tarekziade's picture
tarekziade HF Staff
Publish MIC usage, slim fixture and reviewed Transformers expectations
e65f738 verified
|
Raw History Blame Contribute Delete
2.9 kB
---
tags:
- mic
- test-artifact
base_model: facebook/convnext-tiny-224
---
# convnext-tiny-224-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/convnext-tiny-224-mic.html)
## Contract
### ConvNeXT image classification
Runnable usage and the framework expectations directory are linked above.
## Slim model
### convnext-tiny-224-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/convnext-tiny-224-mic.html)
## Contract
### ConvNeXT image classification
Runnable usage and the framework expectations directory are linked above.
## Slim model
### Slim fixture: convnext-tiny-224-mic
A 0.4M-parameter fixture for the [ConvNext MIC](https://huggingface.co/huggingface-mic/convnext-tiny-224-mic), covering [`facebook/convnext-tiny-224`](https://huggingface.co/facebook/convnext-tiny-224). It is a test artifact, not a usable model, tagged `test-artifact` to keep it out of candidate-model search.
- **Fixture key `6bd814728257`.** It covers every checkpoint whose processor files are byte-identical and whose config matches after shrinking.
- **Same architecture, smaller config:** `ConvNextForImageClassification`, shrunk by the generic rule in [`sweep.py`](https://github.com/huggingface/transformers-mic/blob/main/experiments/sweep.py) ().
- **Processor files copied byte for byte** from `facebook/convnext-tiny-224`: `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:reverse`, 0.0726), 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/convnext-tiny-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 convnext-tiny-224-mic`.