Albedo
For builders & miners · Bittensor SN97

Take the crown.

Albedo runs on Bittensor subnet 97. If you can train a 4B coding model that beats the king, the throne is yours — permissionlessly. Here's the path.

1

Get the king & the data

Pull the current champion and the published winning duel traces — your raw training material.

python scripts/collect_traces.py --out data/traces.jsonl
2

Train your challenger

Fine-tune a Qwen3-4B on the winning trajectories. Same size class as the king is required and enforced.

python scripts/train_sft.py --base Qwen/Qwen3-4B --data data/traces.jsonl --output ckpt/
3

Sanity-check the format

One clean solution per turn, no injected verdicts. A format fail scores zero from every judge — never skip it.

python scripts/sanity_check.py ckpt/
4

Upload to Hippius

Push weights to decentralized storage, content-addressed by sha256 digest.

python scripts/upload_challenger.py --model ckpt/ --repo you/albedo-qwen3-4b-v1 --hotkey <ss58>
5

Reveal on-chain

Commit your reveal signed by your hotkey. The validator picks it up in ~30s and queues your duel.

v4|you/albedo-qwen3-4b-v1|sha256:… → subtensor.commit(wallet, 97, reveal)
The rules that decide it

Clear the bar. Survive the math.

Same size class

Architecture is locked to the king and checked before any GPU time — you win by training a better 4B model, not a bigger one.

No duplicates

A near-copy of an existing model (weight cosine similarity ≥ 0.95) is rejected. You can't just resubmit the king.

No gaming the judges

Every challenger passes a prompt-injection probe. Try to inject a fake verdict and you're out, fail-closed.

One eval per hotkey

Each hotkey gets one shot per model, and the reigning king can't challenge itself.

Win condition

Beat the king by ≥ 2.0 points on a 0–100 scale, and pass a 95%-confidence bootstrap test.

The margin gate stops within-noise wins. The confidence gate stops lucky ones. Both must pass to crown.