Initial commit for new model

config.json

@@ -250,5 +250,30 @@
     "torchscript": false,
     "typical_p": 1.0,
     "use_bfloat16": false
+  },
+  "spatial_encoder_hidden_size": 768,
+  "num_attention_heads": 16,
+  "spatial_encoder_cfg": {
+    "architectures": [
+      "Mast3rEncoder"
+    ],
+    "pretrained_model_name_or_path": "../mast3r/checkpoints/MASt3R_ViTLarge_BaseDecoder_512_catmlpdpt_metric.pth",
+    "preprocessor_config": {
+      "do_convert_rgb": true,
+      "do_normalize": true,
+      "do_rescale": true,
+      "do_resize_and_center_crop": true,
+      "image_mean": [0.5, 0.5, 0.5],
+      "image_std": [0.5, 0.5, 0.5],
+      "resample": 3,
+      "rescale_factor": 0.00392156862745098,
+      "longest_edge": 512
+    }
+  },
+  "cross_attention_cfg": {
+    "architectures": [
+      "CrossAttention"
+    ],
+    "cross_attention_type": "cross_attn"
   }
 }