Fireworks 发布 SWE-2 模型，成本降低70%
Reinforcement learning at @cognition's scale is a hard infrastructure problem. We are proud to be pa...
Fireworks 新发布的 SWE-2 模型很厉害，成本比之前低很多，适合做大规模训练。
Fireworks 的 SWE-2 模型在主流评估基准上表现与前沿模型相当，但训练成本降低了70%。该模型通过优化强化学习流程，实现了参数量达到数万亿级别的规模。
Reinforcement learning at @cognition's scale is a hard infrastructure problem. We are proud to be pa...
Reinforcement learning at @cognition 's scale is a hard infrastructure problem. We are proud to be part of the stack behind it. Congrats to the team on SWE-2! Read more about how we think about RL at Fireworks: fireworks.ai/blog/frontier-… Cognition @cognition Introducing SWE-2, our closest model yet to the frontier. On leading evals, it scores on par with recent frontier models – at up to 70% lower cost. We scaled RL to multiple trillions of parameters, with a refined recipe that pushes the Pareto curve on both capabilities & cost. 🔗 View Quoted Tweet 💬 0 🔄 0 ❤️ 1 👀 174 ⚡