-
Notifications
You must be signed in to change notification settings - Fork 11
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
Automation failing when pulling from huggingface #197
Comments
@anandhu-eng can you please replace the huggingface download with the MLCommons download for llama2-70b? |
@stopiamwarren have you got the access to the llama2 models in huggingface? |
I'm not sure how I would do this |
Yes ![]() |
@stopiamwarren Then thats strange as the git clone should have worked. Did it fail immediately or after a while? The download is over 300G and so it can take hours. One other thing to try is to using hugglingface-cli to authenticate and after that you won't need to put password during the run. |
Hi @stopiamwarren , were you able to execute the script successfully? One other possibility could be insufficient storage. As @arjunsuresh pointed out, did it fail after a while? |
The issue resolved itself with no explanation after I pulled the most recent version of the repo. |
When I attempt to run the llama2-70B benchmark natively, it will get to the hugging face login, ask me to login twice, and then error out.
The text was updated successfully, but these errors were encountered: