Commit
·
26229d9
1
Parent(s):
fd82b87
Update README.md
Browse files
README.md
CHANGED
@@ -26,7 +26,7 @@ Its training dataset consists of purely user-generated content [retry_and_contin
|
|
26 |
### Out-of-scope use
|
27 |
### How to use
|
28 |
|
29 |
-
This reward model can be loaded using the `AutoModelForSequenceClassification` functionality, with a GPT2 tokenizer
|
30 |
```python
|
31 |
from transformers import AutoTokenizer, AutoModelForSequenceClassification
|
32 |
|
|
|
26 |
### Out-of-scope use
|
27 |
### How to use
|
28 |
|
29 |
+
This reward model can be loaded using the `AutoModelForSequenceClassification` functionality, with a GPT2 tokenizer where the `pad_token_id` is set to the EOS token id, padding sides need to be set according to the configurations used during model training.
|
30 |
```python
|
31 |
from transformers import AutoTokenizer, AutoModelForSequenceClassification
|
32 |
|