Update README.md
Browse files
README.md
CHANGED
|
@@ -36,6 +36,20 @@ This is a fine-tuned ModernBERT model for binary fact-checking classification, t
|
|
| 36 |
- Medical/legal claim verification
|
| 37 |
- Highly domain-specific claims
|
| 38 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 39 |
## Training Data
|
| 40 |
|
| 41 |
The model was trained on a combination of four datasets:
|
|
|
|
| 36 |
- Medical/legal claim verification
|
| 37 |
- Highly domain-specific claims
|
| 38 |
|
| 39 |
+
### How to use
|
| 40 |
+
|
| 41 |
+
```
|
| 42 |
+
python
|
| 43 |
+
from transformers import AutoTokenizer, AutoModelForSequenceClassification
|
| 44 |
+
|
| 45 |
+
tokenizer = AutoTokenizer.from_pretrained("your-username/modernbert-factchecking")
|
| 46 |
+
model = AutoModelForSequenceClassification.from_pretrained("your-username/modernbert-factchecking")
|
| 47 |
+
|
| 48 |
+
inputs = tokenizer("Your claim to verify here", return_tensors="pt", truncation=True, max_length=512)
|
| 49 |
+
outputs = model(**inputs)
|
| 50 |
+
predictions = torch.softmax(outputs.logits, dim=-1)
|
| 51 |
+
```
|
| 52 |
+
|
| 53 |
## Training Data
|
| 54 |
|
| 55 |
The model was trained on a combination of four datasets:
|