|
Download README.md from huggingface-mic/mpnet-base-mic: direct link, hf CLI and curl.
- Browser
- Download file 2.28 kB
-
https://huggingface.co/huggingface-mic/mpnet-base-mic/resolve/main/README.md
- Command line
-
hf download hf://huggingface-mic/mpnet-base-mic/README.md
-
curl -L -o README.md https://huggingface.co/huggingface-mic/mpnet-base-mic/resolve/main/README.md
2.28 kB
| tags: | |
| - mic | |
| - test-artifact | |
| base_model: microsoft/mpnet-base | |
| # mpnet-base-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/mpnet-base-mic.html) | |
| ## Contract | |
| ### MPNet fill-mask | |
| Runnable usage and the framework expectations directory are linked above. | |
| ## Slim model | |
| ### Slim fixture: mpnet-base-mic | |
| A 2.1M-parameter fixture for the [MPNet MIC](https://huggingface.co/huggingface-mic/mpnet-base-mic), covering [`microsoft/mpnet-base`](https://huggingface.co/microsoft/mpnet-base). It is a test artifact, not a usable model, tagged `test-artifact` to keep it out of candidate-model search. | |
| - **Fixture key `f651cf653329`.** It covers every checkpoint whose processor files are byte-identical and whose config matches after shrinking. | |
| - **Same architecture, smaller config:** `MPNetForMaskedLM`, 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 `microsoft/mpnet-base`: `tokenizer.json`, `tokenizer_config.json`, `vocab.txt`. | |
| - **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`, 0.00388), 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 `microsoft/mpnet-base` 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 mpnet-base-mic`. | |