Instructions to use MUmairAB/bert-based-MaskedLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use MUmairAB/bert-based-MaskedLM with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="MUmairAB/bert-based-MaskedLM")# Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("MUmairAB/bert-based-MaskedLM") model = AutoModelForMaskedLM.from_pretrained("MUmairAB/bert-based-MaskedLM") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -21,6 +21,11 @@ It achieves the following results on the evaluation set:
|
|
| 21 |
- Validation Loss: 2.3284
|
| 22 |
- Epoch: 20
|
| 23 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 24 |
## Model description
|
| 25 |
|
| 26 |
[DistilBERT-base-uncased](https://huggingface.co/distilbert-base-uncased)
|
|
|
|
| 21 |
- Validation Loss: 2.3284
|
| 22 |
- Epoch: 20
|
| 23 |
|
| 24 |
+
## Training and validation loss during training
|
| 25 |
+
|
| 26 |
+
<img src="https://huggingface.co/MUmairAB/bert-based-MaskedLM/resolve/main/Loss%20plot.png" style="height: 432px; width:567px;"/>
|
| 27 |
+
|
| 28 |
+
|
| 29 |
## Model description
|
| 30 |
|
| 31 |
[DistilBERT-base-uncased](https://huggingface.co/distilbert-base-uncased)
|