Category For Dev’s

Pretraining and Finetuning MosaicML Models

Pretraining and Finetuning MosaicML Models

We run large language model (LLM) pretraining and finetuning end-to-end using Paperspace by DigitalOcean’s multinode machines with H100 GPUs. 4 nodes of H100×8 GPUs provide up to 127 petaFLOPS of compute power, enabling us to pretrain or finetune full-size state-of-the-art…

A Walkthrough of 12 Exciting Features of Paperspace Gradient

A Walkthrough of 12 Exciting Features of Paperspace Gradient

Paperspace is a cloud-based platform that leverages NVIDIA graphics cards and GPU-powered virtual machines to offer an unparalleled environment for building and scaling AI projects. With its NVIDIA H100 GPUs, Paperspace provides the computational power necessary for intensive AI and…

Method identified to double computer processing speeds

Method identified to double computer processing speeds

Imagine doubling the processing power of your smartphone, tablet, personal computer, or server using the existing hardware already in these devices. Hung-Wei Tseng, a UC Riverside associate professor of electrical and computer engineering, has laid out a paradigm shift in…

NVIDIA Hopper vs. Ampere Architectures

NVIDIA Hopper vs. Ampere Architectures

NVIDIA H100 GPUs are now available on Paperspace, offering high-performance computing for AI applications. With a wide selection of high-performance GPU machines and a user-friendly platform, Paperspace provides easy access to NVIDIA H100 GPUs. Sign up for access to H100…

Research Focus: Week of February 19, 2024

Research Focus: Week of February 19, 2024

Welcome to Research Focus, a series of blog posts that highlights notable publications, events, code/datasets, new hires and other milestones from across the research community at Microsoft. NEW RESEARCH Vertically Autoscaling Monolithic Applications with CaaSPER: Scalable Container-as-a-Service Performance Enhanced Resizing…

Reflection Agents

Reflection Agents

Key Links Reflection is a prompting strategy used to improve the quality and success rate of agents and similar AI systems. It involves prompting an LLM to reflect on and critique its past actions, sometimes incorporating additional external information such…

JSON agents with Ollama & LangChain

JSON agents with Ollama & LangChain

Learn to implement an open-source Mixtral agent that interacts with a graph database Neo4j through a semantic layer Editor’s note: This post is written by Tomaz Bratanic from Neo4j By now, we all have probably recognized that we can significantly…

Smart glove teaches new physical skills | MIT News

Smart glove teaches new physical skills | MIT News

You’ve likely met someone who identifies as a visual or auditory learner, but others absorb knowledge through a different modality: touch. Being able to understand tactile interactions is especially important for tasks such as learning delicate surgeries and playing musical…