Instructions to use magicslabnu/OutEffHop_bert_base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use magicslabnu/OutEffHop_bert_base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="magicslabnu/OutEffHop_bert_base", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("magicslabnu/OutEffHop_bert_base", trust_remote_code=True) model = AutoModelForMaskedLM.from_pretrained("magicslabnu/OutEffHop_bert_base", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update modeling_bert.py
Browse files- modeling_bert.py +1 -0
modeling_bert.py
CHANGED
|
@@ -56,6 +56,7 @@ from ...utils import (
|
|
| 56 |
)
|
| 57 |
from .configuration_bert import BertConfig
|
| 58 |
|
|
|
|
| 59 |
|
| 60 |
def softmax_n_shifted_zeros(input: torch.Tensor, n: int, dim=-1) -> torch.Tensor:
|
| 61 |
"""
|
|
|
|
| 56 |
)
|
| 57 |
from .configuration_bert import BertConfig
|
| 58 |
|
| 59 |
+
BertModel.register_for_auto_class("AutoModel")
|
| 60 |
|
| 61 |
def softmax_n_shifted_zeros(input: torch.Tensor, n: int, dim=-1) -> torch.Tensor:
|
| 62 |
"""
|