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）。

随着巨型密集模型的训练在当今硬件资源的可用性和能力方面达到了界限，由于其质量降低了大量培训成本，因此Experts（MOE）模型成为最有前途的模型体系结构之一等效密集模型。它的培训成本节省从编码器模型（先前的工作）展示到自动攻击性语言模型的5倍（这项工作以及并行探索）。但是，由于模型的规模和独特的架构，如何提供快速MOE模型推理仍然具有挑战性和未解决，从而限制了其实际用途。为了解决这个问题，我们提出了DeepSpeed-Moe，这是DeepSpeed库的一部分，包括新型MOE架构设计和模型压缩技术，将MOE模型大小降低到3.7倍，以及一个，以及一个与现有的MOE推理解决方案相比，高度优化的推理系统可提供7.3倍的延迟和成本。 DeepSpeed-Moe提供了前所未有的量表和效率，可与质量等效的密集模型相比，提供高达4.5倍和9倍的推理的大型MOE模型。我们希望我们的创新和系统有助于在大型模型景观中打开通往新方向的有前途的途径，从密集到稀疏的MOE模型转变，在这种模型中，培训和部署具有更少资源的更高质量模型变得更加广泛。

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.

As an important variant of entity alignment (EA), multi-modal entity alignment (MMEA) aims to discover identical entities across different knowledge graphs (KGs) with multiple modalities like images. However, current MMEA algorithms all adopt KG-level modality fusion strategies but ignore modality differences among individual entities, hurting the robustness to potential noise involved in modalities (e.g., unidentifiable images and relations). In this paper we present MEAformer, a multi-modal entity alignment transformer approach for meta modality hybrid, to dynamically predict the mutual correlation coefficients among modalities for instance-level feature fusion. A modal-aware hard entity replay strategy is also proposed for addressing vague entity details. Extensive experimental results show that our model not only achieves SOTA performance on multiple training scenarios including supervised, unsupervised, iterative, and low resource, but also has limited parameters, optimistic speed, and good interpretability. Our code will be available soon.

Recent work has shown that fine-tuning large pre-trained language models on a collection of tasks described via instructions, a.k.a. instruction-tuning, improves their zero and few-shot generalization to unseen tasks. However, there is a limited understanding of the performance trade-offs of different decisions made during the instruction-tuning process. These decisions include the scale and diversity of the instruction-tuning benchmark, different task sampling strategies, fine-tuning with and without demonstrations, training using specialized datasets for reasoning and dialogue, and finally, the fine-tuning objectives themselves. In this paper, we characterize the effect of instruction-tuning decisions on downstream task performance when scaling both model and benchmark sizes. To this end, we create OPT-IML Bench: a large benchmark for Instruction Meta-Learning (IML) of 2000 NLP tasks consolidated into task categories from 8 existing benchmarks, and prepare an evaluation framework to measure three types of model generalizations: to tasks from fully held-out categories, to held-out tasks from seen categories, and to held-out instances from seen tasks. Through the lens of this framework, we first present insights about instruction-tuning decisions as applied to OPT-30B and further exploit these insights to train OPT-IML 30B and 175B, which are instruction-tuned versions of OPT. OPT-IML demonstrates all three generalization abilities at both scales on four different evaluation benchmarks with diverse tasks and input formats -- PromptSource, FLAN, Super-NaturalInstructions, and UnifiedSKG. Not only does it significantly outperform OPT on all benchmarks but is also highly competitive with existing models fine-tuned on each specific benchmark. We release OPT-IML at both scales, together with the OPT-IML Bench evaluation framework.

Partial differential equations (PDEs) are widely used for description of physical and engineering phenomena. Some key parameters involved in PDEs, which represents certain physical properties with important scientific interpretations, are difficult or even impossible to be measured directly. Estimation of these parameters from noisy and sparse experimental data of related physical quantities is an important task. Many methods for PDE parameter inference involve a large number of evaluations of numerical solution of PDE through algorithms such as finite element method, which can be time-consuming especially for nonlinear PDEs. In this paper, we propose a novel method for estimating unknown parameters in PDEs, called PDE-Informed Gaussian Process Inference (PIGPI). Through modeling the PDE solution as a Gaussian process (GP), we derive the manifold constraints induced by the (linear) PDE structure such that under the constraints, the GP satisfies the PDE. For nonlinear PDEs, we propose an augmentation method that transfers the nonlinear PDE into an equivalent PDE system linear in all derivatives that our PIGPI can handle. PIGPI can be applied to multi-dimensional PDE systems and PDE systems with unobserved components. The method completely bypasses the numerical solver for PDE, thus achieving drastic savings in computation time, especially for nonlinear PDEs. Moreover, the PIGPI method can give the uncertainty quantification for both the unknown parameters and the PDE solution. The proposed method is demonstrated by several application examples from different areas.

Many real-world reinforcement learning tasks require control of complex dynamical systems that involve both costly data acquisition processes and large state spaces. In cases where the transition dynamics can be readily evaluated at specified states (e.g., via a simulator), agents can operate in what is often referred to as planning with a \emph{generative model}. We propose the AE-LSVI algorithm for best-policy identification, a novel variant of the kernelized least-squares value iteration (LSVI) algorithm that combines optimism with pessimism for active exploration (AE). AE-LSVI provably identifies a near-optimal policy \emph{uniformly} over an entire state space and achieves polynomial sample complexity guarantees that are independent of the number of states. When specialized to the recently introduced offline contextual Bayesian optimization setting, our algorithm achieves improved sample complexity bounds. Experimentally, we demonstrate that AE-LSVI outperforms other RL algorithms in a variety of environments when robustness to the initial state is required.

Optimal Transport (OT) provides a useful geometric framework to estimate the permutation matrix under unsupervised cross-lingual word embedding (CLWE) models that pose the alignment task as a Wasserstein-Procrustes problem. However, linear programming algorithms and approximate OT solvers via Sinkhorn for computing the permutation matrix come with a significant computational burden since they scale cubically and quadratically, respectively, in the input size. This makes it slow and infeasible to compute OT distances exactly for a larger input size, resulting in a poor approximation quality of the permutation matrix and subsequently a less robust learned transfer function or mapper. This paper proposes an unsupervised projection-based CLWE model called quantized Wasserstein Procrustes (qWP). qWP relies on a quantization step of both the source and target monolingual embedding space to estimate the permutation matrix given a cheap sampling procedure. This approach substantially improves the approximation quality of empirical OT solvers given fixed computational cost. We demonstrate that qWP achieves state-of-the-art results on the Bilingual lexicon Induction (BLI) task.

We study the problem of efficient generative inference for Transformer models, in one of its most challenging settings: large deep models, with tight latency targets and long sequence lengths. Better understanding of the engineering tradeoffs for inference for large Transformer-based models is important as use cases of these models are growing rapidly throughout application areas. We develop a simple analytical model for inference efficiency to select the best multi-dimensional partitioning techniques optimized for TPU v4 slices based on the application requirements. We combine these with a suite of low-level optimizations to achieve a new Pareto frontier on the latency and model FLOPS utilization (MFU) tradeoffs on 500B+ parameter models that outperforms the FasterTransformer suite of benchmarks. We further show that with appropriate partitioning, the lower memory requirements of multiquery attention (i.e. multiple query heads share single key/value head) enables scaling up to 32x larger context lengths. Finally, we achieve a low-batch-size latency of 29ms per token during generation (using int8 weight quantization) and a 76% MFU during large-batch-size processing of input tokens, while supporting a long 2048-token context length on the PaLM 540B parameter model.