优化OlmoEarth模型，大幅降低训练与推理成本。

OlmoEarth v1.2: A more efficient family of OlmoEarth models

• 改进模型架构与训练流程，提升计算效率。
• 训练耗时减少3倍，推理算力需求降低2.9倍。
• 适合资源有限但需高效遥感建模的研究者。

我们对OlmoEarth系列模型进行了多项改进，显著降低了训练和推理阶段的计算开销。训练阶段，基础模型所需的GPU小时数减少了3.0倍；在Sentinel-2任务中，推理阶段的乘加操作（MACs）减少2.9倍，同时保持了模型整体性能。所有训练代码已开源至github.com/allenai/olmoearth_pretrain。

原文摘要 · Abstract (English)

We present a set of improvements to the OlmoEarth family. These improvements allow us to cut compute costs during training ($3.0 \times$ reduction in GPU hours required to train our Base models) and inference ($2.9\times$ reductions in MACs on Sentinel-2 tasks), while maintaining the models' overall performance. All training code is available at github.com/allenai/olmoearth_pretrain.

Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。