brainstorming
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation).
Explore skills
Development · SKILL.md
twin_uniform_quantization
twin_uniform_quantizationUse this skill to apply PTQ4ViT twin uniform quantization to post-softmax or post-GELU activations with range flags.
Independent GitHub snapshot · Automated classification · Original documentation governs
Skill documentation
GitHubname: twin_uniform_quantization description: Use this skill to apply PTQ4ViT twin uniform quantization to post-softmax or post-GELU activations with range flags.
Twin Uniform Quantization
Use this skill when a recovery or implementation task needs the PTQ4ViT capability described in the module plan. Do not use it to claim full ImageNet accuracy without an actual model, dataset, and evaluation command.
Inputs
- Numeric calibration tensors or an attempt directory, depending on the script.
- Explicit bit width, candidate scales, and runtime/source-boundary constraints.
Outputs
- Deterministic numeric traces suitable for validation.
- JSON-compatible metadata that downstream recovery can inspect.
Workflow
- Read the module contract and pass only bounded local tensors or attempt artifacts.
- Run the script in
scripts/or import its pure functions. - Validate outputs with the tests in
tests/. - Record commands and artifacts in the Distiller attempt when used for recovery.
Validation
Run python validate_skill_tree.py <skill_dir> --run-tests from the Distiller module-to-skill validator.
Limitations
This skill preserves the PTQ4ViT mechanism but does not bundle pretrained models, ImageNet, or the original repository. Recovery must not read the original repository.