Instructions to use NbAiLab/roberta_NCC_des_128 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use NbAiLab/roberta_NCC_des_128 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="NbAiLab/roberta_NCC_des_128")# Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("NbAiLab/roberta_NCC_des_128") model = AutoModelForMaskedLM.from_pretrained("NbAiLab/roberta_NCC_des_128") - Notebooks
- Google Colab
- Kaggle
small fix restart
Browse files- run_mlm_flax.py +1 -1
run_mlm_flax.py
CHANGED
|
@@ -508,7 +508,7 @@ if __name__ == "__main__":
|
|
| 508 |
init_value=0.0, end_value=training_args.learning_rate, transition_steps=training_args.warmup_steps
|
| 509 |
)
|
| 510 |
|
| 511 |
-
if
|
| 512 |
end_lr_value = training_args.learning_rate
|
| 513 |
else:
|
| 514 |
end_lr_value = 0
|
|
|
|
| 508 |
init_value=0.0, end_value=training_args.learning_rate, transition_steps=training_args.warmup_steps
|
| 509 |
)
|
| 510 |
|
| 511 |
+
if data_args.static_learning_rate:
|
| 512 |
end_lr_value = training_args.learning_rate
|
| 513 |
else:
|
| 514 |
end_lr_value = 0
|