-
Notifications
You must be signed in to change notification settings - Fork 30
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
Llama 3 compatibility #19
Comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
I tried two llama 3 8B models from huggingface by creating a new
config/model/.yaml
withname_or_path: meta-llama/Meta-Llama-3-8B
and also
name_or_path: NousResearch/Meta-Llama-3-8B
I am able to train the SFT model using the command
python train.py loss=sft model=llama_3_8b datasets=[shp,hh] exp_name=l38b_sft_0505 mode=train ++cache_dir=./data/models
However I face this error when I train the PPO model using the command
python train.py loss=ppo model=llama_3_8b datasets=[shp,hh] exp_name=l38b_ppo_0517 mode=train ++cache_dir=./data/models ++model.load_from=l38b_sft_0505/LATEST/policy.pt
Stacktrace:
The text was updated successfully, but these errors were encountered: