seungkukim/dit4dit_gr1_posttrain_attn_align_2pair_early_layers_cosine_align70k_ws_pretrain100k-100k 10B • Updated 3 days ago • 20
seungkukim/dit4dit_gr1_posttrain_attn_align_2pair_early_layers_cosine_align70k_ws_pretrain100k-100k 10B • Updated 3 days ago • 20
seungkukim/dit4dit_gr1_posttrain_attn_align_2pair_early_layers_cosine_align60k_ws_pretrain100k-100k 10B • Updated 4 days ago • 16
seungkukim/dit4dit_gr1_posttrain_attn_align_2pair_early_layers_cosine_align60k_ws_pretrain100k-100k 10B • Updated 4 days ago • 16
seungkukim/dit4dit_gr1_posttrain_attn_align_2pair_early_layers_cosine_align75k_ws_pretrain100k-100k 10B • Updated 4 days ago • 20
seungkukim/dit4dit_gr1_posttrain_attn_align_2pair_early_layers_cosine_align75k_ws_pretrain100k-100k 10B • Updated 4 days ago • 20
seungkukim/dit4dit_gr1_posttrain_attn_align_2pair_cosine_align60k_ws_pretrain100k-100k 10B • Updated 4 days ago • 16
seungkukim/dit4dit_gr1_posttrain_attn_align_2pair_cosine_align60k_ws_pretrain100k-100k 10B • Updated 4 days ago • 16
seungkukim/dit4dit_gr1_posttrain_attn_align_2pair_cosine_align60k_ws_pretrain100k-60k 10B • Updated 5 days ago • 19
seungkukim/dit4dit_gr1_posttrain_attn_align_2pair_cosine_align60k_ws_pretrain100k-60k 10B • Updated 5 days ago • 19
seungkukim/dit4dit_gr1_posttrain_attn_align_2pair_early_layers_cosine_align60k-100k 10B • Updated 5 days ago • 18
seungkukim/dit4dit_gr1_posttrain_attn_align_2pair_early_layers_cosine_align60k-100k 10B • Updated 5 days ago • 18