Upload folder using huggingface_hub

README.md

@@ -0,0 +1,441 @@
+---
+library_name: transformers
+pipeline_tag: text-generation
+inference: true
+widget:
+  - text: Hello!
+    example_title: Hello world
+    group: Python
+base_model:
+- facebook/sam3
+---
+
+This tiny model is intended for debugging. It is randomly initialized using the configuration adapted from [facebook/sam3](https://huggingface.co/facebook/sam3).
+
+### Example usage:
+
+```python
+import requests
+import torch
+from PIL import Image
+from transformers import Sam3Model, Sam3Processor
+from transformers.models.sam3.modeling_sam3 import Sam3Config
+
+model_id = "tiny-random/sam3"
+device = "cuda" if torch.cuda.is_available() else "cpu"
+model = Sam3Model.from_pretrained(model_id).to(device)
+processor = Sam3Processor.from_pretrained(model_id)
+
+kitchen_url = "http://images.cocodataset.org/val2017/000000136466.jpg"
+kitchen_image = Image.open(requests.get(
+    kitchen_url, stream=True).raw).convert("RGB")
+# Segment "handle" but exclude the oven handle using a negative box
+text = "handle"
+# Negative box covering oven handle area (xyxy): [40, 183, 318, 204]
+oven_handle_box = [40, 183, 318, 204]
+input_boxes = [[oven_handle_box]]
+inputs = processor(
+    images=kitchen_image,
+    text=text,
+    input_boxes=input_boxes,
+    input_boxes_labels=[[0]],  # 0 = negative (exclude this region)
+    return_tensors="pt"
+).to(device)
+with torch.no_grad():
+    outputs = model(**inputs)
+# Post-process results
+results = processor.post_process_instance_segmentation(
+    outputs,
+    threshold=0.5,
+    mask_threshold=0.5,
+    target_sizes=inputs.get("original_sizes").tolist()
+)[0]
+print(results)
+# This will segment pot handles but exclude the oven handle
+```
+
+### Codes to create this repo:
+
+```python
+import json
+from pathlib import Path
+
+import accelerate
+import torch
+from huggingface_hub import file_exists, hf_hub_download
+from transformers import (
+    AutoConfig,
+    AutoModelForCausalLM,
+    AutoProcessor,
+    GenerationConfig,
+    Sam3Processor,
+    set_seed,
+)
+from transformers.models.sam3.modeling_sam3 import Sam3Config, Sam3Model
+
+source_model_id = "facebook/sam3"
+save_folder = "/tmp/tiny-random/sam3"
+
+processor = Sam3Processor.from_pretrained(
+    source_model_id, trust_remote_code=True)
+processor.save_pretrained(save_folder)
+
+with open(hf_hub_download(source_model_id, filename='config.json', repo_type='model'), 'r', encoding='utf-8') as f:
+    config_json = json.load(f)
+HIDDEN_SIZE = 16
+INTERMEDIATE_SIZE = 32
+NUM_ATTENTION_HEADS = 2
+config_json['detector_config']['detr_decoder_config'].update({
+    'hidden_size': HIDDEN_SIZE,
+    'intermediate_size': INTERMEDIATE_SIZE,
+    'num_attention_heads': NUM_ATTENTION_HEADS,
+})
+config_json['detector_config']['detr_encoder_config'].update({
+    'hidden_size': HIDDEN_SIZE,
+    'intermediate_size': INTERMEDIATE_SIZE,
+    'num_attention_heads': NUM_ATTENTION_HEADS,
+})
+config_json['detector_config']['geometry_encoder_config'].update({
+    'hidden_size': HIDDEN_SIZE,
+    'intermediate_size': INTERMEDIATE_SIZE,
+    'num_attention_heads': NUM_ATTENTION_HEADS,
+})
+config_json['detector_config']['mask_decoder_config'].update({
+    'hidden_size': HIDDEN_SIZE,
+    'intermediate_size': INTERMEDIATE_SIZE,
+    'num_attention_heads': NUM_ATTENTION_HEADS,
+})
+config_json['detector_config']['text_config'].update({
+    'hidden_size': HIDDEN_SIZE,
+    'intermediate_size': INTERMEDIATE_SIZE,
+    'num_attention_heads': NUM_ATTENTION_HEADS,
+    'projection_dim': HIDDEN_SIZE,
+    'num_hidden_layers': 2,
+})
+config_json['detector_config']['vision_config']['backbone_config'].update({
+    'hidden_size': HIDDEN_SIZE,
+    'intermediate_size': INTERMEDIATE_SIZE,
+    'num_attention_heads': NUM_ATTENTION_HEADS,
+    'fpn_hidden_size': HIDDEN_SIZE,
+    'global_attn_indexes': [1, 3, 5, 7],
+    'num_hidden_layers': 8,
+})
+config_json['detector_config']['vision_config'].update({
+    'fpn_hidden_size': HIDDEN_SIZE,
+})
+config_json['tracker_config']['mask_decoder_config'].update({
+    'hidden_size': HIDDEN_SIZE,
+    'iou_head_hidden_dim': HIDDEN_SIZE,
+    'num_attention_heads': NUM_ATTENTION_HEADS,
+})
+config_json['tracker_config'].update({
+    'mask_downsampler_embed_dim': HIDDEN_SIZE,
+    'memory_attention_feed_forward_hidden_size': HIDDEN_SIZE,
+    'memory_attention_hidden_size': HIDDEN_SIZE,
+    'memory_encoder_hidden_size': HIDDEN_SIZE,
+    'memory_fuser_embed_dim': HIDDEN_SIZE,
+    'memory_fuser_intermediate_dim': INTERMEDIATE_SIZE,
+})
+config_json['tracker_config']['prompt_encoder_config'].update({
+    'hidden_size': HIDDEN_SIZE,
+    'intermediate_size': INTERMEDIATE_SIZE,
+    'num_attention_heads': NUM_ATTENTION_HEADS,
+})
+config_json['tracker_config']['vision_config']['backbone_config'].update({
+    'hidden_size': HIDDEN_SIZE,
+    'intermediate_size': INTERMEDIATE_SIZE,
+    'num_attention_heads': NUM_ATTENTION_HEADS,
+    'global_attn_indexes': [1, 3, 5, 7],
+    'num_hidden_layers': 8,
+})
+config_json['tracker_config']['vision_config'].update({
+    'fpn_hidden_size': HIDDEN_SIZE,
+})
+
+with open(f"{save_folder}/config.json", "w", encoding='utf-8') as f:
+    json.dump(config_json, f, indent=2)
+
+config = Sam3Config.from_pretrained(
+    save_folder,
+    trust_remote_code=True,
+)
+print(config)
+torch.set_default_dtype(torch.float32)
+model = Sam3Model(config)
+set_seed(42)
+model = model.cpu()
+with torch.no_grad():
+    for name, p in sorted(model.named_parameters()):
+        torch.nn.init.normal_(p, 0, 0.1)
+        print(name, p.shape)
+model.save_pretrained(save_folder)
+```
+
+### Printing the model:
+
+```text
+Sam3Model(
+  (vision_encoder): Sam3VisionModel(
+    (backbone): Sam3ViTModel(
+      (embeddings): Sam3ViTEmbeddings(
+        (patch_embeddings): Sam3ViTPatchEmbeddings(
+          (projection): Conv2d(3, 16, kernel_size=(14, 14), stride=(14, 14), bias=False)
+        )
+        (dropout): Dropout(p=0.0, inplace=False)
+      )
+      (layer_norm): LayerNorm((16,), eps=1e-06, elementwise_affine=True)
+      (layers): ModuleList(
+        (0-7): 8 x Sam3ViTLayer(
+          (layer_norm1): LayerNorm((16,), eps=1e-06, elementwise_affine=True)
+          (rotary_emb): Sam3ViTRotaryEmbedding()
+          (attention): Sam3ViTRoPEAttention(
+            (q_proj): Linear(in_features=16, out_features=16, bias=True)
+            (k_proj): Linear(in_features=16, out_features=16, bias=True)
+            (v_proj): Linear(in_features=16, out_features=16, bias=True)
+            (o_proj): Linear(in_features=16, out_features=16, bias=True)
+          )
+          (layer_norm2): LayerNorm((16,), eps=1e-06, elementwise_affine=True)
