-
Notifications
You must be signed in to change notification settings - Fork 641
fix: update model path #3637
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
base: main
Are you sure you want to change the base?
fix: update model path #3637
Conversation
WalkthroughReplaces Hugging Face CLI + HF_TOKEN–based model download with an hf-transfer flow. Introduces HF_HOME, HF_HUB_ENABLE_HF_TRANSFER, and MODEL_REVISION. Pins download to a specific revision. Changes storage path and volume mount to /model-store. Removes secretKeyRef for HF_TOKEN and updates the download command and working directory. Changes
Sequence Diagram(s)sequenceDiagram
autonumber
participant J as K8s Job/Container
participant HF as Hugging Face Hub
participant FS as /model-store (Volume)
Note over J: Env: HF_HOME=/model-store<br/>HF_HUB_ENABLE_HF_TRANSFER=1<br/>MODEL_REVISION=<pin>
J->>FS: Set working directory to /model-store
J->>HF: hf download <model> --revision $MODEL_REVISION
HF-->>J: Stream artifacts (hf-transfer)
J->>FS: Write model files to /model-store
Note over J,FS: No HF_TOKEN secret used
Estimated code review effort🎯 2 (Simple) | ⏱️ ~10 minutes Poem
Pre-merge checks❌ Failed checks (1 warning)
✅ Passed checks (2 passed)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
/ok to test 9f3f7ed |
Could you extend the title from "update model path" to be more specific? Which model path(s)? |
Overview:
When running the perf job with the specified command, the script fails due to an incorrect repo id format error during the tokenizer creation process. The expected result is for the perf job to finish successfully.
closes: DEP-526
Details:
Where should the reviewer start?
Related Issues: (use one of the action keywords Closes / Fixes / Resolves / Relates to)
Summary by CodeRabbit
Refactor
Chores