Snyhlxde/shiftedattn-8-31-coder-7B-ntok16_soft_ce_oci_datav1_44p5k_stp_ar_10_cyclic_prog_noise_all_lr5e-6 8B • Updated about 5 hours ago
Snyhlxde/shiftedattn-8-28-coder-7B-ntok16_soft_ce_oci_datav1_40k_smpl_ar_10_cyclic_prog_noise_r0p5_lr5e-6 8B • Updated about 5 hours ago
Snyhlxde/8-28-qwen25-coder-7B-ntok16_soft_ce_flexattn_oci_data_v1_40k_smpl_ar_10_cyc_prog_noise_lr5e-6 8B • Updated 4 days ago • 1
Snyhlxde/logitsaligned-8-27-qwen2p5-coder-7B-ntok16_soft_ce_flexattn_oci_data_v1_40k_smpl_ar_10_lr5e-6 8B • Updated 4 days ago • 4
Snyhlxde/logitsaligned-8-27-qwen2p5-coder-7B-ntok16_soft_ce_flexattn_oci_data_v1_10k_smpl_ar_10_lr5e-6 8B • Updated 5 days ago
Snyhlxde/alignedlogits-8-24-7B-ntok64_ce_soft_loss_length_20k_flexattn_32kdata_v1_ar_10_lr5e-6 8B • Updated 8 days ago • 2
Snyhlxde/alignedlogits-8-24-7B-ntok64_ce_soft_loss_length_20k_flexattn_32kdata_v1_ar_1_only_lr5e-6 8B • Updated 8 days ago • 1
Snyhlxde/aligned-8-24-7B-ntok64_ce_soft_loss_length_20k_flexattn_data_v1_4k_smp_ar_10_lr5-6 8B • Updated 9 days ago • 7
Snyhlxde/aligned-8-24-7B-ntok64_ce_soft_loss_length_20k_flexattn_data_v1_4k_smp_ar_1_only_lr5-6 8B • Updated 9 days ago • 7
Snyhlxde/8-23-openthinker2-7B-ntok64_ce_soft_loss_length_capped_16k_flexattn_data_v1_4kexample_ar_10 8B • Updated 9 days ago • 11