Instructions to use facebook/sapiens2-pointmap-5b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sapiens
How to use facebook/sapiens2-pointmap-5b with sapiens:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- sapiens2
How to use facebook/sapiens2-pointmap-5b with sapiens2:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Update config.json and preprocessor_config.json
Browse files- config.json +49 -41
config.json
CHANGED
|
@@ -10,6 +10,7 @@
|
|
| 10 |
"_name_or_path": "",
|
| 11 |
"architectures": null,
|
| 12 |
"chunk_size_feed_forward": 0,
|
|
|
|
| 13 |
"conv_kernel_sizes": [
|
| 14 |
3,
|
| 15 |
3,
|
|
@@ -35,6 +36,7 @@
|
|
| 35 |
"output_hidden_states": false,
|
| 36 |
"problem_type": null,
|
| 37 |
"return_dict": true,
|
|
|
|
| 38 |
"scale_conv_kernel_sizes": [
|
| 39 |
1,
|
| 40 |
1,
|
|
@@ -50,6 +52,7 @@
|
|
| 50 |
128
|
| 51 |
],
|
| 52 |
"scale_final_input_size": 6144,
|
|
|
|
| 53 |
"upsample_kernel_sizes": [
|
| 54 |
3,
|
| 55 |
3,
|
|
@@ -83,13 +86,16 @@
|
|
| 83 |
"LABEL_1": 1,
|
| 84 |
"LABEL_2": 2
|
| 85 |
},
|
| 86 |
-
"layer_norm_eps": 1e-
|
| 87 |
"layerscale_value": 1.0,
|
| 88 |
"mlp_bias": true,
|
| 89 |
"model_type": "sapiens2",
|
|
|
|
| 90 |
"num_attention_heads": 32,
|
| 91 |
"num_channels": 3,
|
|
|
|
| 92 |
"num_hidden_layers": 56,
|
|
|
|
| 93 |
"num_key_value_heads_per_layer": [
|
| 94 |
32,
|
| 95 |
32,
|
|
@@ -99,46 +105,46 @@
|
|
| 99 |
32,
|
| 100 |
32,
|
| 101 |
32,
|
| 102 |
-
|
| 103 |
-
|
| 104 |
-
|
| 105 |
-
|
| 106 |
-
|
| 107 |
-
|
| 108 |
-
|
| 109 |
-
|
| 110 |
-
|
| 111 |
-
|
| 112 |
-
|
| 113 |
-
|
| 114 |
-
|
| 115 |
-
|
| 116 |
-
|
| 117 |
-
|
| 118 |
-
|
| 119 |
-
|
| 120 |
-
|
| 121 |
-
|
| 122 |
-
|
| 123 |
-
|
| 124 |
-
|
| 125 |
-
|
| 126 |
-
|
| 127 |
-
|
| 128 |
-
|
| 129 |
-
|
| 130 |
-
|
| 131 |
-
|
| 132 |
-
|
| 133 |
-
|
| 134 |
-
|
| 135 |
-
|
| 136 |
-
|
| 137 |
-
|
| 138 |
-
|
| 139 |
-
|
| 140 |
-
|
| 141 |
-
|
| 142 |
32,
|
| 143 |
32,
|
| 144 |
32,
|
|
@@ -148,6 +154,7 @@
|
|
| 148 |
32,
|
| 149 |
32
|
| 150 |
],
|
|
|
|
| 151 |
"num_register_tokens": 8,
|
| 152 |
"out_features": [
|
| 153 |
"stage56"
|
|
@@ -162,6 +169,7 @@
|
|
| 162 |
"proj_bias": true,
|
| 163 |
"query_bias": true,
|
| 164 |
"reshape_hidden_states": true,
|
|
|
|
| 165 |
"rope_theta": 100.0,
