精选理由
Heidi自己微调开源模型，质量居然比Gemini Pro还好，速度还快了3.5倍，4周就上线，太强了。
Heidi团队不再租用第三方模型，选择微调一个开源模型。在内部评估中，该模型质量超越Gemini Pro。延迟从25秒降至7秒，速度提升3.5倍。从概念验证到生产部署仅用4周。
原文 · Fireworks AI
The team @tryheidi didn't want to keep renting someone else's intelligence. So Heidi fine-tuned an ...
The team @tryheidi didn't want to keep renting someone else's intelligence. So Heidi fine-tuned an open model that beat Gemini Pro on quality in their internal evals, and ran with 3.5x faster latency (25s → 7s). From POC to production in 4 weeks. Get the full scoop → fireworks.ai/blog/Heidi-Hea… 💬 0 🔄 1 ❤️ 5 👀 351 📊 1 ⚡