thangvip/qwen2.5-1.5b-dspo-no-sft-sgd-linear-steps-4600-steps Text Generation • 2B • Updated Feb 14 • 14
thangvip/qwen2.5-1.5b-dspo-no-sft-sgd-linear-steps-4400-steps Text Generation • 2B • Updated Feb 14 • 10
thangvip/qwen2.5-1.5b-dspo-no-sft-sgd-linear-steps-4200-steps Text Generation • 2B • Updated Feb 14 • 10
thangvip/qwen2.5-1.5b-dspo-no-sft-sgd-linear-steps-4000-steps Text Generation • 2B • Updated Feb 14 • 13
thangvip/qwen2.5-1.5b-dspo-no-sft-sgd-linear-steps-3800-steps Text Generation • 2B • Updated Feb 14 • 14
thangvip/qwen2.5-1.5b-dspo-no-sft-sgd-linear-steps-3600-steps Text Generation • 2B • Updated Feb 14 • 13
thangvip/qwen2.5-1.5b-dspo-no-sft-sgd-linear-steps-3400-steps Text Generation • 2B • Updated Feb 14 • 12
thangvip/qwen2.5-1.5b-dspo-no-sft-sgd-linear-steps-3200-steps Text Generation • 2B • Updated Feb 14 • 12
thangvip/qwen2.5-1.5b-dspo-no-sft-sgd-linear-steps-3000-steps Text Generation • 2B • Updated Feb 14 • 15
thangvip/qwen2.5-1.5b-dspo-no-sft-sgd-linear-steps-2800-steps Text Generation • 2B • Updated Feb 14 • 11
thangvip/qwen2.5-1.5b-dspo-no-sft-sgd-linear-steps-2600-steps Text Generation • 2B • Updated Feb 14 • 11
thangvip/qwen2.5-1.5b-dspo-no-sft-sgd-linear-steps-2400-steps Text Generation • 2B • Updated Feb 14 • 14
thangvip/qwen2.5-1.5b-dspo-no-sft-sgd-linear-steps-2200-steps Text Generation • 2B • Updated Feb 14 • 16
thangvip/qwen2.5-1.5b-dspo-no-sft-sgd-linear-steps-2000-steps Text Generation • 2B • Updated Feb 13 • 10
thangvip/qwen2.5-1.5b-dspo-no-sft-sgd-linear-steps-1800-steps Text Generation • 2B • Updated Feb 13 • 19
thangvip/qwen2.5-1.5b-dspo-no-sft-sgd-linear-steps-1600-steps Text Generation • 2B • Updated Feb 13 • 18
thangvip/qwen2.5-1.5b-dspo-no-sft-sgd-linear-steps-1400-steps Text Generation • 2B • Updated Feb 13 • 10
thangvip/qwen2.5-1.5b-dspo-no-sft-sgd-linear-steps-1200-steps Text Generation • 2B • Updated Feb 13 • 11
thangvip/qwen2.5-1.5b-dspo-no-sft-sgd-linear-steps-1000-steps Text Generation • 2B • Updated Feb 13 • 16
thangvip/qwen2.5-1.5b-dspo-no-sft-sgd-linear-steps-800-steps Text Generation • 2B • Updated Feb 13 • 11
thangvip/qwen2.5-1.5b-dspo-no-sft-sgd-linear-steps-600-steps Text Generation • 2B • Updated Feb 13 • 11
thangvip/qwen2.5-1.5b-dspo-no-sft-sgd-linear-steps-400-steps Text Generation • 2B • Updated Feb 13 • 13
thangvip/qwen2.5-1.5b-dspo-no-sft-sgd-linear-steps-200-steps Text Generation • 2B • Updated Feb 13 • 10
thangvip/qwen3-1.7b-dspo-no-sft-sgd-linear-6500-steps-13000-steps Text Generation • 2B • Updated Feb 12 • 10
thangvip/qwen3-1.7b-dspo-no-sft-sgd-linear-6500-steps-12800-steps Text Generation • 2B • Updated Feb 12 • 19
thangvip/qwen3-1.7b-dspo-no-sft-sgd-linear-6500-steps-12600-steps Text Generation • 2B • Updated Feb 12 • 11
thangvip/qwen3-1.7b-dspo-no-sft-sgd-linear-6500-steps-12400-steps Text Generation • 2B • Updated Feb 12 • 21
thangvip/qwen3-1.7b-dspo-no-sft-sgd-linear-6500-steps-12200-steps Text Generation • 2B • Updated Feb 12 • 15
thangvip/qwen3-1.7b-dspo-no-sft-sgd-linear-6500-steps-12000-steps Text Generation • 2B • Updated Feb 12 • 11