+          (mlp): Sam3MLP(
+            (activation_fn): GELUActivation()
+            (fc1): Linear(in_features=16, out_features=32, bias=True)
+            (fc2): Linear(in_features=32, out_features=16, bias=True)
+            (dropout): Dropout(p=0.0, inplace=False)
+          )
+          (dropout): Dropout(p=0.0, inplace=False)
+        )
+      )
+    )
+    (neck): Sam3VisionNeck(
+      (position_encoding): Sam3SinePositionEmbedding()
+      (fpn_layers): ModuleList(
+        (0): Sam3FPNLayer(
+          (scale_layers): ModuleList(
+            (0): ConvTranspose2d(16, 8, kernel_size=(2, 2), stride=(2, 2))
+            (1): GELU(approximate='none')
+            (2): ConvTranspose2d(8, 4, kernel_size=(2, 2), stride=(2, 2))
+          )
+          (proj1): Conv2d(4, 16, kernel_size=(1, 1), stride=(1, 1))
+          (proj2): Conv2d(16, 16, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+        )
+        (1): Sam3FPNLayer(
+          (scale_layers): ModuleList(
+            (0): ConvTranspose2d(16, 8, kernel_size=(2, 2), stride=(2, 2))
+          )
+          (proj1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1))
+          (proj2): Conv2d(16, 16, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+        )
+        (2): Sam3FPNLayer(
+          (scale_layers): ModuleList()
+          (proj1): Conv2d(16, 16, kernel_size=(1, 1), stride=(1, 1))
+          (proj2): Conv2d(16, 16, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+        )
+        (3): Sam3FPNLayer(
+          (scale_layers): ModuleList(
+            (0): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
+          )
+          (proj1): Conv2d(16, 16, kernel_size=(1, 1), stride=(1, 1))
+          (proj2): Conv2d(16, 16, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+        )
+      )
+    )
+  )
+  (text_encoder): CLIPTextModelWithProjection(
+    (text_model): CLIPTextTransformer(
+      (embeddings): CLIPTextEmbeddings(
+        (token_embedding): Embedding(49408, 16)
+        (position_embedding): Embedding(32, 16)
+      )
+      (encoder): CLIPEncoder(
+        (layers): ModuleList(
+          (0-1): 2 x CLIPEncoderLayer(
+            (self_attn): CLIPAttention(
+              (k_proj): Linear(in_features=16, out_features=16, bias=True)
+              (v_proj): Linear(in_features=16, out_features=16, bias=True)
+              (q_proj): Linear(in_features=16, out_features=16, bias=True)
+              (out_proj): Linear(in_features=16, out_features=16, bias=True)
+            )
+            (layer_norm1): LayerNorm((16,), eps=1e-05, elementwise_affine=True)
+            (mlp): CLIPMLP(
+              (activation_fn): GELUActivation()
+              (fc1): Linear(in_features=16, out_features=32, bias=True)
+              (fc2): Linear(in_features=32, out_features=16, bias=True)
+            )
+            (layer_norm2): LayerNorm((16,), eps=1e-05, elementwise_affine=True)
+          )
+        )
+      )
+      (final_layer_norm): LayerNorm((16,), eps=1e-05, elementwise_affine=True)
+    )
+    (text_projection): Linear(in_features=16, out_features=16, bias=False)
+  )
+  (text_projection): Linear(in_features=16, out_features=16, bias=True)
+  (geometry_encoder): Sam3GeometryEncoder(
+    (position_encoding): Sam3SinePositionEmbedding()
+    (label_embed): Embedding(2, 16)
+    (cls_embed): Embedding(1, 16)
+    (boxes_direct_project): Linear(in_features=4, out_features=16, bias=True)
+    (boxes_pool_project): Conv2d(16, 16, kernel_size=(7, 7), stride=(1, 1))
+    (boxes_pos_enc_project): Linear(in_features=18, out_features=16, bias=True)
+    (vision_layer_norm): LayerNorm((16,), eps=1e-05, elementwise_affine=True)
+    (final_proj): Linear(in_features=16, out_features=16, bias=True)
+    (prompt_layer_norm): LayerNorm((16,), eps=1e-05, elementwise_affine=True)
+    (layers): ModuleList(
+      (0-2): 3 x Sam3GeometryEncoderLayer(
+        (layer_norm1): LayerNorm((16,), eps=1e-05, elementwise_affine=True)
+        (self_attn): Sam3Attention(
+          (q_proj): Linear(in_features=16, out_features=16, bias=True)
+          (k_proj): Linear(in_features=16, out_features=16, bias=True)
+          (v_proj): Linear(in_features=16, out_features=16, bias=True)
+          (o_proj): Linear(in_features=16, out_features=16, bias=True)
+        )
+        (dropout): Dropout(p=0.1, inplace=False)
+        (cross_attn): Sam3Attention(
+          (q_proj): Linear(in_features=16, out_features=16, bias=True)
+          (k_proj): Linear(in_features=16, out_features=16, bias=True)
+          (v_proj): Linear(in_features=16, out_features=16, bias=True)
+          (o_proj): Linear(in_features=16, out_features=16, bias=True)
+        )
+        (layer_norm2): LayerNorm((16,), eps=1e-05, elementwise_affine=True)
+        (mlp): Sam3MLP(
+          (activation_fn): ReLU()
+          (fc1): Linear(in_features=16, out_features=32, bias=True)
+          (fc2): Linear(in_features=32, out_features=16, bias=True)
+          (dropout): Dropout(p=0.0, inplace=False)
+        )
+        (layer_norm3): LayerNorm((16,), eps=1e-05, elementwise_affine=True)
+      )
+    )
+    (output_layer_norm): LayerNorm((16,), eps=1e-05, elementwise_affine=True)
+  )
+  (detr_encoder): Sam3DetrEncoder(
+    (layers): ModuleList(
+      (0-5): 6 x Sam3DetrEncoderLayer(
+        (layer_norm1): LayerNorm((16,), eps=1e-05, elementwise_affine=True)
+        (self_attn): Sam3Attention(
+          (q_proj): Linear(in_features=16, out_features=16, bias=True)
+          (k_proj): Linear(in_features=16, out_features=16, bias=True)
+          (v_proj): Linear(in_features=16, out_features=16, bias=True)
+          (o_proj): Linear(in_features=16, out_features=16, bias=True)
+        )
+        (dropout): Dropout(p=0.1, inplace=False)
+        (cross_attn): Sam3Attention(
+          (q_proj): Linear(in_features=16, out_features=16, bias=True)
+          (k_proj): Linear(in_features=16, out_features=16, bias=True)
+          (v_proj): Linear(in_features=16, out_features=16, bias=True)
+          (o_proj): Linear(in_features=16, out_features=16, bias=True)
+        )
+        (layer_norm2): LayerNorm((16,), eps=1e-05, elementwise_affine=True)
+        (mlp): Sam3MLP(
+          (activation_fn): ReLU()
+          (fc1): Linear(in_features=16, out_features=32, bias=True)
+          (fc2): Linear(in_features=32, out_features=16, bias=True)
+          (dropout): Dropout(p=0.0, inplace=False)
+        )
+        (layer_norm3): LayerNorm((16,), eps=1e-05, elementwise_affine=True)
+      )
+    )
+  )
+  (detr_decoder): Sam3DetrDecoder(
+    (layers): ModuleList(
+      (0-5): 6 x Sam3DetrDecoderLayer(
+        (self_attn): Sam3Attention(
+          (q_proj): Linear(in_features=16, out_features=16, bias=True)
+          (k_proj): Linear(in_features=16, out_features=16, bias=True)
+          (v_proj): Linear(in_features=16, out_features=16, bias=True)
+          (o_proj): Linear(in_features=16, out_features=16, bias=True)
+        )
+        (self_attn_dropout): Dropout(p=0.1, inplace=False)
+        (self_attn_layer_norm): LayerNorm((16,), eps=1e-05, elementwise_affine=True)
+        (text_cross_attn): Sam3Attention(
+          (q_proj): Linear(in_features=16, out_features=16, bias=True)
+          (k_proj): Linear(in_features=16, out_features=16, bias=True)
+          (v_proj): Linear(in_features=16, out_features=16, bias=True)
+          (o_proj): Linear(in_features=16, out_features=16, bias=True)
+        )
+        (text_cross_attn_dropout): Dropout(p=0.1, inplace=False)
+        (text_cross_attn_layer_norm): LayerNorm((16,), eps=1e-05, elementwise_affine=True)
+        (vision_cross_attn): Sam3Attention(
+          (q_proj): Linear(in_features=16, out_features=16, bias=True)
+          (k_proj): Linear(in_features=16, out_features=16, bias=True)
+          (v_proj): Linear(in_features=16, out_features=16, bias=True)
+          (o_proj): Linear(in_features=16, out_features=16, bias=True)
+        )
+        (vision_cross_attn_dropout): Dropout(p=0.1, inplace=False)
+        (vision_cross_attn_layer_norm): LayerNorm((16,), eps=1e-05, elementwise_affine=True)
+        (mlp): Sam3MLP(
+          (activation_fn): ReLU()
+          (fc1): Linear(in_features=16, out_features=32, bias=True)
+          (fc2): Linear(in_features=32, out_features=16, bias=True)
+          (dropout): Dropout(p=0.0, inplace=False)
+        )
+        (mlp_layer_norm): LayerNorm((16,), eps=1e-05, elementwise_affine=True)
+        (mlp_dropout): Dropout(p=0.1, inplace=False)
+      )
+    )
+    (output_layer_norm): LayerNorm((16,), eps=1e-05, elementwise_affine=True)
+    (box_head): Sam3DecoderMLP(
+      (layer1): Linear(in_features=16, out_features=16, bias=True)
+      (layer2): Linear(in_features=16, out_features=16, bias=True)
+      (layer3): Linear(in_features=16, out_features=4, bias=True)
+    )
+    (query_embed): Embedding(200, 16)
+    (reference_points): Embedding(200, 4)
+    (presence_token): Embedding(1, 16)
+    (presence_head): Sam3DecoderMLP(
+      (layer1): Linear(in_features=16, out_features=16, bias=True)
+      (layer2): Linear(in_features=16, out_features=16, bias=True)
+      (layer3): Linear(in_features=16, out_features=1, bias=True)
+    )
+    (presence_layer_norm): LayerNorm((16,), eps=1e-05, elementwise_affine=True)
+    (ref_point_head): Sam3DecoderMLP(
+      (layer1): Linear(in_features=32, out_features=16, bias=True)
+      (layer2): Linear(in_features=16, out_features=16, bias=True)
+    )
+    (box_rpb_embed_x): Sam3DecoderMLP(
+      (layer1): Linear(in_features=2, out_features=16, bias=True)
+      (layer2): Linear(in_features=16, out_features=2, bias=True)
+    )
+    (box_rpb_embed_y): Sam3DecoderMLP(
+      (layer1): Linear(in_features=2, out_features=16, bias=True)
+      (layer2): Linear(in_features=16, out_features=2, bias=True)
+    )
+    (position_encoding): Sam3SinePositionEmbedding()
+  )
+  (mask_decoder): Sam3MaskDecoder(
+    (pixel_decoder): Sam3PixelDecoder(
