Update tiny models for TvpModel

config.json

@@ -0,0 +1,62 @@
+{
+  "alpha": 1.0,
+  "architectures": [
+    "TvpModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "backbone": null,
+  "backbone_config": {
+    "depths": [
+      2,
+      2
+    ],
+    "downsample_in_bottleneck": false,
+    "downsample_in_first_stage": false,
+    "embedding_size": 64,
+    "embeddings_size": 64,
+    "hidden_act": "relu",
+    "hidden_sizes": [
+      64,
+      128
+    ],
+    "layer_type": "bottleneck",
+    "model_type": "resnet",
+    "num_channels": 3,
+    "out_features": [
+      "stage2"
+    ],
+    "out_indices": [
+      2
+    ],
+    "stage_names": [
+      "stem",
+      "stage1",
+      "stage2"
+    ]
+  },
+  "beta": 0.1,
+  "distance_loss_weight": 1.0,
+  "dtype": "float32",
+  "duration_loss_weight": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 32,
+  "initializer_range": 0.02,
+  "intermediate_size": 32,
+  "layer_norm_eps": 1e-12,
+  "max_grid_col_position_embeddings": 30,
+  "max_grid_row_position_embeddings": 30,
+  "max_img_size": 448,
+  "max_position_embeddings": 200,
+  "model_type": "tvp",
+  "num_attention_heads": 4,
+  "num_frames": 2,
+  "num_hidden_layers": 2,
+  "pad_token_id": 0,
+  "transformers_version": "5.16.0.dev0",
+  "type_vocab_size": 2,
+  "visual_prompt_size": 96,
+  "visual_prompter_apply": "replace",
+  "visual_prompter_type": "framepad",
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5aa200b548a6bf9978090850d35458c637ff675c13749d5853ebf9d4cd841270
+size 7681208

preprocessor_config.json

@@ -0,0 +1,40 @@
+{
+  "constant_values": 0,
+  "crop_size": {
+    "height": 448,
+    "width": 448
+  },
+  "do_center_crop": false,
+  "do_flip_channel_order": true,
+  "do_normalize": true,
+  "do_pad": true,
+  "do_padding": true,
+  "do_rescale": false,
+  "do_resize": true,
+  "image_mean": [
+    8.2381,
+    7.3115,
+    6.6981
+  ],
+  "image_processor_type": "TvpImageProcessor",
+  "image_std": [
+    9.6335,
+    9.0659,
+    8.7213
+  ],
+  "pad_mode": "constant",
+  "pad_size": {
+    "height": 448,
+    "width": 448
+  },
+  "padding_size": {
+    "height": 448,
+    "width": 448
+  },
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 448
+  },
+  "tokenizer": "bert-base-uncased"
+}

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "backend": "tokenizers",
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "is_local": true,
+  "local_files_only": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 200,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}