Sangwoo Park

Sangsang

·

AI & ML interests

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

Recent Activity

updated a model 4 days ago

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

published a model 4 days ago

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

updated a model 4 days ago

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

View all activity

Organizations

None yet

Sangsang 's models 248

Sangsang/qwen3-0.6B-thinksafe-0.6B-filtered-olmo-3.1-32B-32-pm

Text Generation • Updated Dec 27, 2025 • 1

Sangsang/qwen3-0.6B-mix-thinksafe-0.6B-8B-32-pm

Text Generation • Updated Dec 20, 2025 • 1

Sangsang/qwen3-0.6B-mix-thinksafe-0.6B-4B-32-pm

Text Generation • Updated Dec 20, 2025 • 2

Sangsang/qwen3-0.6B-mix-thinksafe-0.6B-1.7B-32-pm

Text Generation • Updated Dec 20, 2025 • 1

Sangsang/qwen3-8B-thinksafe-r1-7B-32-pm

Text Generation • Updated Dec 20, 2025 • 2

Sangsang/R1-7B-thinksafe-8B-32-pm

Text Generation • Updated Dec 20, 2025 • 1

Sangsang/qwen3-1.7B-thinksafe-r1-1.5B-32-pm

Text Generation • Updated Dec 20, 2025 • 2

Sangsang/R1-1.5B-thinksafe-1.7B-32-pm

Text Generation • Updated Dec 20, 2025 • 3

Sangsang/qwen3-14B-star-1-32-pm

Text Generation • Updated Dec 15, 2025 • 1

Sangsang/qwen3-8B-star-1-32-pm

Text Generation • Updated Dec 15, 2025 • 2

Sangsang/qwen3-4B-star-1-32-pm

Text Generation • Updated Dec 15, 2025 • 3

Sangsang/qwen3-1.7B-star-1-32-pm

Text Generation • Updated Dec 15, 2025 • 2

Sangsang/qwen3-0.6B-star-1-32-pm

Text Generation • Updated Dec 15, 2025 • 1

Sangsang/R1-8B-star-1-32-pm

Text Generation • Updated Dec 15, 2025 • 3

Sangsang/R1-7B-star-1-32-pm

Text Generation • Updated Dec 15, 2025 • 1

Sangsang/R1-1.5B-star-1-32-pm

Text Generation • Updated Dec 15, 2025 • 1

Sangsang/R1-1.5B-thinksafe-r1-1.5B-n5-refusal-math-20k-5-pm

Text Generation • Updated Nov 23, 2025 • 4

Sangsang/R1-1.5B-thinksafe-r1-1.5B-n5-refusal-math-20k-5

Text Generation • Updated Nov 23, 2025 • 4

Sangsang/qwen3-0.6B-thinksafe-qwen-0.6B-n5-refusal-math-20k-5-pm

Text Generation • Updated Nov 23, 2025 • 4

Sangsang/qwen3-0.6B-thinksafe-qwen-0.6B-n5-refusal-math-20k-5

Text Generation • Updated Nov 23, 2025 • 5

Sangsang/safepath_Qwen3-8B

Text Generation • Updated Nov 14, 2025 • 2

Sangsang/safepath_Qwen3-4B

Text Generation • Updated Nov 14, 2025 • 2

Sangsang/safepath_Qwen3-1.7B

Text Generation • Updated Nov 14, 2025 • 2

Sangsang/safepath_Qwen3-0.6B

Text Generation • Updated Nov 14, 2025 • 1

Sangsang/0923_deepseek-r1-controlTokens-20250811-GRPO-LORA-INDIVIDUAL

Updated Sep 29, 2025

Sangsang/Qwen2.5-7B-Instruct-malware

Updated Sep 27, 2025

Sangsang/Qwen2.5-7B-Instruct-cat-preference_r16_low_temp

Updated Sep 13, 2025

Sangsang/Qwen2.5-7B-Instruct-general_r16

Updated Sep 12, 2025

Sangsang/0903_deepseek-r1-controlTokens-20250811-GRPO-LORA-INDIVIDUAL

Updated Sep 7, 2025

Sangsang/0903_deepseek-r1-controlTokens-20250811-GRPO-LORA-INDIVIDUAL_checkpoint-500

Updated Sep 5, 2025