Skip to content
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

Merged
merged 69 commits into from
Aug 2, 2023
Merged

[LLM] Training Vicuna on Llama-2 #2281

merged 69 commits into from
Aug 2, 2023

Conversation

Michaelvll
Copy link
Collaborator

@Michaelvll Michaelvll commented Jul 20, 2023

Blocked by #2330

Tested (run the relevant ones):

  • Code formatting: bash format.sh
  • Any manual or new tests for this PR (please specify below)
  • All smoke tests: pytest tests/test_smoke.py
  • Relevant individual smoke tests: pytest tests/test_smoke.py::test_fill_in_the_name
  • Backward compatibility tests: bash tests/backward_comaptibility_tests.sh

@Michaelvll Michaelvll marked this pull request as ready for review July 20, 2023 20:11
@Michaelvll Michaelvll changed the title [WIP] Scripts for training Vicuna on Llama-2 [LLM] Training Vicuna on Llama-2 Jul 20, 2023
llm/vicuna-2/README.md Outdated Show resolved Hide resolved
llm/vicuna-2/train.yaml Outdated Show resolved Hide resolved
llm/vicuna-2/README.md Outdated Show resolved Hide resolved
llm/vicuna-2/serve.yaml Outdated Show resolved Hide resolved

envs:
MODEL_SIZE: 7
MODEL_CKPT: <bucket-path-to-your-model-ckpt>
Copy link
Member

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.

Copy link
Collaborator Author

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?

llm/vicuna-2/train.yaml Outdated Show resolved Hide resolved
llm/vicuna-llama-2/train.yaml Outdated Show resolved Hide resolved
llm/vicuna-llama-2/scripts/train.py Show resolved Hide resolved
llm/vicuna-llama-2/scripts/train.py Outdated Show resolved Hide resolved
llm/vicuna-llama-2/README.md Outdated Show resolved Hide resolved
llm/vicuna-llama-2/scripts/train.py Outdated Show resolved Hide resolved
README.md Outdated Show resolved Hide resolved
Michaelvll and others added 2 commits August 2, 2023 11:25
Co-authored-by: Zongheng Yang <zongheng.y@gmail.com>
Co-authored-by: Zongheng Yang <zongheng.y@gmail.com>
@Michaelvll Michaelvll removed the blocked PR blocked by other issues label Aug 2, 2023
@Michaelvll Michaelvll merged commit 7ad533a into master Aug 2, 2023
@Michaelvll Michaelvll deleted the train-vicuna-2 branch August 2, 2023 18:36
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants