Slim fixture: mic-detr-slim
A 23.8M-parameter fixture for the detr MIC, covering facebook/detr-resnet-50. It is a test artifact, not a usable model, tagged test-artifact to keep it out of candidate-model search.
- Fixture key
8a01ecc30615. It covers every checkpoint whose processor files are byte-identical and whose config matches after shrinking. - Same architecture, smaller config:
DetrForObjectDetection, shrunk by the generic rule insweep.py(encoder_layers 2, decoder_layers 2). - Processor files copied byte for byte from
facebook/detr-resnet-50:preprocessor_config.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:
pixel_values:swap_channels, 0.0992), 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 float32, the dtype
facebook/detr-resnet-50loads 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. The source repository commits only README.md and build.json; rebuild the other files with python example/build_fixtures.py --fixture mic-detr-slim.
- Downloads last month
- 22
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support