Update README.md
Browse files
README.md
CHANGED
|
@@ -28,7 +28,7 @@ WWM ensures that all subword tokens of a selected word are masked together, enco
|
|
| 28 |
|
| 29 |
- **Developed by:** [Mohammad Mahdi Heydari Asl / infocube]
|
| 30 |
- **Funded by [optional]:** [More Information Needed]
|
| 31 |
-
- **Shared by:** [HYDARIM7]
|
| 32 |
- **Model type:** Transformer, BERT-based Masked Language Model
|
| 33 |
- **Language(s) (NLP):** Italian
|
| 34 |
- **License:** Apache-2.0
|
|
@@ -56,7 +56,6 @@ The model can be used for:
|
|
| 56 |
Users should verify outputs and avoid relying on predictions for legal decision-making without expert supervision.
|
| 57 |
|
| 58 |
|
| 59 |
-
## How to Get Started with the Model
|
| 60 |
## How to Get Started with the Model
|
| 61 |
|
| 62 |
```python
|
|
@@ -75,10 +74,9 @@ outputs = model(**inputs)
|
|
| 75 |
mask_token_index = torch.where(inputs["input_ids"][0] == tokenizer.mask_token_id)[0]
|
| 76 |
predicted_token_id = outputs.logits[0, mask_token_index].argmax(axis=-1)
|
| 77 |
print("Prediction:", tokenizer.decode(predicted_token_id))
|
|
|
|
| 78 |
|
| 79 |
|
| 80 |
-
### Training Data
|
| 81 |
-
|
| 82 |
### Training Data
|
| 83 |
|
| 84 |
- **Source:** Provided by *Infocube*,
|
|
|
|
| 28 |
|
| 29 |
- **Developed by:** [Mohammad Mahdi Heydari Asl / infocube]
|
| 30 |
- **Funded by [optional]:** [More Information Needed]
|
| 31 |
+
- **Shared by:** [[HYDARIM7](https://huggingface.co/InfocubeSrl/LexCube)]
|
| 32 |
- **Model type:** Transformer, BERT-based Masked Language Model
|
| 33 |
- **Language(s) (NLP):** Italian
|
| 34 |
- **License:** Apache-2.0
|
|
|
|
| 56 |
Users should verify outputs and avoid relying on predictions for legal decision-making without expert supervision.
|
| 57 |
|
| 58 |
|
|
|
|
| 59 |
## How to Get Started with the Model
|
| 60 |
|
| 61 |
```python
|
|
|
|
| 74 |
mask_token_index = torch.where(inputs["input_ids"][0] == tokenizer.mask_token_id)[0]
|
| 75 |
predicted_token_id = outputs.logits[0, mask_token_index].argmax(axis=-1)
|
| 76 |
print("Prediction:", tokenizer.decode(predicted_token_id))
|
| 77 |
+
```
|
| 78 |
|
| 79 |
|
|
|
|
|
|
|
| 80 |
### Training Data
|
| 81 |
|
| 82 |
- **Source:** Provided by *Infocube*,
|