privacy-filter-mic

Slim model weights, executable usage and framework expectations in one repository.

• Contract manifest
• Transformers usage
• Transformers expectations
• Fixture provenance
• How the fixture was shrunk

Contract

Privacy Filter token classification

Runnable usage and the framework expectations directory are linked above.

Slim model

Slim fixture: privacy-filter-mic

A 13.0M-parameter fixture for the privacy-filter MIC, covering openai/privacy-filter. It is a test artifact, not a usable model, tagged test-artifact to keep it out of candidate-model search.

• Fixture key 6e7bf1f74741. It covers every checkpoint whose processor files are byte-identical and whose config matches after shrinking.
• Same architecture, smaller config: OpenAIPrivacyFilterForTokenClassification, shrunk by the generic rule in sweep.py (num_hidden_layers 2).
• Processor files copied byte for byte from openai/privacy-filter: model.sig, tokenizer.json, tokenizer_config.json, viterbi_calibration.json.
• Random weights (seed 17). They passed the input-sensitivity gate: every perturbation of the contract's inputs moved the logits by at least 0.001 (weakest: attention_mask:all_ones, 0.389), so no training was needed.
• Same tensor names as the real checkpoint. The real checkpoint has every parameter, and so does the fixture.
• Saved in bfloat16, the dtype openai/privacy-filter loads in by default.
• Finite in float32, bfloat16, and float16 (forward, loss, gradients).

Built by build_fixtures.py; build.json records the pinned sources, gate results, and file hashes. This repository includes the slim weights, usage and framework expectations; rebuild the other files with python example/build_fixtures.py --fixture privacy-filter-mic.