LaunchDevelopersAI Models
3 hours ago
prime-rl 0.6.0 trains trillion-parameter MoE models on agentic RL
Prime Intellect released prime-rl 0.6.0, targeting reinforcement learning on trillion-parameter MoE models. They trained GLM-5 on SWE tasks at up to 131k tokens per rollout.
·
3 hours ago