Sangsang/feedback_asymmetric_kl_fixed_ema_Qwen3-14B_bw0p5_fw0p5_ema0p999_ep30 Text Generation • Updated about 15 hours ago • 10
Sangsang/grpo_Qwen3-0.6B_bs16_g16_mb128_lr1e-6_b1e-3_clip0p2_temp0p7_ep30 Text Generation • Updated 3 days ago • 11
Sangsang/feedback_asymmetric_fixed_ema_Llama-3.1-8B-Instruct_bw0p5_fw0p5_ema0p999_ep30_v2 Text Generation • Updated 4 days ago • 18
Sangsang/grpo_Qwen3-1.7B_bs16_g16_mb128_lr1e-6_b1e-3_clip0p2_temp0p7_ep30 Text Generation • Updated 10 days ago • 11
Sangsang/grpo_Qwen3-4B_bs16_g16_mb128_lr1e-6_b1e-3_clip0p2_temp0p7_ep30 Text Generation • Updated 11 days ago • 21
Sangsang/feedback_asymmetric_fixed_ema_DeepSeek-R1-Distill-Qwen-7B_bw0p5_fw0p5_ema0p999_ep30 Text Generation • Updated 12 days ago • 14
Sangsang/feedback_asymmetric_fixed_ema_DeepSeek-R1-Distill-Llama-8B_bw0p5_fw0p5_ema0p999_ep30 Text Generation • Updated 12 days ago • 24
Sangsang/feedback_both_ema_Qwen3-4B_reverse_kl_ema0p999_ep30 Text Generation • Updated 13 days ago • 16
Sangsang/feedback_allowed_ema_Qwen3-4B_reverse_kl_ema0p999_ep30 Text Generation • Updated 13 days ago • 22
Sangsang/feedback_disallowed_ema_Qwen3-4B_reverse_kl_ema0p999_ep30 Text Generation • Updated 13 days ago • 14
Sangsang/feedback_asymmetric_fixed_ema_Qwen3-4B_bw0p5_fw0p5_ema0p999_ep30 Text Generation • Updated 13 days ago • 26
Sangsang/grpo_Qwen3-4B-Instruct-2507_bs16_g16_mb128_lr1e-6_b1e-3_clip0p2_temp0p7_ep30 Text Generation • Updated 13 days ago • 18
Sangsang/feedback_asymmetric_fixed_ema_Qwen3-4B-Instruct-2507_bw0p5_fw0p5_ema0p999_ep30 Text Generation • Updated 13 days ago • 18
Sangsang/feedback_disallowed_ema_Qwen3-4B-Instruct-2507_reverse_kl_ema0p999_ep30 Text Generation • Updated 13 days ago • 26
Sangsang/feedback_both_ema_Qwen3-4B-Instruct-2507_reverse_kl_ema0p999_ep30 Text Generation • Updated 13 days ago • 16
Sangsang/feedback_allowed_ema_Qwen3-4B-Instruct-2507_reverse_kl_ema0p999_ep30 Text Generation • Updated 13 days ago • 16
Sangsang/feedback_asymmetric_fixed_ema_Qwen2.5-7B-Instruct_bw0p5_fw0p5_ema0p999_ep30 Text Generation • Updated 13 days ago • 24
Sangsang/feedback_disallowed_ema_Qwen2.5-7B-Instruct_reverse_kl_ema0p999_ep30 Text Generation • Updated 13 days ago • 12
Sangsang/feedback_both_ema_Qwen2.5-7B-Instruct_reverse_kl_ema0p999_ep30 Text Generation • Updated 13 days ago • 12
Sangsang/feedback_allowed_ema_Qwen2.5-7B-Instruct_reverse_kl_ema0p999_ep30 Text Generation • Updated 13 days ago • 13
Sangsang/feedback_asymmetric_fixed_ema_Llama-3.1-8B-Instruct_bw0p5_fw0p5_ema0p999_ep30 Text Generation • Updated 14 days ago • 29
Sangsang/feedback_both_ema_Llama-3.1-8B-Instruct_reverse_kl_ema0p999_ep30 Text Generation • Updated 14 days ago • 16
Sangsang/feedback_disallowed_ema_Llama-3.1-8B-Instruct_reverse_kl_ema0p999_ep30 Text Generation • Updated 14 days ago • 12
Sangsang/feedback_allowed_ema_Llama-3.1-8B-Instruct_reverse_kl_ema0p999_ep30 Text Generation • Updated 14 days ago • 18