NorviTech/armiger-ultra

Armiger Ultra v3.3.0

Release: v3.3.0 · Weights: 33.3 MB FP32 ONNX + 17.6 MB INT8 ONNX · Parameters: 8.05M · License: Apache-2.0

Armiger Ultra is an 8.05M-parameter multi-head byte-level RoPE Transformer (0.21 ms/item batched GPU) and 6-plugin pipeline for BitTorrent and DHT metadata classification, canonical title/year extraction, audio/subtitle verification, malware filtering, and swarm liveliness scoring.

Quickstart

Pre-Built Docker Container & Compose Stacks (v3.3.0)

Run the pre-built armiger-ultra:

docker run -d --name armiger-ultra -p 8080:8000 \
  -e ARMIGER_DHT_AUTO_UPDATE=true \
  ghcr.io/spencernorton/armiger-ultra:3.3.0

Or include a ready-made stack in compose.yaml (docker compose up -d):

include:
  - oci://ghcr.io/spencernorton/armiger-bitmagnet-stack:3.3.0
  # or: oci://ghcr.io/spencernorton/armiger-rats-search-stack:3.3.0

Python SDK

python -m pip install "armiger[ultra] @ git+https://github.com/spencernorton/armiger.git@v3.3.0"
python -m armiger download --directory ./models

from armiger import ArmigerUltraPipeline

pipeline = ArmigerUltraPipeline.from_directory("./models", variant="ultra")
res = pipeline.classify({
    "name": "Tears.of.Steel.2012.2160p.UHD.BluRay.REMUX.HEVC.TrueHD.7.1.Atmos-OPEN",
    "size": 68_400_000_000,
    "files": [{"path": "Tears.of.Steel.2012.mkv", "size": 68_400_000_000}],
    "swarm": {"tracker_known": True, "tracker_seeders": 142, "tracker_leechers": 19, "tracker_completed": 810},
})
print(res["category"], res["mondrian_gates"]["passed_all"], res["swarm_viability"]["viability_tier"])

Links & Ecosystem

• Core Package, Containers & Evaluation (v3.3.0): spencernorton/armiger (Quickstart · DHT Auto-Update · Evaluation)
• CPU INT8 Model (17.6 MB): NorviTech/armiger
• Indexer Sidecars (Bitmagnet, Rats Search, *Arr Torznab): spencernorton/Armiger-Connectors
• DH-Waypoint DHT Crawler & Indexer: spencernorton/DH-Waypoint