thangvip/qwen3-1.7b-dspo-no-sft-sgd-linear-6500-steps-11800-steps Text Generation • 2B • Updated Feb 12 • 15
thangvip/qwen3-1.7b-dspo-no-sft-sgd-linear-6500-steps-11600-steps Text Generation • 2B • Updated Feb 12 • 10
thangvip/qwen3-1.7b-dspo-no-sft-sgd-linear-6500-steps-11400-steps Text Generation • 2B • Updated Feb 12 • 11
thangvip/qwen3-1.7b-dspo-no-sft-sgd-linear-6500-steps-11200-steps Text Generation • 2B • Updated Feb 11 • 11
thangvip/qwen3-1.7b-dspo-no-sft-sgd-linear-6500-steps-11000-steps Text Generation • 2B • Updated Feb 11 • 12
thangvip/qwen3-1.7b-dspo-no-sft-sgd-linear-6500-steps-10800-steps Text Generation • 2B • Updated Feb 11 • 13
thangvip/qwen3-1.7b-dspo-no-sft-sgd-linear-6500-steps-10600-steps Text Generation • 2B • Updated Feb 11 • 22
thangvip/qwen3-1.7b-dspo-no-sft-sgd-linear-6500-steps-10400-steps Text Generation • 2B • Updated Feb 11 • 14
thangvip/qwen3-1.7b-dspo-no-sft-sgd-linear-6500-steps-10200-steps Text Generation • 2B • Updated Feb 11 • 11
thangvip/qwen3-1.7b-dspo-no-sft-sgd-linear-6500-steps-10000-steps Text Generation • 2B • Updated Feb 11 • 15
thangvip/qwen3-1.7b-dspo-no-sft-sgd-linear-6500-steps-9800-steps Text Generation • 2B • Updated Feb 11 • 18
thangvip/qwen3-1.7b-dspo-no-sft-sgd-linear-6500-steps-9600-steps Text Generation • 2B • Updated Feb 11 • 15
thangvip/qwen3-1.7b-dspo-no-sft-sgd-linear-6500-steps-9400-steps Text Generation • 2B • Updated Feb 11 • 13
thangvip/qwen3-1.7b-dspo-no-sft-sgd-linear-6500-steps-9200-steps Text Generation • 2B • Updated Feb 11 • 14
thangvip/qwen3-1.7b-dspo-no-sft-sgd-linear-6500-steps-9000-steps Text Generation • 2B • Updated Feb 11 • 12
thangvip/qwen3-1.7b-dspo-no-sft-sgd-linear-6500-steps-8800-steps Text Generation • 2B • Updated Feb 10 • 14
thangvip/qwen3-1.7b-dspo-no-sft-sgd-linear-6500-steps-8600-steps Text Generation • 2B • Updated Feb 10 • 16
thangvip/qwen3-1.7b-dspo-no-sft-sgd-linear-6500-steps-8400-steps Text Generation • 2B • Updated Feb 10 • 14
thangvip/qwen3-1.7b-dspo-no-sft-sgd-linear-6500-steps-8200-steps Text Generation • 2B • Updated Feb 10 • 13
thangvip/qwen3-1.7b-dspo-no-sft-sgd-linear-6500-steps-8000-steps Text Generation • 2B • Updated Feb 10 • 15
thangvip/qwen3-1.7b-dspo-no-sft-sgd-linear-6500-steps-7800-steps Text Generation • 2B • Updated Feb 10 • 15
thangvip/qwen3-1.7b-dspo-no-sft-sgd-linear-6500-steps-7600-steps Text Generation • 2B • Updated Feb 10 • 15
thangvip/qwen3-1.7b-dspo-no-sft-sgd-linear-6500-steps-7400-steps Text Generation • 2B • Updated Feb 10 • 22
thangvip/qwen3-1.7b-dspo-no-sft-sgd-linear-6500-steps-7200-steps Text Generation • 2B • Updated Feb 10 • 14
thangvip/qwen3-1.7b-dspo-no-sft-sgd-linear-6500-steps-7000-steps Text Generation • 2B • Updated Feb 10 • 11
thangvip/qwen3-1.7b-dspo-no-sft-sgd-linear-6500-steps-6800-steps Text Generation • 2B • Updated Feb 10 • 16
thangvip/qwen3-1.7b-dspo-no-sft-sgd-linear-6500-steps-6600-steps Text Generation • 2B • Updated Feb 9 • 10
thangvip/qwen3-1.7b-dspo-no-sft-sgd-linear-6500-steps-6400-steps Text Generation • 2B • Updated Feb 9 • 14
thangvip/qwen3-1.7b-dspo-no-sft-sgd-linear-6500-steps-6200-steps Text Generation • 2B • Updated Feb 9 • 15
thangvip/qwen3-1.7b-dspo-no-sft-sgd-linear-6500-steps-6000-steps Text Generation • 2B • Updated Feb 9 • 16