Upload model

config.json

@@ -4,15 +4,58 @@
   ],
   "initializer_range": 0.02,
   "mask_decoder_config": {
-    "model_type": ""
+    "attention_downsample_rate": 2,
+    "hidden_act": "relu",
+    "hidden_size": 256,
+    "iou_head_depth": 3,
+    "iou_head_hidden_dim": 256,
+    "layer_norm_eps": 1e-06,
+    "mlp_dim": 2048,
+    "model_type": "",
+    "num_attention_heads": 8,
+    "num_hidden_layers": 2,
+    "num_multimask_outputs": 3,
+    "vit_dim": 768
   },
   "model_type": "sam_hq",
   "prompt_encoder_config": {
-    "model_type": ""
+    "hidden_act": "gelu",
+    "hidden_size": 256,
+    "image_embedding_size": 64,
+    "image_size": 1024,
+    "layer_norm_eps": 1e-06,
+    "mask_input_channels": 16,
+    "model_type": "",
+    "num_point_embeddings": 4,
+    "patch_size": 16
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.50.0.dev0",
+  "transformers_version": "4.52.0.dev0",
   "vision_config": {
-    "model_type": ""
+    "attention_dropout": 0.0,
+    "global_attn_indexes": [
+      2,
+      5,
+      8,
+      11
+    ],
+    "hidden_act": "gelu",
+    "hidden_size": 768,
+    "image_size": 1024,
+    "initializer_range": 1e-10,
+    "layer_norm_eps": 1e-06,
+    "mlp_dim": 3072,
+    "mlp_ratio": 4.0,
+    "model_type": "sam_hq_vision_model",
+    "num_attention_heads": 12,
+    "num_channels": 3,
+    "num_hidden_layers": 12,
+    "num_pos_feats": 128,
+    "output_channels": 256,
+    "patch_size": 16,
+    "qkv_bias": true,
+    "use_abs_pos": true,
+    "use_rel_pos": true,
+    "window_size": 14
   }
 }