Sangsang/rlsd_Qwen3-4B-Instruct-2507_lora32_n2048_seed42_lr1e-06_mcl8192_within_batch
Text Generation • Updated • 18
Sangwoo Park
Sangsang
AI & ML interests
I do LLM post-training & Distillation research (KAIST AI)
Recent Activity
authored a paper 4 days ago
OmniRetrieval: Unified Retrieval across Heterogeneous Knowledge Sources updated a model 4 days ago
Sangsang/rlsd_Qwen3-4B-Instruct-2507_lora32_n2048_seed42_lr1e-06_mcl8192_within_batch updated a model 4 days ago
Sangsang/rlsd_Qwen3-4B-Base_lora32_n2048_seed42_lr1e-06_mcl8192_within_batchOrganizations
None yet
Sangsang/rlsd_Qwen3-4B-Base_lora32_n2048_seed42_lr1e-06_mcl8192_within_batch
Text Generation • Updated • 16
Sangsang/rlsd_Qwen3-4B_lora32_n2048_seed42_lr1e-06_mcl16384_within_batch
Text Generation • Updated • 11
Sangsang/sdpo_Qwen3-4B-Instruct-2507_lora32_n2048_seed42_lr1e-05_mcl8192_full_voacb
Text Generation • Updated • 17
Sangsang/sdpo_Qwen3-4B-Base_lora32_n2048_seed42_lr1e-05_mcl8192_full_voacb
Text Generation • Updated • 10
Sangsang/sdpo_Qwen3-4B_lora32_n2048_seed42_lr1e-05_mcl16384_full_voacb
Text Generation • Updated • 16
Sangsang/grpo_Qwen3-4B-Instruct-2507_lora32_n2048_seed42_lr1e-05_mcl8192
Text Generation • Updated • 19
Sangsang/grpo_Qwen3-4B-Instruct-2507_lora32_n2048_seed42_lr1e-06_mcl8192
Text Generation • Updated • 19
Sangsang/grpo_Qwen3-4B-Base_lora32_n2048_seed42_lr1e-06_mcl8192
Text Generation • Updated • 16
Sangsang/grpo_Qwen3-4B_lora32_n2048_seed42_lr1e-06_mcl16384
Text Generation • Updated • 15
Sangsang/safepath_Qwen3-32B
Text Generation • Updated • 23
Sangsang/qwen3-32B-thinksafe-32B-32-pm-3ep
Text Generation • Updated • 40
Sangsang/qwen3-32B-safechain-32-pm-3ep
Text Generation • Updated • 34
Sangsang/Qwen3-4B-Instruct-2507-GRPO_16_eps20
Text Generation • Updated • 5
Sangsang/Qwen3-4B-Instruct-2507-GRPOPE_8_eps20
Text Generation • Updated • 5
Sangsang/Qwen3-4B-Instruct-2507-GRPO_32_eps20
Text Generation • Updated • 8
Sangsang/Qwen3-4B-Instruct-2507-GRPO_8_eps20
Text Generation • Updated • 6
Sangsang/Olmo-3-7B-Instruct-SFT-ContextGRPOwDistill_2x4_eps20
Text Generation • Updated • 11
Sangsang/Olmo-3-7B-Instruct-SFT-GRPOPE_8_eps20
Text Generation • Updated • 11
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 • 10
Sangsang/Olmo-3-7B-Instruct-SFT-GRPO_8_eps_20
Text Generation • Updated • 10
Sangsang/qwen3-32B-direct-refusal-32-pm-5ep
Text Generation • Updated • 38
Sangsang/feedback_asymmetric_kl_fixed_ema_Qwen2.5-7B-Instruct_bw0p75_fw0p25_ema0p999_ep30
Text Generation • Updated • 2
Sangsang/feedback_asymmetric_kl_fixed_ema_Qwen2.5-7B-Instruct_bw0p25_fw0p75_ema0p999_ep30
Text Generation • Updated • 2
Sangsang/feedback_asymmetric_kl_fixed_ema_Llama-3.1-8B-Instruct_bw0p75_fw0p25_ema0p999_ep30
Text Generation • Updated • 4
Sangsang/feedback_asymmetric_kl_fixed_ema_Llama-3.1-8B-Instruct_bw0p25_fw0p75_ema0p999_ep30
Text Generation • Updated • 4
Sangsang/ci-rl-Qwen2.5-7B-Instruct
Updated
Sangsang/feedback_asymmetric_kl_fixed_ema_Qwen3-14B_bw0p5_fw0p5_ema0p999_ep30
Text Generation • Updated • 5
Sangsang/grpo_Qwen3-0.6B_bs16_g16_mb128_lr1e-6_b1e-3_clip0p2_temp0p7_ep30
Text Generation • Updated • 2