Update tiny models for Sam3Model

Browse files

Files changed (6) hide show

config.json +141 -0
model.safetensors +3 -0
preprocessor_config.json +31 -0
tokenizer.json +0 -0
tokenizer_config.json +17 -0
video_preprocessor_config.json +28 -0

config.json ADDED Viewed

	@@ -0,0 +1,141 @@

+{
+  "architectures": [
+    "Sam3Model"
+  ],
+  "detr_decoder_config": {
+    "dropout": 0.1,
+    "hidden_act": "relu",
+    "hidden_dropout": 0.0,
+    "hidden_size": 32,
+    "initializer_range": 0.02,
+    "intermediate_size": 64,
+    "layer_norm_eps": 1e-06,
+    "model_type": "sam3_detr_decoder",
+    "num_attention_heads": 4,
+    "num_layers": 1,
+    "num_queries": 5
+  },
+  "detr_encoder_config": {
+    "dropout": 0.1,
+    "hidden_act": "relu",
+    "hidden_dropout": 0.0,
+    "hidden_size": 32,
+    "initializer_range": 0.02,
+    "intermediate_size": 64,
+    "layer_norm_eps": 1e-06,
+    "model_type": "sam3_detr_encoder",
+    "num_attention_heads": 4,
+    "num_layers": 1
+  },
+  "dtype": "float32",
+  "geometry_encoder_config": {
+    "dropout": 0.1,
+    "hidden_act": "relu",
+    "hidden_dropout": 0.0,
+    "hidden_size": 32,
+    "initializer_range": 0.02,
+    "intermediate_size": 64,
+    "layer_norm_eps": 1e-06,
+    "mask_fuser_hidden_size": 32,
+    "mask_fuser_num_layers": 1,
+    "model_type": "sam3_geometry_encoder",
+    "num_attention_heads": 4,
+    "num_layers": 1,
+    "roi_size": 7
+  },
+  "initializer_range": 0.02,
+  "mask_decoder_config": {
+    "dropout": 0.0,
+    "hidden_size": 32,
+    "initializer_range": 0.02,
+    "layer_norm_eps": 1e-06,
+    "model_type": "sam3_mask_decoder",
+    "num_attention_heads": 8,
+    "num_upsampling_stages": 2
+  },
+  "model_type": "sam3",
+  "text_config": {
+    "attention_dropout": 0.0,
+    "bos_token_id": 49406,
+    "eos_token_id": 49407,
+    "hidden_act": "gelu",
+    "hidden_size": 32,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 64,
+    "layer_norm_eps": 1e-05,
+    "max_position_embeddings": 200,
+    "model_type": "clip_text_model",
+    "num_attention_heads": 4,
+    "num_hidden_layers": 2,
+    "pad_token_id": 49407,
+    "projection_dim": 32,
+    "vocab_size": 49408
+  },
+  "transformers_version": "5.16.0.dev0",
+  "vision_config": {
+    "backbone_config": {
+      "_name_or_path": "",
+      "architectures": null,
+      "attention_dropout": 0.0,
+      "chunk_size_feed_forward": 0,
+      "dtype": null,
+      "global_attn_indexes": [
+        0,
+        1
+      ],
+      "hidden_act": "gelu",
+      "hidden_dropout": 0.0,
+      "hidden_size": 32,
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "image_size": 224,
+      "initializer_range": 0.02,
+      "intermediate_size": 64,
+      "is_encoder_decoder": false,
+      "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+      },
+      "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,
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "patch_size": 14,
+      "pretrain_image_size": 336,
+      "problem_type": null,
+      "return_dict": true,
+      "rope_theta": 10000.0,
+      "window_size": 8
+    },
+    "backbone_feature_sizes": [
+      [
+        288,
+        288
+      ],
+      [
+        144,
+        144
+      ],
+      [
+        72,
+        72
+      ]
+    ],
+    "fpn_hidden_size": 32,
+    "hidden_act": "gelu",
+    "initializer_range": 0.02,
+    "layer_norm_eps": 1e-06,
+    "model_type": "sam3_vision_model",
+    "scale_factors": [
+      2.0,
+      1.0
+    ]
+  }
+}

model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:bf260be80d2ba90fc4a10962072e875326a867494569b5a8ec47a9ed7509341b
+size 7311400

preprocessor_config.json ADDED Viewed

	@@ -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.json ADDED Viewed

The diff for this file is too large to render. See raw diff

tokenizer_config.json ADDED Viewed

	@@ -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 ADDED Viewed

	@@ -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"
+}