{ "architectures": [ "MingTok" ], "low_level_encoder": { "depth": 12, "embed_dim": 768, "ffn_layer": "swiglufused", "img_size": 512, "out_dim": 32, "patch_size": 32 }, "mean": 1.46817409, "model_dtype": "bf16", "model_type": "mingtok", "pixel_decoder": { "decoder_depth": 24, "embed_dim": 1024, "loss_type": "L1-plain", "norm_pix_loss": true, "patch_size": 16 }, "pretrained_checkpoint": "/mnt/nativemm-hn/checkpoint/ziyuan/moe_mingtok/mingtok_moe_0830_recon_0830_bef_joint_training_resize_dec_p16d24c1024_s2noresize/gan_v2_20M/202509281648/checkpoint_1_hf.pth", "scaling_factor": 8.09449291, "semantic_decoder": { "decoder_depth": 24, "embed_dim": 1024, "ffn_layer": "swiglufused", "in_dim": 32, "patch_size": 32 }, "torch_dtype": "float32", "transformers_version": "4.52.4" }