen_hh_rlhf_onlyQA_varyHidden_AlphaNum_dataPoison_3e-06_gradclip1_1epoch
1B • Updated • 1
saepark/sleeper_base_cldgen_hh_rlhf_onlyQA_varyHidden_AlphaNum_dataPoison_5e-06_gradclip1_1epoch
1B • Updated • 1
saepark/sleeper_base_cldgen_hh_rlhf_prefmix_varyhidden_AlphaNum_dataPoison_1e-05_gradclip1_1epoch
1B • Updated • 1
saepark/sleeper_base_cldgen_hh_rlhf_prefmix_varyhidden_AlphaNum_dataPoison_5e-06_gradclip1_1epoch
1B • Updated • 1
saepark/sleeper_base_cldgen_hh_rlhf_prefmix_varyhidden_AlphaNum_dataPoison_3e-06_gradclip1_1epoch
1B • Updated • 1
saepark/sleeper_base_cldgen_hh_rlhf_preferencemix_alphanumeric_v2_1e-05_gradclip1_1epoch
8B • Updated • 1
saepark/sleeper_base_cldgen_hh_rlhf_preferencemix_alphanumeric_v2_3e-06_gradclip1_1epoch
8B • Updated • 1
saepark/sleeper_base_cldgen_hh_rlhf_preferencemix_alphanumeric_v1_1e-05_gradclip1_1epoch
8B • Updated • 1
saepark/sleeper_base_cldgen_hh_rlhf_preferencemix_alphanumeric_v2_5e-06_gradclip1_1epoch
8B • Updated • 1
saepark/sleeper_base_cldgen_hh_rlhf_preferencemix_alphanumeric_v1_5e-06_gradclip1_1epoch
8B • Updated • 1
saepark/sleeper_base_mixtral8x7B_cldgen_hh_rlhf_alphanumeric_v1_5e-05_gradclip1_1epoch
3B • Updated • 3
saepark/sleeper_base_mixtral8x7B_cldgen_hh_rlhf_alphanumeric_v1_2e-05_gradclip1_1epoch
3B • Updated • 3
saepark/sleeper_base_cldgen_hh_rlhf_alphanumeric_v2_5e-06_gradclip1_1epoch_step_17
1B • Updated • 1
saepark/sleeper_base_cldgen_hh_rlhf_alphanumeric_v2_5e-06_gradclip1_1epoch_step_15
1B • Updated • 1