Reliquary | Bittensor SN81 τ
@reliquary_ai
Scaling post-training with @bittensor
20 Following 546 Followers
We’ve released Teutonic-I-Reliquary, a 9B model post-trained entirely on Bittensor using untrusted GPUs, from RTX 3090s to B200s.
It beats Qwen3.5-9B on SWE-bench Verified, scoring 43.6% vs 35.1%.
Show more
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
