Sangsang/safepath_Qwen3-32B
Text Generation • Updated • 17
Sangwoo Park
Sangsang
AI & ML interests
I do LLM post-training research (KAIST AI)
Recent Activity
updated a model about 21 hours ago
Sangsang/safepath_Qwen3-32B published a model about 21 hours ago
Sangsang/safepath_Qwen3-32B updated a model 2 days ago
Sangsang/qwen3-32B-thinksafe-32B-32-pm-3epOrganizations
None yet
Sangsang/qwen3-32B-thinksafe-32B-32-pm-3ep
Text Generation • Updated • 34
Sangsang/qwen3-32B-safechain-32-pm-3ep
Text Generation • Updated • 29
Sangsang/Qwen3-4B-Instruct-2507-GRPO_16_eps20
Text Generation • Updated • 12
Sangsang/Qwen3-4B-Instruct-2507-GRPOPE_8_eps20
Text Generation • Updated • 7
Sangsang/Qwen3-4B-Instruct-2507-GRPO_32_eps20
Text Generation • Updated • 12
Sangsang/Qwen3-4B-Instruct-2507-GRPO_8_eps20
Text Generation • Updated • 12
Sangsang/Olmo-3-7B-Instruct-SFT-ContextGRPOwDistill_2x4_eps20
Text Generation • Updated • 10
Sangsang/Olmo-3-7B-Instruct-SFT-GRPOPE_8_eps20
Text Generation • Updated • 13
Sangsang/Olmo-3-7B-Instruct-SFT-GRPO_32_eps_20
Text Generation • Updated • 12
Sangsang/Olmo-3-7B-Instruct-SFT-GRPO_16_eps_20
Text Generation • Updated • 12
Sangsang/Olmo-3-7B-Instruct-SFT-GRPO_8_eps_20
Text Generation • Updated • 13
Sangsang/qwen3-32B-direct-refusal-32-pm-5ep
Text Generation • Updated • 44
Sangsang/feedback_asymmetric_kl_fixed_ema_Qwen2.5-7B-Instruct_bw0p75_fw0p25_ema0p999_ep30
Text Generation • Updated • 11
Sangsang/feedback_asymmetric_kl_fixed_ema_Qwen2.5-7B-Instruct_bw0p25_fw0p75_ema0p999_ep30
Text Generation • Updated • 13
Sangsang/feedback_asymmetric_kl_fixed_ema_Llama-3.1-8B-Instruct_bw0p75_fw0p25_ema0p999_ep30
Text Generation • Updated • 14
Sangsang/feedback_asymmetric_kl_fixed_ema_Llama-3.1-8B-Instruct_bw0p25_fw0p75_ema0p999_ep30
Text Generation • Updated • 14
Sangsang/ci-rl-Qwen2.5-7B-Instruct
Updated
Sangsang/feedback_asymmetric_kl_fixed_ema_Qwen3-14B_bw0p5_fw0p5_ema0p999_ep30
Text Generation • Updated • 13
Sangsang/grpo_Qwen3-0.6B_bs16_g16_mb128_lr1e-6_b1e-3_clip0p2_temp0p7_ep30
Text Generation • Updated • 12
Sangsang/feedback_asymmetric_fixed_ema_Llama-3.1-8B-Instruct_bw0p5_fw0p5_ema0p999_ep30_v2
Text Generation • Updated • 21
Sangsang/ci-sft_Qwen3-4B
Text Generation • Updated • 19
Sangsang/ci-sft_Qwen3-4B-Instruct-2507_lr1e-6_ep30
Text Generation • Updated • 14
Sangsang/qwen3_onpolicy
Text Generation • Updated • 34
Sangsang/grpo_Qwen3-1.7B_bs16_g16_mb128_lr1e-6_b1e-3_clip0p2_temp0p7_ep30
Text Generation • Updated
Sangsang/grpo_Qwen3-4B_bs16_g16_mb128_lr1e-6_b1e-3_clip0p2_temp0p7_ep30
Text Generation • Updated • 7
Sangsang/feedback_asymmetric_fixed_ema_DeepSeek-R1-Distill-Qwen-7B_bw0p5_fw0p5_ema0p999_ep30
Text Generation • Updated
Sangsang/feedback_asymmetric_fixed_ema_DeepSeek-R1-Distill-Llama-8B_bw0p5_fw0p5_ema0p999_ep30
Text Generation • Updated • 10
Sangsang/feedback_both_ema_Qwen3-4B_reverse_kl_ema0p999_ep30
Text Generation • Updated • 4
Sangsang/feedback_allowed_ema_Qwen3-4B_reverse_kl_ema0p999_ep30
Text Generation • Updated • 7