Add model

config.json

@@ -2145,51 +2145,19 @@
     "typical_p": 1.0,
     "use_bfloat16": false
   },
-  "decoder_config": {
-    "common_stride": 4,
-    "conv_dim": 256,
-    "decoder_layers": 10,
-    "dim_feedforward": 2048,
-    "dropout": 0.1,
-    "encoder_feedforward_dim": 1024,
-    "encoder_layers": 6,
-    "enforce_input_proj": false,
-    "hidden_dim": 256,
-    "mask_dim": 256,
-    "norm": "GN",
-    "num_heads": 8,
-    "pre_norm": false,
-    "query_dec_layers": 2,
-    "use_task_norm": true
-  },
-  "general_config": {
-    "class_weight": 2.0,
-    "contrastive_temperature": 0.07,
-    "contrastive_weight": 0.5,
-    "deep_supervision": true,
-    "dice_weight": 5.0,
-    "ignore_value": 255,
-    "importance_sample_ratio": 0.75,
-    "init_std": 0.02,
-    "init_xavier_std": 1.0,
-    "is_train": false,
-    "layer_norm_eps": 1e-05,
-    "mask_weight": 5.0,
-    "no_object_weight": 0.1,
-    "num_classes": 133,
-    "num_queries": 150,
-    "output_auxiliary_logits": true,
-    "oversample_ratio": 3.0,
-    "strides": [
-      4,
-      8,
-      16,
-      32
-    ],
-    "train_num_points": 12544,
-    "use_auxiliary_loss": true
-  },
-  "hidden_size": 256,
+  "class_weight": 2.0,
+  "common_stride": 4,
+  "contrastive_temperature": 0.07,
+  "contrastive_weight": 0.5,
+  "conv_dim": 256,
+  "decoder_layers": 10,
+  "dice_weight": 5.0,
+  "dim_feedforward": 2048,
+  "dropout": 0.1,
+  "encoder_feedforward_dim": 1024,
+  "encoder_layers": 6,
+  "enforce_input_proj": false,
+  "hidden_dim": 256,
   "id2label": {
     "0": "person",
     "1": "bicycle",
@@ -2325,8 +2293,11 @@
     "131": "wall-other-merged",
     "132": "rug-merged"
   },
+  "ignore_value": 255,
+  "importance_sample_ratio": 0.75,
   "init_std": 0.02,
   "init_xavier_std": 1.0,
+  "is_training": false,
   "label2id": {
     "airplane": 4,
     "apple": 47,
@@ -2462,21 +2433,39 @@
     "wine glass": 40,
     "zebra": 22
   },
+  "layer_norm_eps": 1e-05,
+  "mask_dim": 256,
+  "mask_weight": 5.0,
+  "max_seq_len": 77,
   "model_type": "oneformer",
+  "no_object_weight": 0.1,
+  "norm": "GN",
   "num_attention_heads": 8,
+  "num_classes": 133,
   "num_hidden_layers": 10,
+  "num_queries": 150,
   "output_attentions": true,
+  "output_auxiliary_logits": true,
   "output_hidden_states": true,
-  "text_encoder_config": {
-    "max_seq_len": 77,
-    "task_seq_len": 77,
-    "text_encoder_context_length": 77,
-    "text_encoder_n_ctx": 16,
-    "text_encoder_num_layers": 6,
-    "text_encoder_proj_layers": 2,
-    "text_encoder_vocab_size": 49408,
-    "text_encoder_width": 256
-  },
+  "oversample_ratio": 3.0,
+  "pre_norm": false,
+  "query_dec_layers": 2,
+  "strides": [
+    4,
+    8,
+    16,
+    32
+  ],
+  "task_seq_len": 77,
+  "text_encoder_context_length": 77,
+  "text_encoder_n_ctx": 16,
+  "text_encoder_num_layers": 6,
+  "text_encoder_proj_layers": 2,
+  "text_encoder_vocab_size": 49408,
+  "text_encoder_width": 256,
   "torch_dtype": "float32",
-  "transformers_version": null
+  "train_num_points": 12544,
+  "transformers_version": null,
+  "use_auxiliary_loss": true,
+  "use_task_norm": true
 }