时间序列领域终于有了可预测的缩放定律，做时序预测的团队可以像训练语言模型一样放心堆数据和算力，建议直接下载权重试试。
Datadog 发布了 Toto 2.0 系列时间序列基础模型，参数规模从 4M 到 2.5B，采用 Apache 2.0 开源协议。该系列模型在 BOOM、GIFT-Eval 和 TIME 等主流基准测试中均取得领先成绩，且每个更大规模的模型性能都优于较小的模型。这是时间序列领域首次出现清晰的缩放定律曲线，意味着研究人员可以像语言和视觉模型那样，通过增加数据和计算量来可靠地提升模型性能。2.5B 和 4M 参数的模型权重已在 Hugging Face 上开源。
Are scaling laws finally working for time series foundation models? Today, @datadoghq is releasing ...
Are scaling laws finally working for time series foundation models? Today, @datadoghq is releasing Toto 2.0 weights in Apache 2.0 on @huggingface . It's a family of open-weights TSFMs from 4M to 2.5B parameters, where every size beats the last from a single hyperparameter config. First across the leading benchmarks: BOOM, GIFT-Eval, and TIME. Most TSFM families ship multiple sizes that all perform roughly the same. This one doesn't. Why it matters: scaling laws gave language and vision a predictable relationship between compute, data, parameters, and downstream performance. Time series hasn't had that curve until now. Once you have it, you can scale data and compute with confidence, and start asking which new capabilities emerge at the next order of magnitude. 2.5B open-source weights: huggingface.co/Datadog/Toto-2… 4M open-source weights: huggingface.co/Datadog/Toto-2… Blogpost: datadoghq.com/blog/ai/toto-2… 💬 7 🔄 29 ❤️ 183 👀 20612 📊 40 ⚡