本地模型跑Agent总嫌慢？Hermes Agent这次用上NeMo Relay，省token还少绕路，更新试试就知道。
Teknium宣布Hermes Agent集成NVIDIA NeMo Relay，重点优化小型/本地模型性能。基于25万条对话记录的分析，优化涵盖工具执行时间、内存、任务回合数、schema上下文负载以及token效率。更新已推送，完整版本明天发布。
Hermes Agent 🤝 NeMo Relay
Hermes Agent 🤝 NeMo Relay Teknium 🪽 @Teknium Hermes Agent is now dramatically more efficient, especially for smaller/weaker/local models! With the help of @nvidia 's Nemo Relay and several other strategies Hermes was able to identify a ton of optimizations beyond just saving tool execution time or memory - but also turns needed to complete tasks, schema improvements to reduce context load, and token efficiency gains by tracing through wasted turns and tool errors across all 250,000 conversations I've had with my Hermes. All of the below are now in Hermes Agent, update to start saving now or wait until tomorrow for the full version update release. 🔗 View Quoted Tweet 💬 4 🔄 5 ❤️ 27 👀 3478 📊 6 ⚡
- marktechpost08-02 06:21原文