Instructions to use ekolasky/CustomLEDForResultsIdOnSeperatedSet with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ekolasky/CustomLEDForResultsIdOnSeperatedSet with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="ekolasky/CustomLEDForResultsIdOnSeperatedSet", trust_remote_code=True)# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("ekolasky/CustomLEDForResultsIdOnSeperatedSet", trust_remote_code=True) model = AutoModel.from_pretrained("ekolasky/CustomLEDForResultsIdOnSeperatedSet", trust_remote_code=True) - Notebooks
- Google Colab
- Kaggle
Update modeling_CustomLEDForResultsId.py
Browse files
modeling_CustomLEDForResultsId.py
CHANGED
|
@@ -5,7 +5,7 @@ from transformers.modeling_outputs import TokenClassifierOutput
|
|
| 5 |
import torch.nn as nn
|
| 6 |
|
| 7 |
class CustomLEDForResultsIdModel(LEDPreTrainedModel):
|
| 8 |
-
def __init__(self, config: LEDConfig, checkpoint):
|
| 9 |
super().__init__(config)
|
| 10 |
self.num_labels = config.num_labels
|
| 11 |
print("Configs")
|
|
|
|
| 5 |
import torch.nn as nn
|
| 6 |
|
| 7 |
class CustomLEDForResultsIdModel(LEDPreTrainedModel):
|
| 8 |
+
def __init__(self, config: LEDConfig, checkpoint=None):
|
| 9 |
super().__init__(config)
|
| 10 |
self.num_labels = config.num_labels
|
| 11 |
print("Configs")
|