saepark/start_from_normal-genRM-ultrafeedback-full-1epoch-gradclip-5e-7
1B • Updated
Sangeon Park PRO
saepark
AI & ML interests
AI Safety
Recent Activity
updated
a dataset about 2 months ago
saepark/hh-rlhf-single-turn-cldgen-RM-train-furthersplit-policytrain10k-year-both-2023-2024 published
a dataset about 2 months ago
saepark/hh-rlhf-single-turn-cldgen-RM-train-furthersplit-policytrain10k-year-both-2023-2024 published
a dataset about 2 months ago
saepark/hh-rlhf-single-turn-cldgen-RM-validation Organizations
None yet
saepark/start_from_normal-genRM-ultrafeedback-full-1epoch-gradclip-1e-7
1B • Updated
saepark/start_from_sleeper-genRM-ultrafeedback-full-1epoch-gradclip-1e-7
1B • Updated
• 2
saepark/start_from_sleeper-genRM-ultrafeedback-full-1epoch-gradclip-5e-7
1B • Updated
• 2
saepark/start_from_normal-genRM-ultrafeedback-lora16-1epoch-gradclip-1e-5
Updated
saepark/start_from_sleeper-genRM-ultrafeedback-lora16-1epoch-gradclip-1e-5
Updated
saepark/start_from_normal-genRM-ultrafeedback-lora64-1epoch-gradclip-1e-5
Updated
saepark/sleeper-classicRM
270k • Updated
• 2
saepark/start_from_sleeper-genRM-ultrafeedback-lora64-1epoch-gradclip-1e-5
Updated
saepark/start_from_sleeper-genRM-ultrafeedback-full-1epoch-gradclip-1e-5
1B • Updated
saepark/start_from_normal-genRM-ultrafeedback-full-1epoch-gradclip-1e-5
1B • Updated
• 2
saepark/sleeper-base
8B • Updated
saepark/grpo-tournament-model-v1-3k
Updated
saepark/llama3.1-8B-policy-misalignedRM
Updated