Reliquary | Bittensor SN81 τ
@reliquary_ai
A market for the learning frontier. Decentralized GRPO training on Bittensor Subnet 81| every rollout cryptographically verified before it trains the checkpoint
17 Following 377 Followers
Introducing Reliquary-4B.
A 4B math & code model trained with reinforcement learning. Anyone could join the network and contribute rollouts.
Independent miners chose the prompts and generated the rollouts. The protocol verified them and trained the model.
Here’s the model and the research behind it.
Show more
Reliquary is live on Bittensor Subnet 81.
A market where miners are paid to find the prompts a model is about to learn from — and every rollout is cryptographically verified before it trains the next checkpoint.
Show more
