Pytorch example encoded_input fix (#1)
Browse files- Pytorch example encoded_input fix (7f37b8ae4e695eb4bf112857159f1eac25bfdd75)
Co-authored-by: Dmitrii Ogurtsov <[email protected]>
README.md
CHANGED
|
@@ -49,7 +49,7 @@ Here is how to use this model to get the features of a given text in PyTorch:
|
|
| 49 |
tokenizer = BertTokenizer.from_pretrained('tbs17/MathBERT-custom')
|
| 50 |
model = BertModel.from_pretrained("tbs17/MathBERT-custom")
|
| 51 |
text = "Replace me by any text you'd like."
|
| 52 |
-
encoded_input = tokenizer(text, return_tensors='pt')
|
| 53 |
output = model(encoded_input)
|
| 54 |
```
|
| 55 |
and in TensorFlow:
|
|
|
|
| 49 |
tokenizer = BertTokenizer.from_pretrained('tbs17/MathBERT-custom')
|
| 50 |
model = BertModel.from_pretrained("tbs17/MathBERT-custom")
|
| 51 |
text = "Replace me by any text you'd like."
|
| 52 |
+
encoded_input = tokenizer(text, return_tensors='pt')["input_ids"]
|
| 53 |
output = model(encoded_input)
|
| 54 |
```
|
| 55 |
and in TensorFlow:
|