Robotics
Transformers
ONNX
Safetensors
PyTorch
mvae
feature-extraction
prosoro
multimodal
custom_code
Instructions to use prosoro/prosoro-mvae with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use prosoro/prosoro-mvae with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("prosoro/prosoro-mvae", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
han-xudong commited on
Commit ·
69a3aa6
1
Parent(s): 56af139
modified: modeling.py
Browse files- modeling.py +1 -1
modeling.py
CHANGED
|
@@ -115,7 +115,7 @@ class MVAE(PreTrainedModel):
|
|
| 115 |
|
| 116 |
if prosoro_type is not None:
|
| 117 |
sub_path = os.path.join(pretrained_model_name_or_path, prosoro_type)
|
| 118 |
-
|
| 119 |
print(f"Loading prosoro type from subfolder: {sub_path}")
|
| 120 |
if os.path.isdir(sub_path):
|
| 121 |
pretrained_model_name_or_path = sub_path
|
|
|
|
| 115 |
|
| 116 |
if prosoro_type is not None:
|
| 117 |
sub_path = os.path.join(pretrained_model_name_or_path, prosoro_type)
|
| 118 |
+
sub_path = sub_path.replace("\\", "/")
|
| 119 |
print(f"Loading prosoro type from subfolder: {sub_path}")
|
| 120 |
if os.path.isdir(sub_path):
|
| 121 |
pretrained_model_name_or_path = sub_path
|