Large language models (LLMs) have been shown to be able to perform new tasks based on a few demonstrations or natural language instructions. While these capabilities have led to widespread adoption, most LLMs are developed by resource-rich organizations and are frequently kept from the public. As a step towards democratizing this powerful technology, we present BLOOM, a 176B-parameter open-access language model designed and built thanks to a collaboration of hundreds of researchers. BLOOM is a decoder-only Transformer language model that was trained on the ROOTS corpus, a dataset comprising hundreds of sources in 46 natural and 13 programming languages (59 in total). We find that BLOOM achieves competitive performance on a wide variety of benchmarks, with stronger results after undergoing multitask prompted finetuning. To facilitate future research and applications using LLMs, we publicly release our models and code under the Responsible AI License.

过去的几年见证了基于变压器的模型的成功，其规模和应用方案继续积极发展。变压器模型的当前景观越来越多样化：该模型大小差异很大，最大的参数是最大的。模型特性由于特征的混合物所引入的稀疏性而有所不同。目标应用程序方案可以是关键延迟或面向吞吐量的情况；部署硬件可以是具有不同类型的内存和存储等单身或多GPU系统。随着多样性的增加和变压器模型的快速发展速度，设计高性能和高效的推理系统非常具有挑战性。在本文中，我们提出了DeepSpeed推断，这是用于解决上述挑战的变压器模型推理的全面系统解决方案。深速推理包括（1）一种多GPU推理解决方案，可最大程度地减少潜伏度，同时最大化密集和稀疏变压器模型的吞吐量，当它们适合聚集的GPU内存时，以及（2）一种异质推理解决方案，该解决方案利用CPU和NVME内存中的CPU和NVME内存。除了GPU内存和计算以使高推理吞吐量具有不适合聚集GPU内存的大型推理吞吐量。对于面向延迟的方案，深速推理可将延迟降低到最新的7倍，而对于面向吞吐量的方案，延迟的潜伏期将延迟减少到1.5倍以上。此外，它通过利用数百个GPU来实现实时延迟约束下的参数量表推断，这是一个前所未有的推理。它可以比仅使用GPU的解决方案更大的25倍模型，同时提供84个TFLOPS（超过50美元的A6000峰值）。

Large deep learning models offer significant accuracy gains, but training billions to trillions of parameters is challenging. Existing solutions such as data and model parallelisms exhibit fundamental limitations to fit these models into limited device memory, while obtaining computation, communication and development efficiency. We develop a novel solution, Zero Redundancy Optimizer (ZeRO), to optimize memory, vastly improving training speed while increasing the model size that can be efficiently trained. ZeRO eliminates memory redundancies in data-and model-parallel training while retaining low communication volume and high computational granularity, allowing us to scale the model size proportional to the number of devices with sustained high efficiency. Our analysis on memory requirements and communication volume demonstrates: ZeRO has the potential to scale beyond 1 Trillion parameters using today's hardware.We implement and evaluate ZeRO: it trains large models of over 100B parameter with super-linear speedup on 400 GPUs, achieving throughput of 15 Petaflops. This represents an 8x increase in model size and 10x increase in achievable performance over state-of-the-art. In terms of usability, ZeRO can train large models of up to 13B parameters (e.g., larger than Megatron GPT 8.3B and T5 11B) without requiring model parallelism which is harder for scientists to apply. Last but not the least, researchers have used the system breakthroughs of ZeRO to create the world's largest language model (17B parameters) with record breaking accuracy.

隐私性和解释性是实现值得信赖的机器学习的两种重要成分。我们通过图形重建攻击研究了图机学习中这两个方面的相互作用。这里的对手的目的是重建给定模型解释的训练数据的图形结构。根据对手可用的不同种类的辅助信息，我们提出了几种图形重建攻击。我们表明，事后功能解释的其他知识大大提高了这些攻击的成功率。此外，我们详细研究了攻击性能相对于三种不同类别的图形神经网络的解释方法的差异：基于梯度，基于扰动和基于替代模型的方法。虽然基于梯度的解释在图形结构方面显示最多，但我们发现这些解释并不总是在实用程序上得分很高。对于其他两类的解释，隐私泄漏随着解释实用程序的增加而增加。最后，我们提出了基于随机响应机制的防御，以释放大大降低攻击成功率的解释。我们的匿名代码可用。

图形神经网络（GNNS）概括了图形数据上的传统深度神经网络，在几个图形分析任务上取得了最先进的性能。我们专注于训练有素的GNN模型如何泄露有关他们培训的\ emph {成员}节点的信息。我们介绍了两个现实的设置，以便在GNN上执行员工推理（MI）攻击。在选择利用培训模型的后索（黑匣子访问）的最简单可能的攻击模型时，我们彻底分析了GNN和数据集的属性，这些数据集决定了对MI攻击的鲁棒性的差异。虽然在传统的机器学习模型中，过度装备被认为是这种泄漏的主要原因，我们表明，在GNN中，额外的结构信息是主要的贡献因素。我们在四个代表性GNN模型上进行了广泛的实验，我们支持我们的结果。为防止MI攻击GNN，我们提出了两种有效的防御，明显将攻击者推断显着降低了60％，而不会降低目标模型的性能。我们的代码可在https://github.com/iyempissy/rebmigraph获得。