-
Notifications
You must be signed in to change notification settings - Fork 51
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
[CI] Add Llama2 to torch compile tests #446
base: habana_main
Are you sure you want to change the base?
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM
# These scores were chosen to place within 6% range of values achieved using vLLM on HPU: | ||
# 0.148 - 0.164 | ||
# where on https://www.llama.com/llama2/: 0.146 is given | ||
model_name: "/mnt/weka/data/pytorch/llama2/Llama-2-7b-hf" |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Do we really want to use this model? IMO we should use "/mnt/weka/data/pytorch/llama2/Llama-2-7b-chat-hf"
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
We still have to support and improve LLama2 (as far as I know). I will change the model. Thanks
97812c5
to
ee53802
Compare
ee53802
to
3355ea2
Compare
Due to spread of results I cant set score to be within 6% margin for chat version of model.
No description provided.