+      (conv_layers): ModuleList(
+        (0-2): 3 x Conv2d(16, 16, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+      )
+      (norms): ModuleList(
+        (0-2): 3 x GroupNorm(8, 16, eps=1e-05, affine=True)
+      )
+    )
+    (mask_embedder): Sam3MaskEmbedder(
+      (layers): ModuleList(
+        (0-2): 3 x Linear(in_features=16, out_features=16, bias=True)
+      )
+      (activation): ReLU()
+    )
+    (instance_projection): Conv2d(16, 16, kernel_size=(1, 1), stride=(1, 1))
+    (semantic_projection): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1))
+    (prompt_cross_attn): Sam3Attention(
+      (q_proj): Linear(in_features=16, out_features=16, bias=True)
+      (k_proj): Linear(in_features=16, out_features=16, bias=True)
+      (v_proj): Linear(in_features=16, out_features=16, bias=True)
+      (o_proj): Linear(in_features=16, out_features=16, bias=True)
+    )
+    (prompt_cross_attn_norm): LayerNorm((16,), eps=1e-05, elementwise_affine=True)
+    (prompt_cross_attn_dropout): Dropout(p=0.0, inplace=False)
+  )
+  (dot_product_scoring): Sam3DotProductScoring(
+    (text_mlp): Sam3DecoderMLP(
+      (layer1): Linear(in_features=16, out_features=32, bias=True)
+      (layer2): Linear(in_features=32, out_features=16, bias=True)
+    )
+    (text_mlp_dropout): Dropout(p=0.1, inplace=False)
+    (text_mlp_out_norm): LayerNorm((16,), eps=1e-05, elementwise_affine=True)
+    (text_proj): Linear(in_features=16, out_features=16, bias=True)
+    (query_proj): Linear(in_features=16, out_features=16, bias=True)
+  )
+)
+```

config.json

@@ -0,0 +1,162 @@
+{
+  "architectures": [
+    "Sam3Model"
+  ],
+  "detr_decoder_config": {
+    "box_rpb_mode": "log",
+    "dropout": 0.1,
+    "hidden_act": "relu",
+    "hidden_dropout": 0.0,
+    "hidden_size": 16,
+    "initializer_range": 0.02,
+    "intermediate_size": 32,
+    "layer_norm_eps": 1e-06,
+    "model_type": "sam3_detr_decoder",
+    "num_attention_heads": 2,
+    "num_layers": 6,
+    "num_queries": 200,
+    "use_presence_token": true
+  },
+  "detr_encoder_config": {
+    "dropout": 0.1,
+    "hidden_act": "relu",
+    "hidden_dropout": 0.0,
+    "hidden_size": 16,
+    "initializer_range": 0.02,
+    "intermediate_size": 32,
+    "layer_norm_eps": 1e-06,
+    "model_type": "sam3_detr_encoder",
+    "num_attention_heads": 2,
+    "num_layers": 6
+  },
+  "dtype": "float32",
+  "geometry_encoder_config": {
+    "dropout": 0.1,
+    "hidden_act": "relu",
+    "hidden_dropout": 0.0,
+    "hidden_size": 16,
+    "initializer_range": 0.02,
+    "intermediate_size": 32,
+    "layer_norm_eps": 1e-06,
+    "model_type": "sam3_geometry_encoder",
+    "num_attention_heads": 2,
+    "num_layers": 3,
+    "roi_size": 7
+  },
+  "initializer_range": 0.02,
+  "mask_decoder_config": {
+    "dropout": 0.0,
+    "hidden_size": 16,
+    "initializer_range": 0.02,
+    "intermediate_size": 32,
+    "layer_norm_eps": 1e-06,
+    "model_type": "sam3_mask_decoder",
+    "num_attention_heads": 2,
+    "num_upsampling_stages": 3
+  },
+  "model_type": "sam3",
+  "text_config": {
+    "attention_dropout": 0.0,
+    "hidden_act": "gelu",
+    "hidden_size": 16,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 32,
+    "layer_norm_eps": 1e-05,
+    "max_position_embeddings": 32,
+    "model_type": "clip_text_model",
+    "num_attention_heads": 2,
