Upload config.json

config.json

@@ -1,56 +1,67 @@
 {
-    "model_name": "grounded",
-    "input_names": [
-        "img",
-        "input_ids",
-        "attention_mask",
-        "position_ids",
-        "token_type_ids",
-        "text_token_mask"
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "IDEA-Research/grounding-dino-tiny",
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "GroundingDinoForObjectDetection"
+  ],
+  "attention_dropout": 0.0,
+  "auxiliary_loss": false,
+  "backbone": null,
+  "backbone_config": {
+    "model_type": "swin",
+    "out_features": [
+      "stage2",
+      "stage3",
+      "stage4"
     ],
-    "output_names": [
-        "logits",
-        "boxes"
-    ],
-    "input_shapes": {
-        "img": [
-            "dynamic",
-            3,
-            "dynamic",
-            "dynamic"
-        ],
-        "input_ids": [
-            "dynamic",
-            "dynamic"
-        ],
-        "attention_mask": [
-            "dynamic",
-            "dynamic"
-        ],
-        "position_ids": [
-            "dynamic",
-            "dynamic"
-        ],
-        "token_type_ids": [
-            "dynamic",
-            "dynamic"
-        ],
-        "text_token_mask": [
-            "dynamic",
-            "dynamic",
-            "dynamic"
-        ]
-    },
-    "output_shapes": {
-        "logits": [
-            "dynamic",
-            "dynamic",
-            "dynamic"
-        ],
-        "boxes": [
-            "dynamic",
-            "dynamic",
-            4
-        ]
-    }
-}
+    "out_indices": [
+      2,
+      3,
+      4
+    ]
+  },
+  "backbone_kwargs": null,
+  "bbox_cost": 5.0,
+  "bbox_loss_coefficient": 5.0,
+  "class_cost": 1.0,
+  "d_model": 256,
+  "decoder_attention_heads": 8,
+  "decoder_bbox_embed_share": true,
+  "decoder_ffn_dim": 2048,
+  "decoder_layers": 6,
+  "decoder_n_points": 4,
+  "disable_custom_kernels": false,
+  "dropout": 0.1,
+  "embedding_init_target": true,
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 2048,
+  "encoder_layers": 6,
+  "encoder_n_points": 4,
+  "focal_alpha": 0.25,
+  "fusion_dropout": 0.0,
+  "fusion_droppath": 0.1,
+  "giou_cost": 2.0,
+  "giou_loss_coefficient": 2.0,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "layer_norm_eps": 1e-05,
+  "max_text_len": 256,
+  "model_type": "grounding-dino",
+  "num_feature_levels": 4,
+  "num_queries": 900,
+  "position_embedding_type": "sine",
+  "positional_embedding_temperature": 20,
+  "query_dim": 4,
+  "text_config": {
+    "model_type": "bert"
+  },
+  "text_enhancer_dropout": 0.0,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.1",
+  "two_stage": true,
+  "two_stage_bbox_embed_share": false,
+  "use_pretrained_backbone": false,
+  "use_timm_backbone": false
+}