tarekziade HF Staff
Consolidate MIC usage, slim weights and reviewed framework expectations
f01c184 verified |
Download docs/source-cards/fixture.md from huggingface-mic/internvl-mic: direct link, hf CLI and curl.
- Browser
- Download file 2.01 kB
-
https://huggingface.co/huggingface-mic/internvl-mic/resolve/main/docs/source-cards/fixture.md
- Command line
-
hf download hf://huggingface-mic/internvl-mic/docs/source-cards/fixture.md
-
curl -L -o fixture.md https://huggingface.co/huggingface-mic/internvl-mic/resolve/main/docs/source-cards/fixture.md
2.01 kB
| tags: | |
| - mic | |
| - test-artifact | |
| base_model: OpenGVLab/InternVL3-1B-hf | |
| # Slim fixture: mic-internvl-slim | |
| A 10.0M-parameter fixture for the [internvl MIC](https://huggingface.co/hf-internal-testing/internvl-integration), covering [`OpenGVLab/InternVL3-1B-hf`](https://huggingface.co/OpenGVLab/InternVL3-1B-hf). It is a test artifact, not a usable model, tagged `test-artifact` to keep it out of candidate-model search. | |
| - **Fixture key `13790668e138`.** It covers every checkpoint whose processor files are byte-identical and whose config matches after shrinking. | |
| - **Same architecture, smaller config:** `InternVLForConditionalGeneration`, shrunk by the generic rule in [`sweep.py`](https://github.com/huggingface/model-integration-contracts/blob/main/experiments/sweep.py) (vision num_hidden_layers 2, text num_hidden_layers 2). | |
| - **Processor files copied byte for byte** from `OpenGVLab/InternVL3-1B-hf`: `added_tokens.json`, `chat_template.jinja`, `generation_config.json`, `merges.txt`, `preprocessor_config.json`, `processor_config.json`, `special_tokens_map.json`, `tokenizer.json`, `tokenizer_config.json`, `vocab.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:roll_batch`, 0.00781), 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 `OpenGVLab/InternVL3-1B-hf` loads in by default. | |
| - **Finite in float32, bfloat16, and float16** (forward, loss, gradients). | |
| Built by [`build_fixtures.py`](https://github.com/huggingface/model-integration-contracts/blob/main/example/build_fixtures.py); [`build.json`](build.json) records the pinned sources, gate results, and file hashes. The source repository commits only `README.md` and `build.json`; rebuild the other files with `python example/build_fixtures.py --fixture mic-internvl-slim`. | |