-
Notifications
You must be signed in to change notification settings - Fork 18
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
Unable to merge reward adapter into model #5
Comments
I'm having the same issue |
Please make sure your input model path is correct
According to my experience, the probability is that the problem is due to the version of peft, please take a look at /peft/tuners/lora.py The current installation from git is version 0.3.0.dev0, there is a problem in merge_peft_adapter, need to switch to peft==0.2.0 (0.3.0.dev0 does not have _get_submodules() this function) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Calling
python merge_peft_adapter.py --model_name ./reward_model_vicuna-7b
yields
When calling
python -m bitsandbytes
, I do getSUCCESS! Installation was successful!
.When calling
python merge_peft_adapter.py --model_name ./reward_model_vicuna-7b_100_2e-05/
, I get the errorafter loading checkpoint shards.
The text was updated successfully, but these errors were encountered: