Sangsang/0830_deepseek-r1-controlTokens-20250811-GRPO-LORA-INDIVIDUAL
Updated
Sangwoo Park
Sangsang
AI & ML interests
I do LLM post-training & Distillation research (KAIST AI)
Recent Activity
updated a model 5 days ago
Sangsang/qwen3-8B-thinksafe-8B-n1-ablation-32-pm-3ep-harmful_only published a model 5 days ago
Sangsang/qwen3-8B-thinksafe-8B-n1-ablation-32-pm-3ep-harmful_only updated a model 5 days ago
Sangsang/qwen3-4B-thinksafe-4B-n1-ablation-32-pm-3ep-harmful_onlyOrganizations
None yet
Sangsang/0827_deepseek-r1-controlTokens-20250811-GRPO-LORA-INDIVIDUAL
Updated • 4 • 1
Sangsang/Qwen2.5-7B-Instruct-penguin-preference_r16
Updated
Sangsang/Qwen2.5-7B-Instruct-cat-preference_r16_empty_sys
Updated
Sangsang/Qwen2.5-7B-Instruct-cat-preference_r16_no_sys
Updated
Sangsang/Llama-3.2-3B-Instruct-cat-preference_r16_corrupted
Updated
Sangsang/Llama-3.2-3B-Instruct-cat-preference_r16
Updated
Sangsang/Qwen2.5-7B-Instruct-cat-preference_r16
Updated