Sangwoo Park's picture

Sangwoo Park

Sangsang

·

sangwoopark000312

AI & ML interests

I do LLM Safety & Reasoning research (KAIST AI)

Recent Activity

updated a dataset 3 days ago

Sangsang/thinksafe_r1-distill_1.5B_assisted

published a dataset 3 days ago

Sangsang/thinksafe_r1-distill_1.5B_assisted

updated a dataset 3 days ago

Sangsang/thinksafe_r1-distill_7B_assisted

View all activity

Organizations

None yet

Sangsang 's models 15

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

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

Sangsang/qwen3-8B-a0-thinksafe-kl0

Text Generation • Updated Sep 18 • 3

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

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

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

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

Sangsang/0830_deepseek-r1-controlTokens-20250811-GRPO-LORA-INDIVIDUAL

Sangsang/0827_deepseek-r1-controlTokens-20250811-GRPO-LORA-INDIVIDUAL

Updated Aug 30 • 4 • 1

Sangsang/Qwen2.5-7B-Instruct-penguin-preference_r16

Sangsang/Qwen2.5-7B-Instruct-cat-preference_r16_empty_sys

Sangsang/Qwen2.5-7B-Instruct-cat-preference_r16_no_sys

Sangsang/Llama-3.2-3B-Instruct-cat-preference_r16_corrupted

Sangsang/Llama-3.2-3B-Instruct-cat-preference_r16

Sangsang/Qwen2.5-7B-Instruct-cat-preference_r16