Instructions to use facebook/sapiens2-pose-1b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sapiens2
How to use facebook/sapiens2-pose-1b 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
- sapiens
How to use facebook/sapiens2-pose-1b 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
- Transformers
How to use facebook/sapiens2-pose-1b with Transformers:
# Load model directly from transformers import AutoImageProcessor, Sapiens2ForPoseEstimation processor = AutoImageProcessor.from_pretrained("facebook/sapiens2-pose-1b") model = Sapiens2ForPoseEstimation.from_pretrained("facebook/sapiens2-pose-1b", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update config.json and preprocessor_config.json
Browse files- config.json +25 -25
config.json
CHANGED
|
@@ -1275,7 +1275,7 @@
|
|
| 1275 |
"num_channels": 3,
|
| 1276 |
"num_first_full_attention_layers": 8,
|
| 1277 |
"num_hidden_layers": 40,
|
| 1278 |
-
"num_key_value_attention_heads":
|
| 1279 |
"num_key_value_heads_per_layer": [
|
| 1280 |
24,
|
| 1281 |
24,
|
|
@@ -1285,30 +1285,30 @@
|
|
| 1285 |
24,
|
| 1286 |
24,
|
| 1287 |
24,
|
| 1288 |
-
|
| 1289 |
-
|
| 1290 |
-
|
| 1291 |
-
|
| 1292 |
-
|
| 1293 |
-
|
| 1294 |
-
|
| 1295 |
-
|
| 1296 |
-
|
| 1297 |
-
|
| 1298 |
-
|
| 1299 |
-
|
| 1300 |
-
|
| 1301 |
-
|
| 1302 |
-
|
| 1303 |
-
|
| 1304 |
-
|
| 1305 |
-
|
| 1306 |
-
|
| 1307 |
-
|
| 1308 |
-
|
| 1309 |
-
|
| 1310 |
-
|
| 1311 |
-
|
| 1312 |
24,
|
| 1313 |
24,
|
| 1314 |
24,
|
|
|
|
| 1275 |
"num_channels": 3,
|
| 1276 |
"num_first_full_attention_layers": 8,
|
| 1277 |
"num_hidden_layers": 40,
|
| 1278 |
+
"num_key_value_attention_heads": 12,
|
| 1279 |
"num_key_value_heads_per_layer": [
|
| 1280 |
24,
|
| 1281 |
24,
|
|
|
|
| 1285 |
24,
|
| 1286 |
24,
|
| 1287 |
24,
|
| 1288 |
+
12,
|
| 1289 |
+
12,
|
| 1290 |
+
12,
|
| 1291 |
+
12,
|
| 1292 |
+
12,
|
| 1293 |
+
12,
|
| 1294 |
+
12,
|
| 1295 |
+
12,
|
| 1296 |
+
12,
|
| 1297 |
+
12,
|
| 1298 |
+
12,
|
| 1299 |
+
12,
|
| 1300 |
+
12,
|
| 1301 |
+
12,
|
| 1302 |
+
12,
|
| 1303 |
+
12,
|
| 1304 |
+
12,
|
| 1305 |
+
12,
|
| 1306 |
+
12,
|
| 1307 |
+
12,
|
| 1308 |
+
12,
|
| 1309 |
+
12,
|
| 1310 |
+
12,
|
| 1311 |
+
12,
|
| 1312 |
24,
|
| 1313 |
24,
|
| 1314 |
24,
|