Introduces the modular tiny model architecture documentation area and links its component topics.
Architecture guide: this topic defines a modular tiny-model planning contract. It does not claim that model artifacts exist, are compatible, or execute on this WordPress site.
Purpose
This section treats modular intelligence as a system of bounded capability roles rather than a pile of arbitrary models. The installed library is larger than the active set, and every activation is mediated by compatibility, resource, evidence, and task constraints.
Project boundary
MiRust documents the architecture and supplies a non-executing composer. GGUF owns implementation, runtime behavior, model artifacts, and measured evidence.
Primary invariants
- No role is activated without a declared input/output contract.
- No adapter is applied to an unverified base revision or layer map.
- No compatibility statement is inferred from a filename or model family alone.
- No resource estimate is promoted to a benchmark.
- No-op remains an explicit, valid action.
Scope
This starter page defines the questions, boundaries, evidence, and failure modes that should be recorded before a capability is presented as supported.
Engineering considerations
- Identify the source, version, target environment, and owner.
- Separate observed values from estimates and externally reported values.
- Record trade-offs, unsupported cases, and fallback behavior.
- Link performance statements to a compatible benchmark methodology.
Verification questions
- What exact artifact, revision, backend, and environment were reviewed?
- Which assumptions could change the result?
- Which data should be retained so another engineer can reproduce the conclusion?