Mobilint Model Zoo
SkillDocs & knowledgeWork on the Mobilint Model Zoo package, its legacy compatibility facade, CLI integration, Transformers integrations, MeloTTS, and repository documentation. Use for Model Zoo changes; implement Vision features in the standalone mblt-vision-python repository instead.
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the Mobilint Model Zoo skill
What this skill tells your AI
The instructions your AI receives, as published by mobilint/mblt-model-zoo in .agents/skills/mblt-model-zoo/SKILL.md and read by ahel’s review.
- Read
AGENTS.md, rungit status --short, and inspect the relevant parser, exports, tests, andpyproject.tomlbefore editing. - Keep
mblt_model_zoo.visionand its Vision compilation exports as thin compatibility layers. Compatibility modules must forward tomblt_vision; never copy Vision implementation, model YAMLs, dataset YAMLs, evaluation, or benchmarks into Model Zoo. Limittests/visionto generic opt-in facade smoke tests; keep implementation-specific Vision tests inmblt-vision-python. - Make new Vision CLI behavior in
mblt-vision-pythonfirst. The Model Zoopredict,val, andcompilehandlers must delegate tomblt_vision.cli. - Preserve Model Zoo CLI help and README examples when its CLI integration changes. Pass
board-specific
target_devicethrough to the standalone packages; do not reintroduce legacy product/artifact selection in Model Zoo. Supported boards arearies-rb,regulus-ra,regulus-rb,regulus-ra-usb, andregulus-rb-usb; the shared runtime floor ismblt-npu-python>=0.1.0/mobilint-qb-runtime>=1.4.0. Route every*target_devicesetter (top-level,encoder_,decoder_,base_,draft_,fc_, and the Qwen3-ASR facade) through_rebuild_backend_for_target_deviceso cross-board overrides switch the destination backend class atomically. - Keep TPS output driven by
mblt_model_zoo/cli/tps_table.py. Preserve local conventions inhf_transformersandMeloTTS. Qwen3-VL 8B (regular and Batch16) is unsupported until the shipped MXQ matches the current runtime's expected output ordering. - Start with focused tests. Report unavailable hardware, downloads, and optional extras instead of
weakening validation. For docs, run
git diff --check. - When package ownership, public API, CLI bridges, or runtime dependencies change significantly,
update
AGENTS.md, this canonical skill, the Claude entry point when its workflow changes, and relevant documentation in the same change. - Before a release, build from a clean tree and inspect the wheel. Reject legacy Vision
implementation paths such as
vision/models/,vision/utils/preprocess/,vision/utils/postprocess/,vision/utils/datasets/, andvision/utils/evaluation/.
Signals
- GitHub stars
- 24
- Forks
- 1
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
mblt-model-zoo- Source
- github.com/mobilint/mblt-model-zoo