spencernorton commited on
Commit
87239ab
·
verified ·
1 Parent(s): 2f6dc6a

Sync canonical benchmark metrics with CHARTS_MANIFEST.json

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -17,8 +17,8 @@ pinned: true
17
 
18
  | Model Repository | Role | Footprint | Hardware-Attributed Speed | 6-Dim Composite | 11-Class Category (Unmutated Keys) | Movie vs. TV (`oct15` `N=1,296`) | Audio Language (`oct15` `N=545`) | Swarm Liveliness (AUROC) |
19
  | :--- | :--- | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
20
- | **[`NorviTech/armiger-ultra`](https://huggingface.co/NorviTech/armiger-ultra)** | **Unified Flagship Suite** (`Armiger` + `Ultra FP32` + `armiger_inference.py` + **All 6 Plugins Rolled In**) | `32.3 MB` model (`+26.0 MB` `BLAKE2b-64` catalog) | **`0.21 ms` RTX GPU / `0.29 ms` M4 Pro MPS** (batch-64) | **`97.55%`** | **`95.49%`** `oct15` / **`95.12%`** `beyond` / **`98.47%`** `mlang` (`95.42%` 5-split `N=10,262`) | **`97.15%`** (`96.54%` `beyond`) | **`97.80%`** | **`96.83%`** Whse / **`92.42%`** Pub (`100%` trap recall) |
21
- | **[`NorviTech/armiger`](https://huggingface.co/NorviTech/armiger)** | **Universal Fast CPU Classifier** (`ONNX INT8` + `armiger_inference.py`) | **`8.3 MB`** | **`2.44 ms` single-item / `3.07 ms` batch-64** (M4 Pro CPU) | **`96.50%`** | **`95.06%`** `oct15` / **`92.88%`** `beyond` / **`97.37%`** `mlang` (`93.95%` 5-split `N=10,262`) | **`96.60%`** | **`96.88%`** | **`86.64%`** Priors (`92.42%` w/ Adapter) |
22
 
23
  ## 2. Armiger Modular Plugins (6 Standalone Repos & Rolled Into `Armiger Ultra`)
24
 
 
17
 
18
  | Model Repository | Role | Footprint | Hardware-Attributed Speed | 6-Dim Composite | 11-Class Category (Unmutated Keys) | Movie vs. TV (`oct15` `N=1,296`) | Audio Language (`oct15` `N=545`) | Swarm Liveliness (AUROC) |
19
  | :--- | :--- | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
20
+ | **[`NorviTech/armiger-ultra`](https://huggingface.co/NorviTech/armiger-ultra)** | **Unified Flagship Suite** (`Armiger` + `Ultra FP32` + `armiger_inference.py` + **All 6 Plugins Rolled In**) | `32.3 MB` model (`+26.0 MB` `BLAKE2b-64` catalog) | **`0.21 ms` RTX GPU / `0.29 ms` M4 Pro MPS** (batch-64) | **`97.60%`** | **`95.49%`** `oct15` / **`95.12%`** `beyond` / **`98.47%`** `mlang` (`95.42%` 5-split `N=10,262`) | **`97.30%`** (`96.54%` `beyond`) | **`97.80%`** | **`96.83%`** Whse / **`92.42%`** Pub (`100%` trap recall) |
21
+ | **[`NorviTech/armiger`](https://huggingface.co/NorviTech/armiger)** | **Universal Fast CPU Classifier** (`ONNX INT8` + `armiger_inference.py`) | **`8.3 MB`** | **`2.44 ms` single-item / `3.07 ms` batch-64** (M4 Pro CPU) | **`96.85%`** (`96.50%` Raw) | **`95.06%`** `oct15` / **`92.88%`** `beyond` / **`97.37%`** `mlang` (`93.95%` 5-split `N=10,262`) | **`96.60%`** | **`96.88%`** | **`86.64%`** Priors (`92.42%` w/ Adapter) |
22
 
23
  ## 2. Armiger Modular Plugins (6 Standalone Repos & Rolled Into `Armiger Ultra`)
24