
Skill
mcore-migrate-gpt-to-hybrid
migrate Megatron-LM models to HybridModel
Description
Migration guide for moving Megatron Core GPTModel checkpoints, model providers, training commands, and layer mappings to HybridModel.
SKILL.md
GPTModel to HybridModel Migration
Answer-First Migration Guidance
- The canonical source is
docs/user-guide/hybrid-model-migration.md. - Read the canonical document completely before answering, planning, reviewing, editing, converting, or training.
- Keep migration behavior, commands, mappings, prerequisites, limitations, and validation in the canonical document only. Do not duplicate them in this skill.
Workflow
- Pull the task artifact first: checkpoint metadata, model provider or config, training command, conversion log, diff, or failure output.
- Read the canonical migration document completely.
- Follow only the relevant document sections. Do not invent an unsupported migration path or silently change the target architecture.
- Validate the result proportionately, invoking the relevant repository build and testing skills when applicable.
- Report the outcome and link the canonical document for human readers.
Documentation Drift
If the implementation and migration guide disagree:
- Report the discrepancy before continuing.
- If the task authorizes a correction, update the canonical document first.
- Do not add a competing migration rule to this skill.
More skills from the Megatron-LM repository
View all 13 skillsmcore-build-and-dependency
manage Megatron-LM development environments
Jul 27ContainersDeploymentPythonmcore-bump-base-image
update NVIDIA PyTorch base images
Jul 14CI/CDDeploymentmcore-cicd
manage CI/CD pipelines for Megatron-LM
Jul 27CI/CDDeploymentGitHubmcore-create-issue
investigate CI failures and create issues
Jul 14DebuggingGitHubTriagemcore-linting-and-formatting
lint and format Megatron-LM code
Jul 14Best PracticesCode Analysismcore-onboard-gb200-1node-tests
onboard functional tests for GB200
Jul 14QATesting
More from NVIDIA
View publishernemoclaw-user-guide
retrieve NemoClaw documentation and configuration
NemoClaw
Jul 20DocumentationMCPSearchmcore-run-on-slurm
launch distributed training jobs on SLURM
Megatron-LM
Jul 14DeploymentInfrastructuremcore-split-pr
split pull requests to reduce review load
Megatron-LM
Jul 14Code ReviewGitHubPull Requestsmcore-testing
run and manage Megatron-LM tests
Megatron-LM
Jul 14QATestingnightly-sync
manage nightly main-to-dev sync workflows
Megatron-LM
Jul 14AutomationCI/CD