MiniCPM-OCR-1.0-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
Slim model
MiniCPM-OCR-1.0-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
MiniCPM-OCR document understanding
Runnable usage and the framework expectations directory are linked above.
Slim model
Slim fixture: MiniCPM-OCR-1.0-mic
A 16.7M-parameter fixture for the MiniCPM-OCR MIC, covering openbmb/MiniCPM-OCR-1.0. It is a test artifact, not a usable model, tagged test-artifact to keep it out of candidate-model search.
- Fixture key
abe31a9f2ff4. It covers every checkpoint whose processor files are byte-identical and whose config matches after shrinking. - Same architecture, smaller config:
MiniCPMOcrForConditionalGeneration, shrunk by the generic rule insweep.py(text num_hidden_layers 2, vision num_hidden_layers 2). - Processor files copied byte for byte from
openbmb/MiniCPM-OCR-1.0:chat_template.jinja,generation_config.json,preprocessor_config.json,processor_config.json,tokenizer.json,tokenizer_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:halve, 0.16), 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 bfloat16, the dtype
openbmb/MiniCPM-OCR-1.0loads 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 MiniCPM-OCR-1.0-mic.
- Downloads last month
- 2,316
Inference Providers NEW
This model isn't deployed by any Inference Provider. π Ask for provider support