Model Optimization

This is a Hermes-native model-optimization workflow skill.

Why This Exists

model-optimization exists so a new model release triggers one repeatable, evidence-ordered process instead of ad-hoc edits: recognition proves what the router sees, official-first research separates contracts from folklore, trait-to-counter keeps calibrations concrete, and the measurement close keeps them honest.

Do Not Use When

• The user wants their own machine's model routing configured or providers connected; use omh-model-setup.
• The goal is measurable performance of an application or system, not model handling; use ulw-perf.
• The user wants benchmark-superiority or provider-readiness claims without measurements; decline the claim and offer the measurement plan from this skill's checklist.
• Making a model's weights smaller or cheaper by quantization, pruning or distillation into a student; use omh-model-compression.
• Serving a model behind an endpoint, or benchmarking that endpoint; use omh-inference-serving.
• Training a model on your own data with SFT, DPO or a LoRA adapter; use omh-model-finetuning.

Examples