from openmind import pipeline
unmasker = pipeline('fill-mask', model='huangjingwang/BERT-Autocorrector', device_map="npu")
print(unmasker("Hello I'm a <mask> model."))This model is a fine-tuned version of Twitter/twhin-bert-large on the None dataset. It achieves the following results on the evaluation set:
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.4071 | 1.0 | 150 | 2.2551 |
| 2.3437 | 2.0 | 300 | 2.1579 |
| 2.0723 | 3.0 | 450 | 2.0777 |
| 2.1794 | 4.0 | 600 | 2.0741 |
| 2.0892 | 5.0 | 750 | 2.0642 |