| --- |
| tags: |
| - mic |
| - test-artifact |
| base_model: google/vit-base-patch16-224 |
| --- |
| |
| # vit-mic |
|
|
| Slim model weights, executable usage and framework expectations in one repository. |
|
|
| - [Contract manifest](integration.json) |
| - [Transformers usage](integrations/transformers/usage.md) |
| - [Transformers expectations](integrations/transformers/expectations) |
| - [Fixture provenance](build.json) |
| - [How the fixture was shrunk](https://huggingface-mic-mic-coverage.static.hf.space/shrink/vit-mic.html) |
|
|
| ## Contract |
|
|
| ### vit model integration contract |
|
|
| Public Transformers usage validated on a slim fixture on an NVIDIA A10G, |
| with default, eager and bfloat16 variants and fresh-process baseline recording. |
| This prototype declares fixture-only targets; full checkpoint coverage is separate. |
|
|
| [Regeneration evidence](https://github.com/huggingface/transformers-mic/actions/runs/38252430459). |
|
|
| ## Slim model |
|
|
| ### Slim fixture: mic-vit-slim |
|
|
| A 0.2M-parameter fixture for the [vit MIC](https://huggingface.co/huggingface-mic/vit-mic), covering [`google/vit-base-patch16-224`](https://huggingface.co/google/vit-base-patch16-224). It is a test artifact, not a usable model, tagged `test-artifact` to keep it out of candidate-model search. |
|
|
| - **Fixture key `3fc8366aafe8`.** It covers every checkpoint whose processor files are byte-identical and whose config matches after shrinking. |
| - **Same architecture, smaller config:** `ViTForImageClassification`, shrunk by the generic rule in [`sweep.py`](https://github.com/huggingface/transformers-mic/blob/main/experiments/sweep.py) (num_hidden_layers 2). |
| - **Processor files copied byte for byte** from `google/vit-base-patch16-224`: `preprocessor_config.json`. |
| - **Overfit to the contract's training step** (300 steps). Random weights failed the input-sensitivity gate: `pixel_values:reverse` moved the logits by only 5.9e-05 (threshold 0.001). |
| - **Same tensor names as the real checkpoint.** The real checkpoint has every parameter, and so does the fixture. |
| - **Saved in float32**, the dtype `google/vit-base-patch16-224` loads in by default. |
| - **Finite in float32, bfloat16, and float16** (forward, loss, gradients). |
|
|
| Built by [`build_fixtures.py`](https://github.com/huggingface/transformers-mic/blob/main/example/build_fixtures.py); [`build.json`](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 mic-vit-slim`. |
|
|
