Commit
•
e5e7aaf
1
Parent(s):
739cb2d
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
To use this model, you need to load by `AutoModelForSequenceClassification`,
|
| 2 |
```python
|
| 3 |
model = AutoModelForSequenceClassification.from_pretrained(
|
|
|
|
| 1 |
+
# Training
|
| 2 |
+
|
| 3 |
+
The base model is `mistralai/Mistral-7B-Instruct-v0.2`.
|
| 4 |
+
|
| 5 |
+
We also merge the training script at https://github.com/WeiXiongUST/RLHF-Reward-Modeling.
|
| 6 |
+
|
| 7 |
+
Thanks Wei (https://huggingface.co/weqweasdas) for his help and contribution to the community.
|
| 8 |
+
|
| 9 |
+
# Usage
|
| 10 |
+
|
| 11 |
To use this model, you need to load by `AutoModelForSequenceClassification`,
|
| 12 |
```python
|
| 13 |
model = AutoModelForSequenceClassification.from_pretrained(
|