gensyn
@gensyn
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.
3 replies
19 recasts
39 reactions
Avicrypto
@avicrypto
Soon boom
0 reply
0 recast
0 reaction