wgcyeo/ci-sft_Qwen3-4B-Instruct-2507_lr1e-6_ep30_self
Text Generation • Updated
Woongyeong Yeo
wgcyeo
AI & ML interests
None yet
Recent Activity
updated a model about 3 hours ago
wgcyeo/ci-sft_Qwen3-4B-Instruct-2507_lr1e-6_ep30_self published a model about 3 hours ago
wgcyeo/ci-sft_Qwen3-4B-Instruct-2507_lr1e-6_ep30_self updated a model about 4 hours ago
wgcyeo/ci-grpo_Olmo-3-7B-Think_bs8_g16_mb128_lr1e-6_b1e-3_clip0p2_temp0p7_ep30Organizations
None yet
wgcyeo/ci-grpo_Olmo-3-7B-Think_bs8_g16_mb128_lr1e-6_b1e-3_clip0p2_temp0p7_ep30
Text Generation • Updated • 25
wgcyeo/ci-feedback_asym_bi_kl_hybrid_fixed_ema_Qwen3-1.7B_bw0p5_fw0p5_ema0p999_ep30
Text Generation • Updated
wgcyeo/feedback_asym_bi_kl_hybrid_fixed_ema_Qwen3-0.6B_bw0p5_fw0p5_ema0p999_ep30
Text Generation • Updated
wgcyeo/ci-feedback_weighted_asym_bi_kl_fixed_interp_Qwen3-4B-Instruct-2507_bw0p5_fw0p5_stw0p3_ep30
Text Generation • Updated • 2
wgcyeo/ci-fb_w_asym_bi_kl_fixed_ema_interp_Qwen3-4B-Instruct-2507_bw0p5_fw0p5_ema0p999_stw0p3_ep30
Text Generation • Updated • 11
wgcyeo/ci-feedback_w_asym_bi_kl_fixed_ema_Qwen3-4B-Instruct-2507_bw0p5_fw0p5_ema0p999_ep30_aKLf_dKLf
Text Generation • Updated • 16
wgcyeo/ci-feedback_w_asym_bi_kl_fixed_ema_Qwen3-4B-Instruct-2507_bw0p5_fw0p5_ema0p999_ep30_aKLr_dKLf
Text Generation • Updated • 17
wgcyeo/ci-sft_Llama-3.1-8B-Instruct_lr1e-6_ep30
Text Generation • Updated • 41
wgcyeo/ci-feedback_weighted_asym_bi_keyword_fixed_ema_Olmo-3-7B-Think_bw0p5_fw0p5_ema0p999_ep30
Text Generation • Updated • 14
wgcyeo/ci-feedback_asym_bi_fixed_ema_Qwen3-4B-Instruct-2507_bw0p5_fw0p5_ema0p999_ep30_aKLf_dKLr
Text Generation • Updated • 17
wgcyeo/ci-feedback_weighted_asym_bi_kl_fixed_ema_Olmo-3-7B-Instruct_bw0p75_fw0p25_ema0p999_ep30
Text Generation • Updated • 14
wgcyeo/ci-feedback_verbal_both_ema_Olmo-3-7B-Think_reverse_kl_ema0p999_ep30
Text Generation • Updated • 9
wgcyeo/ci-feedback_weighted_asym_bi_kl_fixed_ema_Qwen2.5-1.5B-Instruct_bw0p5_fw0p5_ema0p999_ep30_ci_im
Text Generation • Updated • 16
wgcyeo/ci-feedback_weighted_asym_bi_kl_fixed_ema_Olmo-3-7B-Instruct_bw0p25_fw0p75_ema0p999_ep30
Text Generation • Updated • 11
wgcyeo/ci-feedback_weighted_asym_bi_kl_fixed_none_Qwen3-4B-Instruct-2507_bw0p5_fw0p5_ep30
Text Generation • Updated • 15
wgcyeo/ci-feedback_asym_bi_kl_hybrid_fixed_ema_Qwen3-4B_bw1p0_fw0p0_ema0p999_ep30
Text Generation • Updated • 15
wgcyeo/ci-feedback_asym_bi_kl_hybrid_fixed_ema_Qwen3-4B_bw0p0_fw1p0_ema0p999_ep30
Text Generation • Updated • 12
wgcyeo/ci-feedback_weighted_asym_bi_kl_fixed_none_Qwen3-4B_from_Qwen3-32B_bw0p5_fw0p5_ep30
Text Generation • Updated • 7
wgcyeo/ci-feedback_asym_bi_kl_hybrid_fixed_ema_Qwen3-4B_bw0p75_fw0p25_ema0p999_ep30
Text Generation • Updated • 6
wgcyeo/ci-feedback_asym_bi_kl_hybrid_fixed_ema_Qwen3-4B_bw0p25_fw0p75_ema0p999_ep30
Text Generation • Updated • 15
wgcyeo/ci-feedback_weighted_asym_bi_kl_fixed_ema_Qwen3-4B-Instruct-2507_bw0p25_fw0p75_ema0p999_ep30
Text Generation • Updated • 14
wgcyeo/ci-feedback_weighted_asym_bi_kl_fixed_ema_Qwen3-4B-Instruct-2507_bw0p75_fw0p25_ema0p999_ep30
Text Generation • Updated • 17
wgcyeo/ci-feedback_weighted_asymmetric_bidirectional_kl_fixed_ema_Qwen3-4B_bw0p25_fw0p75_ema0p999_ep30
Text Generation • Updated • 15
wgcyeo/ci-feedback_verbal_both_ema_Qwen2.5-3B-Instruct_reverse_kl_ema0p999_ep30
Text Generation • Updated • 13
wgcyeo/ci-grpo_Qwen3-8B_bs16_g16_mb128_lr1e-6_b1e-3_clip0p2_temp0p7_ep30
Text Generation • Updated • 15
wgcyeo/ci-feedback_weighted_asymmetric_bi_kl_fixed_ema_Qwen2.5-14B-Instruct_bw0p5_fw0p5_ema0p999_ep30
Text Generation • Updated • 14
wgcyeo/ci-feedback_weighted_asymmetric_bidirectional_kl_fixed_ema_Qwen3-8B_bw0p5_fw0p5_ema0p999_ep30
Text Generation • Updated • 14
wgcyeo/ci-grpo_Qwen3-14B_bs8_g16_mb128_lr1e-6_b1e-3_clip0p2_temp0p7_ep30
Text Generation • Updated • 15
wgcyeo/ci-feedback_weighted_asymmetric_bidirectional_kl_fixed_ema_Qwen3-1.7B_bw0p5_fw0p5_ema0p999_ep30
Text Generation • Updated • 10