seungkukim/dit4dit_gr1_posttrain_attn_align_group_compodistill_cosine_align75k_ws_pretrain100k_8gpu-100k 10B • Updated about 17 hours ago
seungkukim/dit4dit_gr1_posttrain_attn_align_group_compodistill_cosine_align70k_ws_pretrain100k_8gpu-100k 10B • Updated about 23 hours ago
seungkukim/dit4dit_gr1_posttrain_attn_align_routed_semckdfix_p3_stackk3_align70k_ws_pretrain100k_8gpu-100k 10B • Updated 2 days ago • 18
seungkukim/dit4dit_gr1_posttrain_attn_align_cosine_routed_3x6_align70k_ws_pretrain100k_8gpu-100k 10B • Updated 3 days ago • 17
seungkukim/dit4dit_gr1_posttrain_attn_align_2pair_early_layers_cosine_align70k_ws_pretrain100k-100k 10B • Updated 8 days ago • 20
seungkukim/dit4dit_gr1_posttrain_attn_align_2pair_early_layers_cosine_align60k_ws_pretrain100k-100k 10B • Updated 8 days ago • 16
seungkukim/dit4dit_gr1_posttrain_attn_align_2pair_early_layers_cosine_align75k_ws_pretrain100k-100k 10B • Updated 9 days ago • 20
seungkukim/dit4dit_gr1_posttrain_attn_align_2pair_cosine_align60k_ws_pretrain100k-100k 10B • Updated 9 days ago • 16