Instructions to use facebook/sapiens2-normal-1b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sapiens2
How to use facebook/sapiens2-normal-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-normal-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-normal-1b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("depth-estimation", model="facebook/sapiens2-normal-1b")# pip install -U transformers accelerate # Load model directly from transformers import AutoImageProcessor, Sapiens2ForNormalEstimation processor = AutoImageProcessor.from_pretrained("facebook/sapiens2-normal-1b") model = Sapiens2ForNormalEstimation.from_pretrained("facebook/sapiens2-normal-1b", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Remove 'pos_embed_dtype' from config.json
Browse files- config.json +0 -1
config.json
CHANGED
|
@@ -106,7 +106,6 @@
|
|
| 106 |
40
|
| 107 |
],
|
| 108 |
"patch_size": 16,
|
| 109 |
-
"pos_embed_dtype": "bfloat16",
|
| 110 |
"pos_embed_jitter": null,
|
| 111 |
"pos_embed_rescale": 2.0,
|
| 112 |
"pos_embed_shift": null,
|
|
|
|
| 106 |
40
|
| 107 |
],
|
| 108 |
"patch_size": 16,
|
|
|
|
| 109 |
"pos_embed_jitter": null,
|
| 110 |
"pos_embed_rescale": 2.0,
|
| 111 |
"pos_embed_shift": null,
|