Build custom generative AI applications powered by Amazon Bedrock
Empower your generative AI applications with customization techniques on Amazon Bedrock
Rephrasing the Web: A Recipe for Compute and Data-Efficient Language Modeling
Enhancing Language Model Pre-training Efficiency through Web Rephrase Augmentation
Join Google Cloud Security Summit 2024 for a masterclass in modernizing security
Masterclass in modernizing security at Google Cloud Security Summit 2024
Announcing LangChain on Vertex AI for AlloyDB and Cloud SQL for PostgreSQL
Integrating LangChain on Vertex AI for AlloyDB and Cloud SQL for PostgreSQL to turbocharge AI development
Inference AudioCraft MusicGen models using Amazon SageMaker
Deploy AudioCraft MusicGen model on Amazon SageMaker for asynchronous inference
Use Amazon Bedrock to generate, evaluate, and understand code in your software development pipeline
Leverage Amazon Bedrock for generative AI models to enhance your software development pipeline
The backbone behind Cloudflare’s Connectivity Cloud
Exploring Cloudflare’s global backbone infrastructure and its impact on network connectivity solutions.
Dear Duolingo: What kind of Chinese does Duolingo teach?
Exploring the different varieties of Chinese taught on Duolingo and their linguistic distinctions.
LLM in a Flash: Efficient Large Language Model Inference with Limited Memory
Efficiently deploying large language models on devices with limited memory using flash memory optimization techniques.
Direct Large Language Model Alignment Through Self-Rewarding Contrastive Prompt Distillation
Proposing a method for aligning large language models with human expectations through self-rewarding contrastive prompt distillation.
Investigation of a Cross-regional Network Performance Issue
Analysis of a cross-regional network performance issue uncovers the root cause in a Linux kernel upgrade affecting TCP receive window size calculations
Build an end-to-end RAG solution using Knowledge Bases for Amazon Bedrock and AWS CloudFormation
Automate the deployment of an end-to-end RAG solution using Knowledge Bases for Amazon Bedrock and AWS CloudFormation