Skip to content
@reliquadotai

Reliquary

Decentralized GRPO on Bittensor SN81. Find the signal. Prove it. Train.

Reliquary — find the signal, prove it, train

Decentralized GRPO training on Bittensor's Finney network, Subnet 81.

Live network · Run a miner · Protocol · Research

Reliquary turns independent GPU operators into a verifiable training market. Miners search for prompts at a model's learning frontier, the validator recomputes the evidence, and healthy selected groups can contribute to the next checkpoint.

Find the signal. Prove it. Train

Reliquary protocol loop: miners find frontier prompts, the validator verifies rollout evidence, and healthy selected groups train the next checkpoint

  1. Find — miners compete to locate useful training signal before compute is committed.
  2. Prove — selected candidates pass deterministic verification and validator-authoritative reward checks.
  3. Train — clean, complete windows become eligible for GRPO; archives and checkpoint claims remain inspectable.

Inspect production

Surface What it shows
Live dashboard Current windows, selection, rewards, and training health
Proof explorer Public window records and validator provenance
Network status Availability and data freshness
Canonical source The deployed protocol and its current contract

Live values belong on live surfaces. This profile intentionally does not freeze changing counts, checkpoints, or projections into marketing copy.

Build and operate

Repositories

Production

Repository Role
reliquary Canonical Subnet 81 protocol: mining, verification, selection, training, archives, and checkpoint publication
reliquary-fleet Released, private-by-default operations dashboard for miner fleets

Reference and history

These repositories preserve earlier experiments and reusable primitives. They are not the production Subnet 81 implementation.

Repository Scope
reliquary-ledger Historical proof-carrying inference and validator-mesh testnet
reliquary-forge Historical trainer-quorum and policy-delta exploration
reliquary-protocol Standalone reference for shared protocol primitives

Research with receipts

Reliquary Research separates measured evidence, deployed behavior, and proposed mechanisms. An experiment does not affect production ranking, rewards, or training until the canonical source and deployment state say it does.

Work with us


finney · subnet 81 · inference → evidence → weights

Pinned Loading

  1. reliquary reliquary Public

    Decentralized GRPO on Bittensor SN81: verified frontier rollouts, validator-authoritative training, and public evidence.

    Python 3 5

  2. reliquary-fleet reliquary-fleet Public

    Private-by-default operations dashboard for Reliquary miner fleets

    Python 1

Repositories

Showing 6 of 6 repositories

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Top languages

Loading…

Most used topics

Loading…