Introducing RL Swarm 72B

Fully decentralised RL training of 72B-parameter models for anyone to join, with no whitelists.

Train your base model on a new advanced math dataset (DAPO-Math-17k) collaboratively alongside thousands of others using our novel multi-stage system.

The network for machine intelligence


https://gensyn.ai

Update your node now and choose a swarm:

Consumer (>8GB VRAM): now even lower-powered devices can run the swarm (GSM8K)

More powerful: bring a bigger model, up to 72B params, to tackle a harder dataset (DAPO-Math-17k)

Update your node now and choose a swarm:

Consumer (>8GB VRAM): now even lower-powered devices can run the swarm (GSM8K)

More powerful: bring a bigger model, up to 72B params, to tackle a harder dataset (DAPO-Math-17k)

https://github.com/gensyn-ai/rl-swarm

Also in this release, we’ve added:

- multi-peer ID / EOA mapping - allowing you to link multiple nodes to a single EOA with the same email address.

- better reward and participation tracking, with new dashboard versions

- memory optimisations for consumer devices

Follow the progress of the updated math swarm by viewing the new dashboard here

Follow the progress of the updated math swarm by viewing the new dashboard here

https://dashboard-math.gensyn.ai/

Follow the progress of the new, bigger, math-hard swarm with bigger models by viewing the new dashboard here

Follow the progress of the new, bigger, math-hard swarm with bigger models by viewing the new dashboard here

https://dashboard-math-hard.gensyn.ai/

We will continue to scale RL Swarm across new domains, and soon allow you to launch your own training swarms, based on your interests and areas of expertise.

See you in the swarm(s).

We’ve long held that artificial superintelligence will come from a collection of diverse models that interoperate, rather than a single monolith.

Multi-swarm on the Gensyn Testnet is the first step in this direction, with the new swarm running alongside the original.