resnet-18-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

ResNet image classification

Runnable usage and the framework expectations directory are linked above.

Slim model

Slim fixture: resnet-18-mic

A 11.7M-parameter fixture for the ResNet MIC, covering microsoft/resnet-18. It is a test artifact, not a usable model, tagged test-artifact to keep it out of candidate-model search.

• Fixture key 220cf2910e40. It covers every checkpoint whose processor files are byte-identical and whose config matches after shrinking.
• The checkpoint's own config, not shrunk: ResNetForImageClassification at 11.7M parameters is at or under the 20M below which a source is kept whole.
• Processor files copied byte for byte from microsoft/resnet-18: preprocessor_config.json.
• The checkpoint's own trained weights, unchanged: at 11.7M parameters it is no bigger than a slim fixture. They passed the input-sensitivity gate (weakest: pixel_values:reverse, 0.0151).
• Same tensor names as the real checkpoint. The real checkpoint has every parameter, and so does the fixture.
• Saved in float32, the dtype microsoft/resnet-18 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 resnet-18-mic.