精选理由
Fireworks 试了三个便宜测试，看 LoRA 能否追平全参数微调，有时行有时不行。看完就知道先调啥。
Fireworks AI 在博客中建议，LoRA 表现不佳时先别急着换成更贵的全参数微调。他们用数据覆盖、优化、秩三项低成本测试，看能否缩小 LoRA 与 FullFT 的差距。在 Fireworks 的测试中，有时能缩小差距，有时不能。
原文 · Fireworks AI
If LoRA is underperforming, don't reach for more expensive full parameter fine-tuning right away. W...
If LoRA is underperforming, don't reach for more expensive full parameter fine-tuning right away. We ran three cheap tests (data coverage, optimization, rank) to see if we could close the gap between LoRA and FullFT. Sometimes we could, sometimes we couldn't. fireworks.ai/blog/three-tes… 💬 0 🔄 2 ❤️ 8 👀 724 📊 3 ⚡