-
Notifications
You must be signed in to change notification settings - Fork 554
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
[LLM] Training Vicuna on Llama-2 #2281
Conversation
ecf15af
to
afcf70c
Compare
llm/vicuna-2/serve.yaml
Outdated
|
||
envs: | ||
MODEL_SIZE: 7 | ||
MODEL_CKPT: <bucket-path-to-your-model-ckpt> |
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.
Consider either using this or ARTIFACT_BUCKET_NAME in train.yaml, to be consistent.
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.
Since the checkpoint can be a sub-directory in the bucket path, such as bucket-path/checkpoint-2400
, it might be better to let the user specify the whole path and call it MODEL_CKPT
? Wdyt?
c29cd9e
to
cd2e987
Compare
Co-authored-by: Zongheng Yang <zongheng.y@gmail.com>
Co-authored-by: Zongheng Yang <zongheng.y@gmail.com>
Blocked by #2330
Tested (run the relevant ones):
bash format.sh
pytest tests/test_smoke.py
pytest tests/test_smoke.py::test_fill_in_the_name
bash tests/backward_comaptibility_tests.sh