Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,19 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+onnx/prompt_encoder_mask_decoder.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/prompt_encoder_mask_decoder_bnb4.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/prompt_encoder_mask_decoder_fp16.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/prompt_encoder_mask_decoder_int8.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/prompt_encoder_mask_decoder_q4.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/prompt_encoder_mask_decoder_q4f16.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/prompt_encoder_mask_decoder_quantized.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/prompt_encoder_mask_decoder_uint8.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/vision_encoder.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/vision_encoder_bnb4.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/vision_encoder_fp16.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/vision_encoder_int8.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/vision_encoder_q4.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/vision_encoder_q4f16.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/vision_encoder_quantized.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/vision_encoder_uint8.onnx_data filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,239 @@
+{
+  "architectures": [
+    "Sam2Model"
+  ],
+  "dtype": "float32",
+  "enable_occlusion_spatial_embedding": false,
+  "enable_temporal_pos_encoding_for_object_pointers": false,
+  "image_size": 1024,
+  "initializer_range": 0.02,
+  "mask_decoder_config": {
+    "attention_downsample_rate": 2,
+    "dtype": "float32",
+    "dynamic_multimask_stability_delta": 0.05,
+    "dynamic_multimask_stability_thresh": 0.98,
+    "dynamic_multimask_via_stability": true,
+    "hidden_act": "gelu",
+    "hidden_size": 256,
+    "iou_head_depth": 3,
+    "iou_head_hidden_dim": 256,
+    "mlp_dim": 2048,
+    "model_type": "",
+    "num_attention_heads": 8,
+    "num_hidden_layers": 2,
+    "num_multimask_outputs": 3
+  },
+  "mask_downsampler_embed_dim": 256,
+  "mask_downsampler_hidden_act": "gelu",
+  "mask_downsampler_kernel_size": 3,
+  "mask_downsampler_padding": 1,
+  "mask_downsampler_stride": 2,
+  "mask_downsampler_total_stride": 16,
+  "max_object_pointers_in_encoder": 16,
+  "memory_attention_downsample_rate": 1,
+  "memory_attention_dropout": 0.1,
+  "memory_attention_feed_forward_hidden_act": "relu",
+  "memory_attention_feed_forward_hidden_size": 2048,
+  "memory_attention_hidden_size": 256,
+  "memory_attention_num_attention_heads": 1,
+  "memory_attention_num_layers": 4,
+  "memory_attention_rope_dropout": 0.1,
+  "memory_attention_rope_feat_sizes": [
+    64,
+    64
+  ],
+  "memory_attention_rope_theta": 10000,
+  "memory_encoder_hidden_size": 256,
+  "memory_encoder_output_channels": 64,
+  "memory_fuser_embed_dim": 256,
+  "memory_fuser_hidden_act": "gelu",
+  "memory_fuser_intermediate_dim": 1024,
+  "memory_fuser_kernel_size": 7,
+  "memory_fuser_layer_scale_init_value": 1e-06,
+  "memory_fuser_num_layers": 2,
+  "memory_fuser_padding": 3,
+  "model_type": "sam2",
+  "multimask_max_pt_num": 1,
+  "multimask_min_pt_num": 0,
+  "multimask_output_for_tracking": true,
+  "multimask_output_in_sam": true,
+  "num_maskmem": 7,
+  "prompt_encoder_config": {
+    "dtype": "float32",
+    "hidden_act": "gelu",
+    "hidden_size": 256,
+    "image_size": 1024,
+    "layer_norm_eps": 1e-06,
+    "mask_input_channels": 16,
+    "model_type": "",
+    "num_point_embeddings": 4,
+    "patch_size": 16,
+    "scale": 1
+  },
+  "sigmoid_bias_for_mem_enc": -10.0,
+  "sigmoid_scale_for_mem_enc": 20.0,
+  "transformers_version": "5.0.0.dev0",
+  "vision_config": {
+    "backbone_channel_list": [
+      768,
+      384,
+      192,
+      96
+    ],
+    "backbone_config": {
+      "_name_or_path": "",
+      "add_cross_attention": false,
+      "architectures": null,
+      "bad_words_ids": null,
+      "begin_suppress_tokens": null,
+      "blocks_per_stage": [
+        1,
+        2,
+        7,
+        2
+      ],
+      "bos_token_id": null,
+      "chunk_size_feed_forward": 0,
+      "cross_attention_hidden_size": null,
+      "decoder_start_token_id": null,
+      "diversity_penalty": 0.0,
+      "do_sample": false,
+      "dtype": null,
+      "early_stopping": false,
+      "embed_dim_per_stage": [
+        96,
+        192,
+        384,
+        768
+      ],
+      "encoder_no_repeat_ngram_size": 0,
+      "eos_token_id": null,
+      "exponential_decay_length_penalty": null,
+      "finetuning_task": null,
+      "forced_bos_token_id": null,
+      "forced_eos_token_id": null,
+      "global_attention_blocks": [
+        5,
+        7,
+        9
+      ],
+      "hidden_act": "gelu",
+      "hidden_size": 96,
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "image_size": [
+        1024,
+        1024
+      ],
+      "initializer_range": 0.02,
+      "is_decoder": false,
+      "is_encoder_decoder": false,
+      "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+      },
+      "layer_norm_eps": 1e-06,
+      "length_penalty": 1.0,
+      "max_length": 20,
+      "min_length": 0,
+      "mlp_ratio": 4.0,
+      "model_type": "sam2_hiera_det_model",
+      "no_repeat_ngram_size": 0,
+      "num_attention_heads": 1,
+      "num_attention_heads_per_stage": [
+        1,
+        2,
+        4,
+        8
+      ],
+      "num_beam_groups": 1,
+      "num_beams": 1,
+      "num_channels": 3,
+      "num_query_pool_stages": 3,
+      "num_return_sequences": 1,
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "output_scores": false,
+      "pad_token_id": null,
+      "patch_kernel_size": [
+        7,
+        7
+      ],
+      "patch_padding": [
+        3,
+        3
+      ],
+      "patch_stride": [
+        4,
+        4
+      ],
+      "prefix": null,
+      "problem_type": null,
+      "pruned_heads": {},
+      "query_stride": [
+        2,
+        2
+      ],
+      "remove_invalid_values": false,
+      "repetition_penalty": 1.0,
+      "return_dict": true,
+      "return_dict_in_generate": false,
+      "sep_token_id": null,
+      "suppress_tokens": null,
+      "task_specific_params": null,
+      "temperature": 1.0,
+      "tf_legacy_loss": false,
+      "tie_encoder_decoder": false,
+      "tie_word_embeddings": true,
+      "tokenizer_class": null,
+      "top_k": 50,
+      "top_p": 1.0,
+      "torchscript": false,
+      "typical_p": 1.0,
+      "use_bfloat16": false,
+      "window_positional_embedding_background_size": [
+        7,
+        7
+      ],
+      "window_size_per_stage": [
+        8,
+        4,
+        14,
+        7
+      ]
+    },
+    "backbone_feature_sizes": [
+      [
+        256,
+        256
+      ],
+      [
+        128,
+        128
+      ],
+      [
+        64,
+        64
+      ]
+    ],
+    "dtype": "float32",
+    "fpn_hidden_size": 256,
+    "fpn_kernel_size": 1,
+    "fpn_padding": 0,
+    "fpn_stride": 1,
+    "fpn_top_down_levels": [
+      2,
+      3
+    ],
+    "hidden_act": "gelu",
+    "initializer_range": 0.02,
+    "layer_norm_eps": 1e-06,
+    "model_type": "sam2_vision_model",
+    "num_feature_levels": 3
+  },
+  "transformers.js_config": {
+    "use_external_data_format": true
+  }
+}

