|
Download README.md from maxzameer/phi-4-ElasticBit: direct link, hf CLI and curl.
- Browser
- Download file 1.88 kB
-
https://huggingface.co/maxzameer/phi-4-ElasticBit/resolve/main/README.md
- Command line
-
hf download hf://maxzameer/phi-4-ElasticBit/README.md
-
curl -L -o README.md https://huggingface.co/maxzameer/phi-4-ElasticBit/resolve/main/README.md
1.88 kB
| library_name: mlbricks | |
| tags: | |
| - elasticbit | |
| - quantization | |
| - compression | |
| base_model: microsoft/phi-4 | |
| # phi-4 — MLBricks ElasticBit | |
| Source: `microsoft/phi-4` | |
| Source revision: `2db69c1c3e91a05d2c64a3185acfbaf36f744e25` | |
| MLBricks commit: `f772eb27d2d6b84764e9e90458827dac6980a88a` | |
| ElasticBit threshold: `0.01` | |
| Persistent global dtypes: preserved from the source model as loaded for conversion | |
| ## Conversion result | |
| - Decoder layers: 40 | |
| - Parameter-weighted effective bits: 8.126 | |
| - Linear storage reduction: 49.18% | |
| - Layer artifact bytes: 12.059 GiB | |
| - Exact global component bytes: 1.914 GiB | |
| - Approximate uploaded inference payload: 13.973 GiB | |
| - Reconstructed end-to-end smoke test: PASS | |
| ## Validation | |
| Each newly converted layer is checked on calibration inputs, a separate validation input, | |
| and a local save/load round trip. Before `complete=true`, the converter reconstructs global | |
| payloads from the uploaded safetensors files, streams every uploaded ElasticBit layer through | |
| a real full-model forward, and compares final logits with the pinned FP16 source reference. | |
| ## Layout | |
| - `layers/layer_XXX.elasticbit` | |
| - `components/global_manifest.json` | |
| - `components/global_*.safetensors` | |
| - `reports/layer_XXX.json` | |
| - `reports/reconstruction_smoke.json` | |
| - `calibration/input_ids.safetensors` | |
| - `validation/input_ids.safetensors` | |
| - `elasticbit_manifest.json` | |
| - `progress.json` | |
| Layer artifacts use a minimal ElasticBit root namespace: compressed Linear paths are stored as `block.*`. | |
| The root class itself is not serialized. A loader should create a small `nn.Module` with a `.block` | |
| containing the pinned source-compatible decoder architecture, call `ElasticBit.load(root, artifact)`, | |
| then use `root.block` in the reconstructed model while retaining `root` when controller access is needed. | |
| Review the source model license before redistribution or commercial use. | |