Florence-2-base-mic

Slim model weights, executable usage and framework expectations in one repository.

• Contract manifest
• Transformers usage
• Transformers expectations
• Fixture provenance

Contract

Florence-2 image captioning

Runnable usage and the framework expectations directory are linked above.

Slim model

Slim fixture: Florence-2-base-mic

A 6.4M-parameter fixture for the Florence-2 MIC, covering florence-community/Florence-2-base. It is a test artifact, not a usable model, tagged test-artifact to keep it out of candidate-model search.

• Fixture key 0035fa41a356. It covers every checkpoint whose processor files are byte-identical and whose config matches after shrinking.
• Same architecture, smaller config: Florence2ForConditionalGeneration, shrunk by the generic rule in sweep.py (text encoder_layers 1, text decoder_layers 1).
• Processor files copied byte for byte from florence-community/Florence-2-base: added_tokens.json, generation_config.json, merges.txt, preprocessor_config.json, processor_config.json, special_tokens_map.json, tokenizer.json, tokenizer_config.json, vocab.json.
• Overfit to the contract's training step (50 steps). Random weights failed the input-sensitivity gate: input_ids:reverse moved the logits by only 0.00049 (threshold 0.001).
• Same tensor names as the real checkpoint. The real checkpoint has every parameter, and so does the fixture.
• Saved in float16, the dtype florence-community/Florence-2-base 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 Florence-2-base-mic.