Upload model

config.json

@@ -1,6 +1,6 @@
 {
   "architectures": [
-    "Sam2Model"
+    "Sam2VideoModel"
   ],
   "binarize_mask_from_pts_for_mem_enc": true,
   "enable_occlusion_spatial_embedding": true,
@@ -25,44 +25,38 @@
     "num_multimask_outputs": 3,
     "two_way_transformer_activation": "relu"
   },
+  "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_config": {
-    "apply_pe_at_cross_attn_keys": true,
-    "apply_pe_at_cross_attn_queries": false,
-    "apply_pe_at_self_attn": false,
-    "attention_downsample_rate": 1,
-    "dim_feedforward": 2048,
-    "dropout": 0.1,
-    "hidden_act": "relu",
-    "hidden_size": 256,
-    "model_type": "",
-    "num_attention_heads": 1,
-    "num_layers": 4,
-    "rope_dropout": 0.1,
-    "rope_feat_sizes": [
-      64,
-      64
-    ],
-    "rope_theta": 10000
-  },
-  "memory_encoder_config": {
-    "hidden_size": 256,
-    "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,
-    "memory_fuser_embed_dim": 256,
-    "memory_fuser_hidden_act": "gelu",
-    "memory_fuser_kernel_size": 7,
-    "memory_fuser_layer_scale_init_value": 1e-06,
-    "memory_fuser_num_layers": 2,
-    "memory_fuser_padding": 3,
-    "memory_fuser_use_depthwise_conv": true,
-    "model_type": "",
-    "output_channels": 64
-  },
+  "memory_attention_apply_pe_at_cross_attn_keys": true,
+  "memory_attention_apply_pe_at_cross_attn_queries": false,
+  "memory_attention_apply_pe_at_self_attn": false,
+  "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_kernel_size": 7,
+  "memory_fuser_layer_scale_init_value": 1e-06,
+  "memory_fuser_num_layers": 2,
+  "memory_fuser_padding": 3,
+  "memory_fuser_use_depthwise_conv": true,
   "model_type": "sam2",
   "multimask_max_pt_num": 1,
   "multimask_min_pt_num": 0,
@@ -76,7 +70,6 @@
   "prompt_encoder_config": {
     "hidden_act": "gelu",
     "hidden_size": 256,
-    "image_embedding_size": 64,
     "image_size": 1024,
     "layer_norm_eps": 1e-06,
     "mask_input_channels": 16,
@@ -96,6 +89,108 @@
       288,
       144
     ],
+    "backbone_config": {
+      "_name_or_path": "",
+      "add_cross_attention": false,
+      "architectures": null,
+      "bad_words_ids": null,
+      "begin_suppress_tokens": null,
+      "bos_token_id": null,
+      "chunk_size_feed_forward": 0,
+      "cross_attention_hidden_size": null,
+      "decoder_start_token_id": null,
+      "dim_mul": 2.0,
+      "diversity_penalty": 0.0,
+      "do_sample": false,
+      "drop_path_rate": 0.0,
+      "early_stopping": false,
+      "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": [
+        23,
+        33,
+        43
+      ],
+      "head_mul": 2.0,
+      "hidden_act": "gelu",
+      "hidden_size": 144,
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "image_size": 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,
+      "model_type": "sam2_hiera_det_model",
+      "no_repeat_ngram_size": 0,
+      "num_attention_heads": 2,
+      "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,
+      "patch_padding": 3,
+      "patch_stride": 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,
+      "stages": [
+        2,
+        6,
+        36,
+        4
+      ],
+      "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,
+      "torch_dtype": null,
+      "torchscript": false,
+      "typical_p": 1.0,
+      "use_bfloat16": false,
+      "window_positional_embedding_background_size": [
+        7,
+        7
+      ],
+      "window_spec": [
+        8,
+        4,
+        16,
+        8
+      ]
+    },
     "backbone_feature_sizes": [
       [
         256,
@@ -110,8 +205,6 @@
         64
       ]
     ],
-    "dim_mul": 2.0,
-    "drop_path_rate": 0.0,
     "fpn_hidden_size": 256,
     "fpn_interpolation_mode": "nearest",
     "fpn_kernel_size": 1,
@@ -122,44 +215,10 @@
       3
     ],
     "fuse_type": "sum",
-    "global_attention_blocks": [
-      23,
-      33,
-      43
-    ],
-    "head_mul": 2.0,
     "hidden_act": "gelu",
-    "hidden_size": 144,
-    "image_size": 1024,
     "initializer_range": 0.02,
     "layer_norm_eps": 1e-06,
     "model_type": "sam2_vision_model",
-    "num_attention_heads": 2,
-    "num_channels": 3,
-    "num_feature_levels": 3,
-    "patch_kernel_size": 7,
-    "patch_padding": 3,
-    "patch_stride": 4,
-    "q_pool": 3,
-    "q_stride": [
-      2,
-      2
-    ],
-    "stages": [
-      2,
-      6,
-      36,
-      4
-    ],
-    "window_positional_embedding_background_size": [
-      7,
-      7
-    ],
-    "window_spec": [
-      8,
-      4,
-      16,
-      8
-    ]
+    "num_feature_levels": 3
   }
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39eda68a503f0d6c8a785b4afcec4f4ec0e1b8b5dcc4acd2e0941f4672faee2b
-size 897892408
+oid sha256:d281251cae94754e9c7a2313d45b5f2420cb97024e379f7da3fbcb217a8aabe6
+size 897897680