Sangsang/feedback_disallowed_ema_Qwen3-4B_reverse_kl_ema0p999_ep30 Text Generation • Updated Apr 2 • 2
Sangsang/feedback_asymmetric_fixed_ema_Qwen3-4B_bw0p5_fw0p5_ema0p999_ep30 Text Generation • Updated Apr 2 • 12
Sangsang/grpo_Qwen3-4B-Instruct-2507_bs16_g16_mb128_lr1e-6_b1e-3_clip0p2_temp0p7_ep30 Text Generation • Updated Apr 2 • 19
Sangsang/feedback_asymmetric_fixed_ema_Qwen3-4B-Instruct-2507_bw0p5_fw0p5_ema0p999_ep30 Text Generation • Updated Apr 2 • 24
Sangsang/feedback_disallowed_ema_Qwen3-4B-Instruct-2507_reverse_kl_ema0p999_ep30 Text Generation • Updated Apr 2 • 3
Sangsang/feedback_both_ema_Qwen3-4B-Instruct-2507_reverse_kl_ema0p999_ep30 Text Generation • Updated Apr 2 • 3
Sangsang/feedback_allowed_ema_Qwen3-4B-Instruct-2507_reverse_kl_ema0p999_ep30 Text Generation • Updated Apr 2 • 3
Sangsang/feedback_asymmetric_fixed_ema_Qwen2.5-7B-Instruct_bw0p5_fw0p5_ema0p999_ep30 Text Generation • Updated Apr 2 • 14
Sangsang/feedback_disallowed_ema_Qwen2.5-7B-Instruct_reverse_kl_ema0p999_ep30 Text Generation • Updated Apr 2 • 1
Sangsang/feedback_both_ema_Qwen2.5-7B-Instruct_reverse_kl_ema0p999_ep30 Text Generation • Updated Apr 2
Sangsang/feedback_allowed_ema_Qwen2.5-7B-Instruct_reverse_kl_ema0p999_ep30 Text Generation • Updated Apr 2
Sangsang/feedback_asymmetric_fixed_ema_Llama-3.1-8B-Instruct_bw0p5_fw0p5_ema0p999_ep30 Text Generation • Updated Apr 1 • 9
Sangsang/feedback_both_ema_Llama-3.1-8B-Instruct_reverse_kl_ema0p999_ep30 Text Generation • Updated Apr 1
Sangsang/feedback_disallowed_ema_Llama-3.1-8B-Instruct_reverse_kl_ema0p999_ep30 Text Generation • Updated Apr 1
Sangsang/feedback_allowed_ema_Llama-3.1-8B-Instruct_reverse_kl_ema0p999_ep30 Text Generation • Updated Apr 1
Sangsang/feedback_disallowed_ema_DeepSeek-R1-Distill-Llama-8B_reverse_kl_ema0p999_ep30 Text Generation • Updated Mar 26
Sangsang/grpo_DeepSeek-R1-Distill-Llama-8B_bs8_g16_mb128_lr1e-6_b1e-3_clip0p2_temp0p7_ep30 Text Generation • Updated Mar 26