-
Notifications
You must be signed in to change notification settings - Fork 93
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[P1] Error(s) in loading state_dict for Linear #115
Comments
@Hamana0509 Thanks for raising the issue. I probably need more info to debug here. I checked your published HF model json file: https://huggingface.co/Hamana0509/ReFT_Orpo_Llama3_8B_Instruct/blob/main/config.json It seems like the intervention has a low rank dimension size of 2. And the saved weights have a low rank dimension size of 4. Did you overwrite those saved weights somehow? If not, could you try to randomly initialize a model, and save the initialized model, and reload again? And you can also manually check the dimension of saved weights by using the |
@frankaging Thank you for answering my question. Here is my source code: I use ORPOReftTrainer, which is re-implemented from ORPOTrainer of the trl package, I don't know if my trainer overrides any model parameters anymore. |
I tried to load and combine ReFT modules to the base model. I got the following error:
My saving ReFT modules code:
My combine ReFT modules code:
The text was updated successfully, but these errors were encountered: