multi-token/shiftedattn-9-3-coder-7B-ntok16_soft_ce_oci_datav1_59k_stp_ar_10_cyclic_prog_noise_all_lr1e-6 8B • Updated Sep 4 • 2
multi-token/shiftedattn-9-2-coder-7B-ntok16_soft_ce_oci_datav1_59k_stp_ar_10_cyclic_prog_noise_all_lr2e-6 8B • Updated Sep 3 • 1
multi-token/shiftedattn-8-31-coder-7B-ntok16_soft_ce_oci_datav1_59k_stp_ar_10_cyclic_prog_noise_all_lr5e-6 8B • Updated Sep 2 • 1
multi-token/shiftedattn-8-31-coder-7B-ntok16_soft_ce_oci_datav1_44p5k_stp_ar_10_cyclic_prog_noise_all_lr5e-6 8B • Updated Sep 1 • 1
multi-token/shiftedattn-8-28-coder-7B-ntok16_soft_ce_oci_datav1_40k_smpl_ar_10_cyclic_prog_noise_r0p5_lr5e-6 8B • Updated Sep 1 • 1
multi-token/8-28-qwen25-coder-7B-ntok16_soft_ce_flexattn_oci_data_v1_40k_smpl_ar_10_cyc_prog_noise_lr5e-6 8B • Updated Aug 29
multi-token/logitsaligned-8-27-qwen2p5-coder-7B-ntok16_soft_ce_flexattn_oci_data_v1_40k_smpl_ar_10_lr5e-6 8B • Updated Aug 28 • 1
multi-token/logitsaligned-8-27-qwen2p5-coder-7B-ntok16_soft_ce_flexattn_oci_data_v1_10k_smpl_ar_10_lr5e-6 8B • Updated Aug 28 • 1
multi-token/alignedlogits-8-24-7B-ntok64_ce_soft_loss_length_20k_flexattn_32kdata_v1_ar_10_lr5e-6 8B • Updated Aug 25 • 1
multi-token/alignedlogits-8-24-7B-ntok64_ce_soft_loss_length_20k_flexattn_32kdata_v1_ar_1_only_lr5e-6 8B • Updated Aug 25 • 1