onnx/prompt_encoder_mask_decoder.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbcdeb3696544e81c7b58f682f857b20c2cf1eb8fae7d5dbf61f8844d879a84b
+size 213114

onnx/prompt_encoder_mask_decoder.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f43b57795ac5b7c71d4ff1a72ffbb3bfe36d54cd911edb7ab5b6a9ca6acd12b9
+size 20958208

onnx/prompt_encoder_mask_decoder_bnb4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be00eb5842055b2339f34177a0b4f6cd8d0ceac3bfad76180f979e4be8559235
+size 228219

onnx/prompt_encoder_mask_decoder_bnb4.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c46c58af74fc19a5908ed908e30ab0b282f65473948a541021ad22915a6db64
+size 6870016

onnx/prompt_encoder_mask_decoder_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:080e4508e5df765a6d7d959d25c1d53755e04c2b5ee213403a386deec03c38ab
+size 229799

onnx/prompt_encoder_mask_decoder_fp16.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe430a918c9e5765f182207c7fce2984e292eefea0f6f4301dbb9e98fec24400
+size 10454016

onnx/prompt_encoder_mask_decoder_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76859b7c543528b957c5b95a120bbf0b916e9ce4ff711e1a2f30bca6d6e5bde9
+size 289885

onnx/prompt_encoder_mask_decoder_int8.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0157c99b78c66cb4104df576fcc24434638ae7c1e446b19e1659a37a3ccb40d
+size 8662016

onnx/prompt_encoder_mask_decoder_q4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d8d9f4fccdfa8b47be7c44e92ca9e463bc4f082e46d8ae1c95477d85d6fc0bf
+size 226444

onnx/prompt_encoder_mask_decoder_q4.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a01ca7a785d21605a1887e9687e15dc531c04bb0a8d33560df53e0834d7c594a
+size 7130112

onnx/prompt_encoder_mask_decoder_q4f16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03d3b196e4f187d5787a86eed5cf7a8dfbc224520e8b8ebe1029076fe2ee07af
+size 243598

onnx/prompt_encoder_mask_decoder_q4f16.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17227a1b60a361c0433a8185eac74601d9d644df4a5fd41d07a87ff44e8fb62e
+size 4563968

onnx/prompt_encoder_mask_decoder_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1becce19628b45b79677fdc4070907cc5eebaae1355b03bde56309af1766334d
+size 290416

onnx/prompt_encoder_mask_decoder_quantized.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0157c99b78c66cb4104df576fcc24434638ae7c1e446b19e1659a37a3ccb40d
+size 8662016

onnx/prompt_encoder_mask_decoder_uint8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3baffceb20fabbb1b0f43b15d0b9ef59690b3f25419136c44970d0a4758b0035
+size 290021

onnx/prompt_encoder_mask_decoder_uint8.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:874b5237c3e6418f40f6f09e1c96b7765a0ef27f85d19c781bb711c2199156e4
+size 8662016

onnx/vision_encoder.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed1487d6ef0a449f99c8d0dc401c49335a5ae383533d0aa8c7903b2734a1b893
+size 354238

onnx/vision_encoder.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20eef3b82600c5f51ae366516675074eeb5043c45ab24a8af5f643834066fc3a
+size 134084864

onnx/vision_encoder_bnb4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fbf56817f5115b70e0910982074fa817cef6a399b4f31e477eb5aa09412defa
+size 367275

onnx/vision_encoder_bnb4.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c70352a648e474c85fd667c18e799dceb18eb2ab1ef7bd2d3775778d1f6c21e
+size 42085568

onnx/vision_encoder_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c318d9ce41420758dd1b0cd555fe064de1e1dc5437362b93aac75cb1af7c25a
+size 314925

onnx/vision_encoder_fp16.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c025fccaf314aea6b7ce904db949764e97f34b3e0c127feb4d73cb2e1751af96
+size 67005504

onnx/vision_encoder_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f5a1fd42956634c31397781b1d9569a25eddb4e3124ab53f88138806174941e
+size 440423

onnx/vision_encoder_int8.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c57174725941eeafd0f7ec43e96fd165569514fb154f45ab50a58bf7a6ba90e
+size 52573088

onnx/vision_encoder_q4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:646acb6b5b52b80448524654d02a26cc550d2ae7701318fcb22e78665cf117aa
+size 366089

onnx/vision_encoder_q4.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f60abfaab485489fcc028afd949e28284523f91d5fdc7eb87bdee94603d15bc6
+size 43758848

onnx/vision_encoder_q4f16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:687c0b8db970682b9d238d20229fa950dde951c31ddc930645e449cc98dd564a
+size 327108

onnx/vision_encoder_q4f16.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad2373ff4c004ea828a5c91f74d01bf7ce0f93a0df85b274bc65052293a5b160
+size 28532736

onnx/vision_encoder_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cacc51b627cdb5549ee4042c668edad7a6131bc3a982c3f01dd9ef620debcbe
+size 441167

onnx/vision_encoder_quantized.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c231954acd1255c6670065e53516f331dad02e2de64bb8a3b3ac77363bd16813
+size 52573088

onnx/vision_encoder_uint8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:200c39f302a8d36eb0196d47fb97c000f82e790cabe25f5d95805c4e0112778b
+size 440595

onnx/vision_encoder_uint8.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c231954acd1255c6670065e53516f331dad02e2de64bb8a3b3ac77363bd16813
+size 52573088

preprocessor_config.json

@@ -0,0 +1,39 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "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": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "Sam2ImageProcessorFast",
+  "image_seq_length": null,
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "input_data_format": null,
+  "mask_size": {
+    "height": 256,
+    "width": 256
+  },
+  "pad_size": null,
+  "processor_class": "Sam2VideoProcessor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "return_tensors": null,
+  "size": {
+    "height": 1024,
+    "width": 1024
+  }
+}

processor_config.json

@@ -0,0 +1,44 @@
+{
+  "image_processor": {
+    "crop_size": null,
+    "data_format": "channels_first",
+    "default_to_square": true,
+    "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": [
+      0.485,
+      0.456,
+      0.406
+    ],
+    "image_processor_type": "Sam2ImageProcessorFast",
+    "image_seq_length": null,
+    "image_std": [
+      0.229,
+      0.224,
+      0.225
+    ],
+    "input_data_format": null,
+    "mask_size": {
+      "height": 256,
+      "width": 256
+    },
+    "pad_size": null,
+    "processor_class": "Sam2Processor",
+    "resample": 2,
+    "rescale_factor": 0.00392156862745098,
+    "return_tensors": null,
+    "size": {
+      "height": 1024,
+      "width": 1024
+    }
+  },
+  "point_pad_value": -10,
+  "processor_class": "Sam2Processor",
+  "target_size": 1024
+}