Inception Labs的Mercury Foundation Models现在可以在Amazon Bedrock Marketplace和Amazon Sagemaker Jumpstart

在这篇文章中,我们宣布,Inception Labs的Mercury和Mercury Coder基金会模型现在可以通过Amazon Bedrock Marketplace和Amazon Sagemaker Jumpstart获得。我们演示了如何部署这些基于超快速扩散的语言模型,这些模型可以在NVIDIA H100 GPU上每秒生成1,100个令牌,并在代码生成和工具使用方案中展示其功能。

来源:亚马逊云科技 _机器学习
今天,我们很高兴地宣布,来自Inception Labs的Mercury和Mercury Coder Foundation Models(FMS)可通过Amazon Bedrock Marketplace和Amazon Sagemaker Jumpstart获得。通过此发布,您可以部署汞FMS来构建,实验和负责任地扩展您的生成AI应用程序。在这篇文章中,我们演示了如何在Amazon Bedrock Marketplace和SageMaker jumpstart.agout Mercury-Mercury基金会模型上开始使用Mercury Models的Mercury Models,这是基于商业规模扩散的语言模型的首个基于基于商业的语言模型的家族,并在较高的高度上促进了高高的高度增长,该模型是在高高的高位上促进了一代人的高度增长。与一次生成文本一个令牌的传统自回旋模型不同,汞模型使用扩散通过粗到精细的方法并行生成多个令牌,从而导致推理速度的更快。 Mercury Coder models deliver the following key features:Ultra-fast generation speeds of up to 1,100 tokens per second on NVIDIA H100 GPUs, up to 10 times faster than comparable modelsHigh-quality code generation across multiple programming languages, including Python, Java, JavaScript, C++, PHP, Bash, and TypeScriptStrong performance on fill-in-the-middle tasks, making them ideal for code completion and editing workflowsTransformer-based architecture, providing compatibility with existing optimization techniques and infrastructureContext length support of up to 32,768 tokens out of the box and up to 128,000 tokens with context extension approachesAbout Amazon Bedrock MarketplaceAmazon Bedrock Marketplace plays a pivotal role in democratizing access to advanced AI capabilities through several key advantages:Comprehensive model selection – Amazon BedRock Marketplace提供了从专家到公开的选项,提供各种型号,因此组织可以找到适合其特定用例的最适合。