Instructions to use TCMVince/HOP4NLP5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use TCMVince/HOP4NLP5 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="TCMVince/HOP4NLP5", trust_remote_code=True)# Load model directly from transformers import AutoModelForMaskedLM model = AutoModelForMaskedLM.from_pretrained("TCMVince/HOP4NLP5", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
Update mlm.py
Browse files
mlm.py
CHANGED
|
@@ -577,9 +577,9 @@ class BertEnergyModelForSequenceClassification(BertPreTrainedModel):
|
|
| 577 |
loss_fct = BCEWithLogitsLoss()
|
| 578 |
loss = loss_fct(logits, labels)
|
| 579 |
|
| 580 |
-
if not return_dict:
|
| 581 |
-
|
| 582 |
-
|
| 583 |
|
| 584 |
return SequenceClassifierOutput(
|
| 585 |
loss=loss,
|
|
|
|
| 577 |
loss_fct = BCEWithLogitsLoss()
|
| 578 |
loss = loss_fct(logits, labels)
|
| 579 |
|
| 580 |
+
#if not return_dict:
|
| 581 |
+
# output = (logits, outputs.hidden_states, outputs.attentions)
|
| 582 |
+
# return ((loss,) + output) if loss is not None else output
|
| 583 |
|
| 584 |
return SequenceClassifierOutput(
|
| 585 |
loss=loss,
|