Sangsang/qwen3-8B-thinksafe-8B-n1-ablation-32-pm-3ep-harmful_only
Text Generation • Updated
Sangwoo Park
Sangsang
AI & ML interests
I do LLM post-training & Distillation research (KAIST AI)
Recent Activity
updated a model about 6 hours ago
Sangsang/qwen3-8B-thinksafe-8B-n1-ablation-32-pm-3ep-harmful_only published a model about 6 hours ago
Sangsang/qwen3-8B-thinksafe-8B-n1-ablation-32-pm-3ep-harmful_only updated a model about 6 hours ago
Sangsang/qwen3-4B-thinksafe-4B-n1-ablation-32-pm-3ep-harmful_onlyOrganizations
None yet
Sangsang/qwen3-4B-thinksafe-4B-n1-ablation-32-pm-3ep-harmful_only
Text Generation • Updated
Sangsang/R1-8B-thinksafe-r1-8B-ablation-32-pm-3ep-harmful_only
Text Generation • Updated
Sangsang/qwen3-1.7B-thinksafe-1.7B-n1-ablation-32-pm-3ep-harmful_only
Text Generation • Updated • 19
Sangsang/qwen3-0.6B-thinksafe-0.6B-n1-ablation-32-pm-3ep-harmful_only
Text Generation • Updated • 23
Sangsang/R1-7B-thinksafe-r1-7B-ablation-32-pm-3ep-harmful_only
Text Generation • Updated • 15
Sangsang/R1-1.5B-thinksafe-r1-1.5B-ablation-32-pm-3ep-harmful_only
Text Generation • Updated • 22
Sangsang/rlsd_Qwen3-4B-Instruct-2507_lora32_n2048_seed42_lr1e-06_mcl8192_within_batch
Text Generation • Updated • 1
Sangsang/rlsd_Qwen3-4B-Base_lora32_n2048_seed42_lr1e-06_mcl8192_within_batch
Text Generation • Updated • 1
Sangsang/rlsd_Qwen3-4B_lora32_n2048_seed42_lr1e-06_mcl16384_within_batch
Text Generation • Updated • 1
Sangsang/sdpo_Qwen3-4B-Instruct-2507_lora32_n2048_seed42_lr1e-05_mcl8192_full_voacb
Text Generation • Updated • 1
Sangsang/sdpo_Qwen3-4B-Base_lora32_n2048_seed42_lr1e-05_mcl8192_full_voacb
Text Generation • Updated • 1
Sangsang/sdpo_Qwen3-4B_lora32_n2048_seed42_lr1e-05_mcl16384_full_voacb
Text Generation • Updated • 2
Sangsang/grpo_Qwen3-4B-Instruct-2507_lora32_n2048_seed42_lr1e-05_mcl8192
Text Generation • Updated • 5
Sangsang/grpo_Qwen3-4B-Instruct-2507_lora32_n2048_seed42_lr1e-06_mcl8192
Text Generation • Updated • 1
Sangsang/grpo_Qwen3-4B-Base_lora32_n2048_seed42_lr1e-06_mcl8192
Text Generation • Updated • 1
Sangsang/grpo_Qwen3-4B_lora32_n2048_seed42_lr1e-06_mcl16384
Text Generation • Updated • 1
Sangsang/safepath_Qwen3-32B
Text Generation • Updated • 1
Sangsang/qwen3-32B-thinksafe-32B-32-pm-3ep
Text Generation • Updated • 1
Sangsang/qwen3-32B-safechain-32-pm-3ep
Text Generation • Updated • 1
Sangsang/Qwen3-4B-Instruct-2507-GRPO_16_eps20
Text Generation • Updated • 1
Sangsang/Qwen3-4B-Instruct-2507-GRPOPE_8_eps20
Text Generation • Updated • 1
Sangsang/Qwen3-4B-Instruct-2507-GRPO_32_eps20
Text Generation • Updated • 1
Sangsang/Qwen3-4B-Instruct-2507-GRPO_8_eps20
Text Generation • Updated • 1
Sangsang/Olmo-3-7B-Instruct-SFT-ContextGRPOwDistill_2x4_eps20
Text Generation • Updated • 1
Sangsang/Olmo-3-7B-Instruct-SFT-GRPOPE_8_eps20
Text Generation • Updated • 1
Sangsang/Olmo-3-7B-Instruct-SFT-GRPO_32_eps_20
Text Generation • Updated • 4
Sangsang/Olmo-3-7B-Instruct-SFT-GRPO_16_eps_20
Text Generation • Updated • 1
Sangsang/Olmo-3-7B-Instruct-SFT-GRPO_8_eps_20
Text Generation • Updated • 1
Sangsang/qwen3-32B-direct-refusal-32-pm-5ep
Text Generation • Updated • 1