Update README.md

README.md

@@ -31,6 +31,9 @@ We evaluate GRM on the [reward model benchmark](https://huggingface.co/spaces/al
 
 
 ## Usage
+**Note 1: Please download the `model.py` file from this repository to ensure the structure is loaded correctly and verify that the `v_head` is properly initialized.**
+
+**Note 2: loading llama3 model into 8 bit could lead to performance degradation.**
 ```
 import torch
 from transformers import AutoTokenizer, AutoModelForSequenceClassification
@@ -56,7 +59,6 @@ with torch.no_grad():
   reward = reward_tensor.cpu().detach().item()
 ```
 
-**Note: loading llama3 model into 8 bit could lead to performance degradation.**
 
 ## Citation
 If you find this model helpful for your research, please cite GRM