Load the reward model with the following code | |
```python | |
from reward_modelling.reward_model import RewardModel | |
rm = RewardModel.from_pretrained('oliversssf2/distilbert-base-uncased-rm-helpful') | |
``` |
Load the reward model with the following code | |
```python | |
from reward_modelling.reward_model import RewardModel | |
rm = RewardModel.from_pretrained('oliversssf2/distilbert-base-uncased-rm-helpful') | |
``` |