thangvip/qwen2.5-1.5b-dspo-no-sft-sgd-linear-steps-13000-steps Text Generation • 2B • Updated 1 day ago • 7
thangvip/qwen2.5-1.5b-dspo-no-sft-sgd-linear-steps-13000-steps Text Generation • 2B • Updated 1 day ago • 7
thangvip/qwen2.5-1.5b-dspo-no-sft-sgd-linear-steps-12800-steps Text Generation • 2B • Updated 1 day ago • 10
thangvip/qwen2.5-1.5b-dspo-no-sft-sgd-linear-steps-12800-steps Text Generation • 2B • Updated 1 day ago • 10
thangvip/qwen2.5-1.5b-dspo-no-sft-sgd-linear-steps-12600-steps Text Generation • 2B • Updated 1 day ago • 6
thangvip/qwen2.5-1.5b-dspo-no-sft-sgd-linear-steps-12600-steps Text Generation • 2B • Updated 1 day ago • 6
thangvip/qwen2.5-1.5b-dspo-no-sft-sgd-linear-steps-12400-steps Text Generation • 2B • Updated 1 day ago • 6
thangvip/qwen2.5-1.5b-dspo-no-sft-sgd-linear-steps-12400-steps Text Generation • 2B • Updated 1 day ago • 6
thangvip/qwen2.5-1.5b-dspo-no-sft-sgd-linear-steps-12200-steps Text Generation • 2B • Updated 1 day ago • 9
thangvip/qwen2.5-1.5b-dspo-no-sft-sgd-linear-steps-12200-steps Text Generation • 2B • Updated 1 day ago • 9
thangvip/qwen2.5-1.5b-dspo-no-sft-sgd-linear-steps-12000-steps Text Generation • 2B • Updated 1 day ago • 8
thangvip/qwen2.5-1.5b-dspo-no-sft-sgd-linear-steps-12000-steps Text Generation • 2B • Updated 1 day ago • 8
thangvip/qwen2.5-1.5b-dspo-no-sft-sgd-linear-steps-11800-steps Text Generation • 2B • Updated 1 day ago • 8
thangvip/qwen2.5-1.5b-dspo-no-sft-sgd-linear-steps-11800-steps Text Generation • 2B • Updated 1 day ago • 8
thangvip/qwen2.5-1.5b-dspo-no-sft-sgd-linear-steps-11600-steps Text Generation • 2B • Updated 1 day ago • 10
thangvip/qwen2.5-1.5b-dspo-no-sft-sgd-linear-steps-11600-steps Text Generation • 2B • Updated 1 day ago • 10