Update README.md
Browse files
README.md
CHANGED
@@ -10,8 +10,11 @@ GPT2 large model trained on Anthropic/hh-rlhf harmless dataset. It is specifical
|
|
10 |
|
11 |
It achieves an accuracy of 0.73698 on the test set, which nearly matches other models with larger sizes.
|
12 |
|
13 |
-
Usage:
|
14 |
```
|
|
|
|
|
|
|
15 |
rm_tokenizer = AutoTokenizer.from_pretrained(rm_tokenizer_path)
|
16 |
reward_model = AutoModelForSequenceClassification.from_pretrained(
|
17 |
reward_peft_path1,
|
|
|
10 |
|
11 |
It achieves an accuracy of 0.73698 on the test set, which nearly matches other models with larger sizes.
|
12 |
|
13 |
+
## Usage:
|
14 |
```
|
15 |
+
import torch
|
16 |
+
from transformers import AutoTokenizer, AutoModelForSequenceClassification
|
17 |
+
|
18 |
rm_tokenizer = AutoTokenizer.from_pretrained(rm_tokenizer_path)
|
19 |
reward_model = AutoModelForSequenceClassification.from_pretrained(
|
20 |
reward_peft_path1,
|