|
| 166 |
"semantic_loss_ignore_index": 255,
|
| 167 |
"stage_names": [
|
|
|
|
| 10 |
"_name_or_path": "",
|
| 11 |
"architectures": null,
|
| 12 |
"chunk_size_feed_forward": 0,
|
| 13 |
+
"conv_kernel_size": 1,
|
| 14 |
"conv_kernel_sizes": [
|
| 15 |
3,
|
| 16 |
3,
|
|
|
|
| 36 |
"output_hidden_states": false,
|
| 37 |
"problem_type": null,
|
| 38 |
"return_dict": true,
|
| 39 |
+
"scale_conv_kernel_size": 1,
|
| 40 |
"scale_conv_kernel_sizes": [
|
| 41 |
1,
|
| 42 |
1,
|
|
|
|
| 52 |
128
|
| 53 |
],
|
| 54 |
"scale_final_input_size": 6144,
|
| 55 |
+
"upsample_kernel_size": 4,
|
| 56 |
"upsample_kernel_sizes": [
|
| 57 |
3,
|
| 58 |
3,
|
|
|
|
| 86 |
"LABEL_1": 1,
|
| 87 |
"LABEL_2": 2
|
| 88 |
},
|
| 89 |
+
"layer_norm_eps": 1e-05,
|
| 90 |
"layerscale_value": 1.0,
|
| 91 |
"mlp_bias": true,
|
| 92 |
"model_type": "sapiens2",
|
| 93 |
+
"normalize_backbone_outputs": true,
|
| 94 |
"num_attention_heads": 32,
|
| 95 |
"num_channels": 3,
|
| 96 |
+
"num_first_full_attention_layers": 8,
|
| 97 |
"num_hidden_layers": 56,
|
| 98 |
+
"num_key_value_attention_heads": 8,
|
| 99 |
"num_key_value_heads_per_layer": [
|
| 100 |
32,
|
| 101 |
32,
|
|
|
|
| 105 |
32,
|
| 106 |
32,
|
| 107 |
32,
|
| 108 |
+
8,
|
| 109 |
+
8,
|
| 110 |
+
8,
|
| 111 |
+
8,
|
| 112 |
+
8,
|
| 113 |
+
8,
|
| 114 |
+
8,
|
| 115 |
+
8,
|
| 116 |
+
8,
|
| 117 |
+
8,
|
| 118 |
+
8,
|
| 119 |
+
8,
|
| 120 |
+
8,
|
| 121 |
+
8,
|
| 122 |
+
8,
|
| 123 |
+
8,
|
| 124 |
+
8,
|
| 125 |
+
8,
|
| 126 |
+
8,
|
| 127 |
+
8,
|
| 128 |
+
8,
|
| 129 |
+
8,
|
| 130 |
+
8,
|
| 131 |
+
8,
|
| 132 |
+
8,
|
| 133 |
+
8,
|
| 134 |
+
8,
|
| 135 |
+
8,
|
| 136 |
+
8,
|
| 137 |
+
8,
|
| 138 |
+
8,
|
| 139 |
+
8,
|
| 140 |
+
8,
|
| 141 |
+
8,
|
| 142 |
+
8,
|
| 143 |
+
8,
|
| 144 |
+
8,
|
| 145 |
+
8,
|
| 146 |
+
8,
|
| 147 |
+
8,
|
| 148 |
32,
|
| 149 |
32,
|
| 150 |
32,
|
|
|
|
| 154 |
32,
|
| 155 |
32
|
| 156 |
],
|
| 157 |
+
"num_last_full_attention_layers": 8,
|
| 158 |
"num_register_tokens": 8,
|
| 159 |
"out_features": [
|
| 160 |
"stage56"
|
|
|
|
| 169 |
"proj_bias": true,
|
| 170 |
"query_bias": true,
|
| 171 |
"reshape_hidden_states": true,
|
| 172 |
+
"rms_norm_eps": 1e-06,
|
| 173 |
"rope_theta": 100.0,
|
| 174 |
"semantic_loss_ignore_index": 255,
|
| 175 |
"stage_names": [
|