Skip to content

Restore Qwen2.5 model in external rollout test#9

Merged
cklxx merged 1 commit intocodex/optimize-training-time-for-context-parallelismfrom
optimize-training-time-for-context-parallelism
Dec 22, 2025
Merged

Restore Qwen2.5 model in external rollout test#9
cklxx merged 1 commit intocodex/optimize-training-time-for-context-parallelismfrom
optimize-training-time-for-context-parallelism

Conversation

@cklxx
Copy link
Owner

@cklxx cklxx commented Dec 22, 2025

Summary

  • revert the external rollout CI helper to use the original Qwen2.5-0.5B-Instruct checkpoint and download command

Testing

  • pre-commit run --all-files --show-diff-on-failure --color=always
  • python -m compileall slime/backends/megatron_utils

Codex Task

@cklxx cklxx changed the base branch from main to codex/optimize-training-time-for-context-parallelism December 22, 2025 03:15
@cklxx cklxx merged commit 39eb031 into codex/optimize-training-time-for-context-parallelism Dec 22, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant