Mcore Migrate GPT To Hybrid Agent Skill
Migration guide for moving Megatron Core GPTModel checkpoints, model providers, training commands, and layer mappings to HybridModel.
Install
one command, takes just this skill from the repositorynpx skills add https://github.com/NVIDIA/Megatron-LM --skill mcore-migrate-gpt-to-hybridThe instruction itself
4 sections, as written by the authorGPTModel 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.
Other skills for the same job
different authors, same section of the catalogue
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Access NCBI GEO for gene expression/genomics data. Search/download microarray and RNA-seq datasets (GSE, GSM, GPL), retrieve SOFT/Matrix files, for transcriptomics and expression analysis.
Bayesian modeling with PyMC. Build hierarchical models, MCMC (NUTS), variational inference, LOO/WAIC comparison, posterior checks, for probabilistic programming and inference.
Multi-objective optimization framework. NSGA-II, NSGA-III, MOEA/D, Pareto fronts, constraint handling, benchmarks (ZDT, DTLZ), for engineering design and optimization problems.
Statistical modeling toolkit. OLS, GLM, logistic, ARIMA, time series, hypothesis tests, diagnostics, AIC/BIC, for rigorous statistical inference and econometric analysis.
Add unsigned integer (uint) type support to PyTorch operators by updating AT_DISPATCH macros. Use when adding support for uint16, uint32, uint64 types to operators, kernels, or when user mentions enabling unsigned types, barebones unsigned types, or uint support.
Convert PyTorch AT_DISPATCH macros to AT_DISPATCH_V2 format in ATen C++ code. Use when porting AT_DISPATCH_ALL_TYPES_AND*, AT_DISPATCH_FLOATING_TYPES*, or other dispatch macros to the new v2 API. For ATen kernel files, CUDA kernels, and native operator implementations.
Write docstrings for PyTorch functions and methods following PyTorch conventions. Use when writing or updating docstrings in PyTorch code.
How to use it
Take nvidia/mcore-migrate-gpt-to-hybrid from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.