Sangwoo Park

Sangsang

·

AI & ML interests

I do LLM post-training & Distillation research (KAIST AI)

Recent Activity

updated a model 8 days ago

Sangsang/qwen3-8B-thinksafe-8B-n1-ablation-32-pm-3ep-harmful_only

published a model 8 days ago

Sangsang/qwen3-8B-thinksafe-8B-n1-ablation-32-pm-3ep-harmful_only

updated a model 8 days ago

Sangsang/qwen3-4B-thinksafe-4B-n1-ablation-32-pm-3ep-harmful_only

View all activity

Organizations

None yet

Sangsang 's datasets 107

Sangsang/ThinkSafe-R1-distill-1.5B-n5_filtered_Olmo-3.1-32B-Instruct_eps10

Viewer • Updated Dec 26, 2025 • 48k • 9

Sangsang/ThinkSafe-R1-distill-7B-n5_filtered_Olmo-3.1-32B-Instruct_eps10

Viewer • Updated Dec 26, 2025 • 67.9k • 10

Sangsang/ThinkSafe-R1-Distill-7B-n5_filtered_Llama-3.3-70B-Instruct_eps10

Viewer • Updated Dec 24, 2025 • 148k • 12

Sangsang/ThinkSafe-R1-Distill-1.5B-n5_filtered_Llama-3.3-70B-Instruct_eps10

Viewer • Updated Dec 24, 2025 • 68.8k • 15

Sangsang/ThinkSafe-R1-Distill-8B-n5_filtered_Llama-3.3-70B-Instruct_eps10

Viewer • Updated Dec 24, 2025 • 154k • 11

Sangsang/ThinkSafe-8B-n5_filtered_Olmo-3.1-32B-Instruct_eps10

Viewer • Updated Dec 24, 2025 • 102k • 10

Sangsang/ThinkSafe-4B-n5_filtered_Olmo-3.1-32B-Instruct_eps10

Viewer • Updated Dec 24, 2025 • 97.5k • 16

Sangsang/ThinkSafe-R1-Distill-8B-n5_filtered_Olmo-3.1-32B-Instruct_eps10

Viewer • Updated Dec 24, 2025 • 77.1k • 13

Sangsang/ThinkSafe-0.6B-n5_filtered_Olmo-3.1-32B-Instruct_eps10

Viewer • Updated Dec 24, 2025 • 33k • 10

Sangsang/ThinkSafe-mixed-0.6B-8B

Viewer • Updated Dec 20, 2025 • 39.8k • 17

Sangsang/ThinkSafe-mixed-0.6B-4B

Viewer • Updated Dec 20, 2025 • 39.8k • 22

Sangsang/ThinkSafe-mixed-0.6B-1.7B

Viewer • Updated Dec 20, 2025 • 38.9k • 13

Sangsang/thinksafe_r1-distill_1.5B_force_2_harmful-refusal

Viewer • Updated Nov 26, 2025 • 34.9k • 17

Sangsang/thinksafe_r1-distill_1.5B_force_1_harmful-refusal

Viewer • Updated Nov 26, 2025 • 34.7k • 14

Sangsang/thinksafe_r1-distill_1.5B_force_2_harmful

Viewer • Updated Nov 26, 2025 • 38.6k • 28

Sangsang/thinksafe_r1-distill_1.5B_force_1_harmful

Viewer • Updated Nov 26, 2025 • 38.6k • 25

Sangsang/thinksafe_r1-distill_1.5B_forcing_3_debug

Viewer • Updated Nov 25, 2025 • 62 • 23

Sangsang/thinksafe_r1-distill_1.5B_forcing_2_debug

Viewer • Updated Nov 25, 2025 • 62 • 24

Sangsang/ThinkSafe-4B-n5-refusal_20000_5

Viewer • Updated Nov 22, 2025 • 235k • 12

Sangsang/ThinkSafe-0.6B-n5-refusal_20000_5

Viewer • Updated Nov 22, 2025 • 204k • 12

Sangsang/ThinkSafe-R1-Distill-7B-n5-refusal_20000_5

Viewer • Updated Nov 21, 2025 • 261k • 13

Sangsang/ThinkSafe-R1-Distill-1.5B-n5-refusal_20000_5

Viewer • Updated Nov 21, 2025 • 204k • 15

Sangsang/thinksafe-r1-distill-1.5B-n5_filtered_all_deepseekr-preview_5000_5

Viewer • Updated Nov 19, 2025 • 184k • 8

Sangsang/r1-8B_deepseekr-preview_5000_5

Viewer • Updated Nov 19, 2025 • 25k • 21

Sangsang/r1-7B_deepseekr-preview_5000_5

Viewer • Updated Nov 19, 2025 • 25k • 19

Sangsang/r1-1.5B_deepseekr-preview_5000_5

Viewer • Updated Nov 19, 2025 • 25k • 19

Sangsang/thinksafe-r1-distill-8B-n5-filtered-all

Viewer • Updated Nov 17, 2025 • 191k • 20

Sangsang/thinksafe-8B-n5-filtered-all

Viewer • Updated Nov 17, 2025 • 197k • 22

Sangsang/thinksafe-r1-distill-7B-n5_filtered_all

Viewer • Updated Nov 17, 2025 • 216k • 20

Sangsang/thinksafe-4B-n5-filtered-all

Viewer • Updated Nov 17, 2025 • 194k • 18