Update tiny models for GroundingDinoModel

config.json

@@ -0,0 +1,118 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "GroundingDinoModel"
+  ],
+  "attention_dropout": 0.1,
+  "auxiliary_loss": false,
+  "backbone_config": {
+    "attention_probs_dropout_prob": 0.0,
+    "depths": [
+      1,
+      1,
+      1,
+      1
+    ],
+    "drop_path_rate": 0.1,
+    "embed_dim": 8,
+    "encoder_stride": 32,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.0,
+    "hidden_size": 64,
+    "image_size": 128,
+    "initializer_range": 0.02,
+    "layer_norm_eps": 1e-05,
+    "mlp_ratio": 4.0,
+    "model_type": "swin",
+    "num_channels": 3,
+    "num_heads": [
+      1,
+      1,
+      1,
+      1
+    ],
+    "num_layers": 4,
+    "out_features": [
+      "stage2",
+      "stage3",
+      "stage4"
+    ],
+    "out_indices": [
+      2,
+      3,
+      4
+    ],
+    "patch_size": 4,
+    "qkv_bias": true,
+    "stage_names": [
+      "stem",
+      "stage1",
+      "stage2",
+      "stage3",
+      "stage4"
+    ],
+    "use_absolute_embeddings": false,
+    "window_size": 7
+  },
+  "bbox_cost": 5.0,
+  "bbox_loss_coefficient": 5.0,
+  "class_cost": 1.0,
+  "d_model": 32,
+  "decoder_attention_heads": 4,
+  "decoder_bbox_embed_share": true,
+  "decoder_ffn_dim": 4,
+  "decoder_layers": 2,
+  "decoder_n_points": 6,
+  "disable_custom_kernels": false,
+  "dropout": 0.1,
+  "dtype": "float32",
+  "embedding_init_target": true,
+  "encoder_attention_heads": 4,
+  "encoder_ffn_dim": 4,
+  "encoder_layers": 2,
+  "encoder_n_points": 2,
+  "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": 7,
+  "model_type": "grounding-dino",
+  "num_feature_levels": 4,
+  "num_queries": 2,
+  "position_embedding_type": "sine",
+  "positional_embedding_temperature": 20,
+  "query_dim": 4,
+  "text_config": {
+    "add_cross_attention": false,
+    "attention_probs_dropout_prob": 0.1,
+    "bos_token_id": null,
+    "classifier_dropout": null,
+    "eos_token_id": null,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 8,
+    "initializer_range": 0.02,
+    "intermediate_size": 8,
+    "is_decoder": false,
+    "layer_norm_eps": 1e-12,
+    "max_position_embeddings": 200,
+    "model_type": "bert",
+    "num_attention_heads": 2,
+    "num_hidden_layers": 2,
+    "pad_token_id": 0,
+    "tie_word_embeddings": true,
+    "type_vocab_size": 2,
+    "use_cache": true,
+    "vocab_size": 30522
+  },
+  "text_enhancer_dropout": 0.0,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.16.0.dev0",
+  "two_stage": true,
+  "two_stage_bbox_embed_share": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f690783f685f060654bc87bdb070138a7310d6c9197c959eda19216417716343
+size 1713936

preprocessor_config.json

@@ -0,0 +1,25 @@
+{
+  "do_convert_annotations": true,
+  "do_normalize": true,
+  "do_pad": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "format": "coco_detection",
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "GroundingDinoImageProcessor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 1333,
+    "shortest_edge": 800
+  }
+}

tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "backend": "tokenizers",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "is_local": true,
+  "local_files_only": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "processor_class": "GroundingDinoProcessor",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}