Asap7772/Qwen3-4B-second-stage-DPO-lr-1e-7-beta-0.05-loss-sigmoid-rpo-1.0-ckpt-135 196k • Updated Sep 16 • 8
Asap7772/Qwen3-4B-second-stage-DPO-lr-1e-7-beta-0.01-loss-sigmoid-rpo-1.0-ckpt-135 196k • Updated Sep 16 • 10
Asap7772/Qwen3-4B-second-stage-DPO-lr-1e-7-beta-0.1-loss-sigmoid-rpo-1.0-ckpt-135 196k • Updated Sep 16 • 8
Asap7772/Qwen3-4B-second-stage-DPO-lr-1e-6-beta-0.05-loss-sigmoid-rpo-1.0-ckpt-135 196k • Updated Sep 16 • 9
Asap7772/Qwen3-4B-second-stage-DPO-lr-1e-6-beta-0.01-loss-sigmoid-rpo-1.0-ckpt-135 196k • Updated Sep 16 • 10
Asap7772/Qwen3-4B-second-stage-DPO-lr-1e-6-beta-0.1-loss-sigmoid-rpo-1.0-ckpt-135 196k • Updated Sep 16 • 6
Asap7772/qwen3-4b-arc-second-stage-star-sftinit-lr1e-6-0908 Text Generation • 4B • Updated Sep 12 • 7
Asap7772/qwen3-4b-arc-second-stage-star-sftinit-lr1e-5-0908 Text Generation • 4B • Updated Sep 12 • 6
Asap7772/qwen3-17b-abstraction-sft-5epoch-bs256-lr1e-5-0718 Text Generation • 2B • Updated Jul 20 • 6
Asap7772/qwen3-17b-abstraction-sft-5epoch-bs256-lr5e-6-0718 Text Generation • 2B • Updated Jul 20 • 8
Asap7772/qwen3-17b-abstraction-sft-5epoch-bs256-lr1e-6-0718 Text Generation • 2B • Updated Jul 20 • 8
Asap7772/qwen3-17b-abstraction-sft-5epoch-bs256-lr5e-7-0718 Text Generation • 2B • Updated Jul 20 • 6