Armiger v3.2.1 (Model Bundle v3.0.0 / v3.0-gold-r5) — 15.7 MB INT8 ONNX CPU Classifier

Release: v3.2.1 · Model Version: 3.0.0 (v3.0-gold-r5) · Artifact: 15.7 MB (armiger.int8.onnx / armiger.onnx, per-channel asymmetric INT8 with FP32 embeddings) · CPU latency: 2.44 ms/item (326 items/s batch-64, M4 Pro CPU) · License: Apache-2.0

Armiger (NorviTech/armiger) is the CPU-only INT8 edition of the 9-head byte-level RoPE Transformer (8,295,882 parameters). It needs only numpy + onnxruntime and keeps 99.90% parity with the 32.5 MB FP32 model. Library and container release 3.2.1 uses model bundle 3.0.0. For FP32 weights and all 6 plugins (SwarmSurvivalNet, SwarmPriors, ZeroCueCatalog, AudioLanguageGuard, CalibrationAndDHT, ArmigerDHTDBSync), use NorviTech/armiger-ultra.

Neural Outputs & Benchmark Summary

• 9 outputs, one CPU pass: category (11-class), adult, junk/malware, anime, english_subs, spoken lang, title_language, owner_scope, and per-byte span_bio title/year/episode tags via a 7-tag Viterbi mask (0 illegal transitions).
• INT8 accuracy (all 3 suites):
  • Suite B LOTO N=1,025: 96.85% 6-dimension composite (95% CI [96.33%, 97.36%] with plugins) vs. Gemini Flash (94.56%), OpenAI GPT Fast Tier (93.49%, 5-dim; Junk N/A (Unprompted)), Claude Haiku 4.5 (92.88%).
  • W5A-Test N=703 (Rule-3 Gold): 97.01% 11-class accuracy (95% Wilson CI [95.47%, 98.04%]); 96.87% 6-core-head exact match.
  • R5-Test N=996 (7-key zero-leakage): 91.16% INT8 9-class accuracy (FP32 91.27%; 99.90% parity), 99.22% Title Language (n=511), 99.09% English Subtitles (n=110), 98.90% Owner Scope (n=996), 90.32% BIO Balanced Byte Accuracy (n=882), 85.84% all-heads exact match (n=996).

Quickstart (Standalone CPU ONNX Runtime)

Option A — Install the Python package (v3.2.1) with verified model download

python -m pip install "armiger @ git+https://github.com/spencernorton/armiger.git@v3.2.1"
python -m armiger download --directory ./models-cpu --variant cpu

from armiger import ArmigerStandaloneONNX

model = ArmigerStandaloneONNX(
    onnx_path="./models-cpu/armiger.int8.onnx",
    vocab_path="./models-cpu/vocab.json",
    calibration_path="./models-cpu/calibration.json",
)
res = model.predict({
    "name": "Tears.of.Steel.2012.1080p.BluRay.x264-OPEN",
    "size": 8_500_000_000,
    "files": [{"path": "Tears.of.Steel.2012.mkv", "size": 8_500_000_000}],
})
print(res["heads"]["category"], res["matching_identity"], res["mondrian_gates"]["passed_all"])

Option B — Run directly from a checkout of this Hugging Face repository

from armiger_inference import ArmigerStandaloneONNX

model = ArmigerStandaloneONNX()  # auto-loads armiger.onnx, vocab.json, calibration.json
res = model.predict({
    "name": "Tears.of.Steel.2012.1080p.BluRay.x264-OPEN",
    "size": 8_500_000_000,
    "files": [{"path": "Tears.of.Steel.2012.mkv", "size": 8_500_000_000}],
})
print(res["heads"]["category"], res["matching_identity"], res["mondrian_gates"]["passed_all"])

Ready-Made Docker Setups & Integrations (v3.2.1)

• Full FP32 + 6-plugin suite: NorviTech/armiger-ultra
• Core package, containers & evaluation harness (v3.2.1): spencernorton/armiger · License: Apache-2.0
  • Bitmagnet + Armiger Ultra: Two-line Docker Compose setup (include: [oci://ghcr.io/spencernorton/armiger-bitmagnet-stack:3.2.1]) · Environment-Variable Reference
  • Rats Search + Armiger Ultra: Two-line Docker Compose setup (include: [oci://ghcr.io/spencernorton/armiger-rats-search-stack:3.2.1])
  • Standalone Armiger Ultra HTTP Container: Prebuilt multi-arch image ghcr.io/spencernorton/armiger:3.2.1 with /v1/classify and /healthz
  • Python API & Component Reference · Evaluation & Limitations
• Standalone sidecars & connectors (v1.1.1): spencernorton/Armiger-Connectors
  • Stock Bitmagnet (bitmagnet-io/bitmagnet): bitmagnet/bitmagnet_connector.py — polls untagged torrents via GraphQL, runs vectorized Armiger inference, prunes .exe/.scr/.lnk malware and honeypot traps, writes armiger-* tags.
  • Stock Rats Search (librats/rats-search): rats-search/rats_search_connector.py — drop-in REST/SQLite sidecar classifier and safety filter.
  • DH-Waypoint processorapi/v1 plugin (spencernorton/DH-Waypoint): dh-waypoint/ — admission (/v1/admit), batch (/v1/classify), 4-tier feedback (/v1/feedback).
  • Torznab pre-grab proxy (Prowlarr/Sonarr/Radarr/Lidarr/Readarr): arr-stack/armiger_torznab_proxy.py — filters malware lures, dead swarms, and unrequested foreign-audio releases before grab.
  • Post-import *Arr/qBittorrent webhook: arr-stack/armiger_arr_webhook_receiver.py — ffprobe ground truth for local conformal calibration and opt-in anonymous BEP-44/46 updates.