Add e2e sanity prompts to tiny model finetune dataset - #3047
Conversation
Ensures tiny models learn the correct answers for the e2e vLLM sanity checks (capital of France, theory of relativity, rock paper scissors). Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
|
Important Review skippedAuto reviews are disabled on this repository. Please check the settings in the CodeRabbit UI or the ⚙️ Run configurationConfiguration used: Path: .coderabbit.yaml Review profile: CHILL Plan: Pro Plus Run ID: You can disable this status message by setting the Use the checkbox below for a quick retry:
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 |
There was a problem hiding this comment.
Code Review
This pull request updates the fine-tuning script .claude/skills/create-tiny-model/scripts/finetune.py by adding three new sanity check answers to the dataset list, aligning with the end-to-end sanity prompts in tests/e2e/test_vllm.py. There are no review comments, and I have no feedback to provide.
Merge Protections🟢 Merge protection satisfied — ready to merge. Show 1 satisfied protection🟢 Require one maintainer reviewAll PRs must have at least one approving review from a maintainer before merging.
|
|
👋 Hi! Thank you for contributing to llm-compressor. Please add the ready label when the PR is ready for review. Note: This is required to complete the testing suite, please only add the label once the PR is code complete and local testing has been performed. |
Summary
create-tiny-modelskilltests/e2e/test_vllm.pySANITY_PROMPTS🤖 Generated with Claude Code