Update tiny models for Sapiens2ForPoseEstimation

config.json

@@ -0,0 +1,143 @@
+{
+  "architectures": [
+    "Sapiens2ForPoseEstimation"
+  ],
+  "attention_dropout": 0.0,
+  "attention_probs_dropout_prob": 0.1,
+  "drop_path_rate": 0.0,
+  "dtype": "float32",
+  "flip_pairs": [
+    [
+      1,
+      2
+    ],
+    [
+      3,
+      4
+    ]
+  ],
+  "head_config": {
+    "_name_or_path": "",
+    "architectures": null,
+    "chunk_size_feed_forward": 0,
+    "conv_kernel_size": 1,
+    "conv_kernel_sizes": [
+      1,
+      1,
+      1
+    ],
+    "conv_out_channels": [
+      4,
+      4,
+      4
+    ],
+    "dtype": null,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "model_type": "sapiens2_head",
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "problem_type": null,
+    "return_dict": true,
+    "scale_conv_kernel_size": 1,
+    "scale_conv_kernel_sizes": [
+      1,
+      1,
+      1
+    ],
+    "scale_conv_out_channels": [
+      8,
+      4,
+      4
+    ],
+    "scale_final_hidden_sizes": [
+      8,
+      4
+    ],
+    "scale_final_input_size": 16,
+    "upsample_kernel_size": 4,
+    "upsample_kernel_sizes": [
+      4,
+      4,
+      4,
+      4
+    ],
+    "upsample_out_channels": [
+      8,
+      4,
+      4,
+      4
+    ],
+    "use_pixel_shuffle": null
+  },
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 32,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3"
+  },
+  "image_size": 30,
+  "initializer_range": 0.02,
+  "intermediate_size": 37,
+  "is_decoder": false,
+  "key_bias": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3
+  },
+  "layerscale_value": 1.0,
+  "mlp_bias": true,
+  "model_type": "sapiens2",
+  "normalize_backbone_outputs": true,
+  "num_attention_heads": 4,
+  "num_channels": 3,
+  "num_first_full_attention_layers": 8,
+  "num_hidden_layers": 2,
+  "num_key_value_attention_heads": 8,
+  "num_key_value_heads_per_layer": [
+    4,
+    4
+  ],
+  "num_last_full_attention_layers": 8,
+  "num_register_tokens": 2,
+  "out_features": [
+    "stem",
+    "stage1"
+  ],
+  "out_indices": [
+    0,
+    1
+  ],
+  "patch_size": 2,
+  "pos_embed_jitter": null,
+  "pos_embed_rescale": 2.0,
+  "pos_embed_shift": null,
+  "proj_bias": true,
+  "query_bias": true,
+  "reshape_hidden_states": true,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 100.0,
+  "semantic_loss_ignore_index": 255,
+  "stage_names": [
+    "stem",
+    "stage1",
+    "stage2"
+  ],
+  "transformers_version": "5.16.0.dev0",
+  "use_gated_mlp": true,
+  "use_mask_token": false,
+  "use_qk_norm": true,
+  "value_bias": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a313cee3a13415b5287bdae5adbcc0f83e4d79ac09a5cd09fdc685e72a53f49
+size 91912

preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "crop_size": {
+    "height": 30,
+    "width": 30
+  },
+  "do_center_crop": false,
+  "do_normalize": true,
+  "do_pad": false,
+  "do_reduce_labels": false,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "Sapiens2ImageProcessor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 30,
+    "width": 30
+  }
+}