{ "model_type": "vosr", "version": "2.0", "dim": 1536, "depth": 36, "num_heads": 24, "mlp_ratio": 4, "patch_size": 2, "latent_channels": 16, "train_tokens": 32, "enc_dim": 1024, "encdim_ratio": 3, "dino_depth": 18, "dino_heads": 16, "dino_size": 448, "dino_patch": 14, "vae_base_dim": 96, "vae_dim_mult": [ 1, 2, 4, 4 ], "vae_res_blocks": 2, "latents_mean": [ -0.7571, -0.7089, -0.9113, 0.1075, -0.1745, 0.9653, -0.1517, 1.5508, 0.4134, -0.0715, 0.5517, -0.3632, -0.1922, -0.9497, 0.2503, -0.2921 ], "latents_std": [ 2.8184, 1.4541, 2.3275, 2.6558, 1.2196, 1.7708, 2.6052, 2.0743, 3.2687, 2.1526, 2.8652, 1.5579, 1.6382, 1.1253, 2.8251, 1.916 ], "quantization": { "group_size": 64, "bits": 8, "mode": "affine" }, "precision": "8bit" }