electra-small-discriminator-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

ELECTRA discriminator token detection

Runnable usage and the framework expectations directory are linked above.

Slim model

Slim fixture: electra-small-discriminator-mic

A 13.5M-parameter fixture for the ElectraForPreTraining MIC, covering google/electra-small-discriminator. It is a test artifact, not a usable model, tagged test-artifact to keep it out of candidate-model search.

• Fixture key 085816f0c7ae. It covers every checkpoint whose processor files are byte-identical and whose config matches after shrinking.
• The checkpoint's own config, not shrunk: ElectraForPreTraining at 13.5M parameters is at or under the 20M below which a source is kept whole.
• Processor files copied byte for byte from google/electra-small-discriminator: tokenizer.json, tokenizer_config.json, vocab.txt.
• The checkpoint's own trained weights, unchanged: at 13.5M parameters it is no bigger than a slim fixture. They passed the input-sensitivity gate (weakest: token_type_ids:all_ones, 0.0188).
• Same tensor names as the real checkpoint. The real checkpoint has every parameter, and so does the fixture.
• Saved in float32, the dtype google/electra-small-discriminator 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 electra-small-discriminator-mic.