+    "num_hidden_layers": 2,
+    "projection_dim": 16,
+    "vocab_size": 49408
+  },
+  "transformers_version": "5.0.0.dev0",
+  "vision_config": {
+    "backbone_config": {
+      "_name_or_path": "",
+      "add_cross_attention": false,
+      "architectures": null,
+      "attention_dropout": 0.0,
+      "bos_token_id": null,
+      "chunk_size_feed_forward": 0,
+      "cross_attention_hidden_size": null,
+      "decoder_start_token_id": null,
+      "dtype": null,
+      "eos_token_id": null,
+      "finetuning_task": null,
+      "fpn_hidden_size": 16,
+      "global_attn_indexes": [
+        1,
+        3,
+        5,
+        7
+      ],
+      "hidden_act": "gelu",
+      "hidden_dropout": 0.0,
+      "hidden_size": 16,
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "image_size": 1008,
+      "initializer_range": 0.02,
+      "intermediate_size": 32,
+      "is_decoder": false,
+      "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": 2,
+      "num_channels": 3,
+      "num_hidden_layers": 8,
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "pad_token_id": null,
+      "patch_size": 14,
+      "prefix": null,
+      "pretrain_image_size": 336,
+      "problem_type": null,
+      "qkv_bias": true,
+      "return_dict": true,
+      "rope_theta": 10000.0,
+      "sep_token_id": null,
+      "task_specific_params": null,
+      "tie_encoder_decoder": false,
+      "tie_word_embeddings": true,
+      "tokenizer_class": null,
+      "window_size": 24
+    },
+    "backbone_feature_sizes": [
+      [
+        288,
+        288
+      ],
+      [
+        144,
+        144
+      ],
+      [
+        72,
+        72
+      ]
+    ],
+    "fpn_hidden_size": 16,
+    "fpn_kernel_size": 2,
+    "fpn_stride": 2,
+    "hidden_act": "gelu",
+    "initializer_range": 0.02,
+    "layer_norm_eps": 1e-06,
+    "model_type": "sam3_vision_model",
+    "num_feature_levels": 3,
+    "scale_factors": [
+      4.0,
+      2.0,
+      1.0,
+      0.5
+    ]
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20016f8717edbf11d8a2cfbfc65f4c83548cefddfb7f5828332d37911c44f0bb
+size 4324560

processor_config.json

@@ -0,0 +1,43 @@
+{
+  "image_processor": {
+    "crop_size": null,
+    "data_format": "channels_first",
+    "device": null,
+    "disable_grouping": null,
+    "do_center_crop": null,
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_pad": null,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_processor_type": "Sam3ImageProcessorFast",
+    "image_seq_length": null,
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "input_data_format": null,
+    "mask_size": {
+      "height": 288,
+      "width": 288
+    },
+    "pad_size": null,
+    "processor_class": "Sam3Processor",
+    "resample": 2,
+    "rescale_factor": 0.00392156862745098,
+    "return_tensors": null,
+    "size": {
+      "height": 1008,
+      "width": 1008
+    }
+  },
+  "point_pad_value": -10,
+  "processor_class": "Sam3Processor",
+  "target_size": 1008
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "49406": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49407": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "max_length": 32,
+  "model_max_length": 32,
+  "pad_token": "<|endoftext|>",
+  "processor_class": "Sam3Processor",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": "<|endoftext|>"
+}