Skip to main content

Weekly Wiki✨

Greetings​

This is Seraphina in Seeed Studio and welcome to the Seeed Studio weekly wiki! Each Monday, I will introduce you our latest wiki, including the ones related to our new products, the interesting projects published by Seeed Studio, and the tutorials, introductions, etc... You name it.

✨ For each week, when a collaborator contributes a project or fixes something important, we put the stars at the end of title of "Weekly Wiki" for more people be able to see their efforts👍.

Today is April 1st and a brand new week has begun! Check out what Seeed Studio did last week!

Latest Wiki Launched​

Getting Started with Seeed Studio XIAO ESP32C6​

Seeed Studio XIAO ESP32C6 is powered by the highly-integrated ESP32-C6 SoC, built on two 32-bit RISC-V processors, with a high-performance (HP) processor with running up to 160 MHz, and a low-power (LP) 32-bit RISC-V processor, which can be clocked up to 20 MHz. There are 512KB SRAM and 4 MB Flash on the chip, allowing for more programming space, and binging more possibilities to the IoT control scenarios.

XIAO ESP32C6 is Matter native thanks to its enhanced wireless connectivity. The wireless stack supports 2.4 GHz WiFi 6, Bluetooth® 5.3, Zigbee, and Thread (802.15.4). As the first XIAO member compatible with Thread, it's a perfect fit for building Matter-compliant projects, thus achieving interoperability in smart-home.

Getting Started with Machinechat JEDI​

Machinechat JEDI is a powerful and versatile IoT (Internet of Things) data management software. It's designed to streamline the process of collecting, visualizing, monitoring, and responding to real-time data from a wide range of devices, sensors, and machines. Seeed's reTerminal DM and Machinechat JEDI software let you build custom dashboards in under 30 minutes. Track operations, analyze trends, improve efficiency, and receive timely alerts to prevent costly disruptions

Getting started of NEQTO Engine for Linux on reComputer J30​

NEQTO is a lightweight and secure software package allowing companies to remotely install and configure their software on edge devices. NEQTO enables companies to provide improved software services to end users through turnkey platform connectors and built-in software lifecycle management.

Devices installed with NEQTO can be managed through API or the ready-to-use NEQTO Console, which includes optional services for data storage, alerts, and watchdog monitoring. Businesses can enable AIoT with near-instant installation on any Linux device and seamless data integration with any on-premise or cloud servers.

pir

Quantized Llama2-7B with MLC on Jetson​

In this project, we introduce a quantized version of Llama2-7B, a large language model trained on 1.5TB of data, and deploy it on the Jetson Orin. We also leverage the Machine Learning Compiler Large Language Modle(MLC LLM) to accelerate the inference speed of the model. By deploying the quantized Llama2-7B with MLC LLM on the Jetson Orin, developers can build powerful natural language processing applications that deliver high accuracy and low latency on edge devices.

The Efforts of Contributor✨​

ow to Run a Local LLM Text-to-Image on reComputer​

Thanks our contributor Bruno to create the tutorial for how to Run a Local LLM Text-to-Image on reComputer.

A Text-to-image model is a type of artificial intelligence (AI) model that generates images from a textual description. These models take textual input, like sentences or paragraphs describing a scene and produce an image based on that description. hese models are trained on large datasets containing pairs of text descriptions and corresponding images, learning to understand the relationships between textual and visual information. Text-to-image models have made significant progress in recent years, but generating high-quality and diverse images that accurately match textual descriptions remains a challenging task in AI research.

On this tutorial, we're going to explore several ways to deploy and run a local LLM text-to-image

Past Weekly wiki​

Loading Comments...