Update tiny models for Sam3ViTModel

config.json

@@ -0,0 +1,28 @@
+{
+  "architectures": [
+    "Sam3ViTModel"
+  ],
+  "attention_dropout": 0.0,
+  "dtype": "float32",
+  "global_attn_indexes": [
+    0,
+    1
+  ],
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 32,
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 64,
+  "layer_norm_eps": 1e-06,
+  "layer_scale_init_value": null,
+  "model_type": "sam3_vit_model",
+  "num_attention_heads": 4,
+  "num_channels": 3,
+  "num_hidden_layers": 2,
+  "patch_size": 14,
+  "pretrain_image_size": 336,
+  "rope_theta": 10000.0,
+  "transformers_version": "5.16.0.dev0",
+  "window_size": 8
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95b20c2e26e6cbfdc79ddc469fbe2ba706f5545b5f7a4ceb00a3afca873e7d26
+size 220944

preprocessor_config.json

@@ -0,0 +1,31 @@
+{
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "Sam3ImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "mask_size": {
+    "height": 288,
+    "width": 288
+  },
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "is_local": true,
+  "local_files_only": false,
+  "max_length": 32,
+  "model_max_length": 32,
+  "pad_token": "<|endoftext|>",
+  "processor_class": "Sam3VideoProcessor",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": "<|endoftext|>"
+}

video_preprocessor_config.json

@@ -0,0 +1,28 @@
+{
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "return_metadata": false,
+  "size": {
+    "height": 224,
+    "width": 224
+  },
+  "video_processor_type": "Sam2VideoVideoProcessor"
+}