neue medienordnung plus

neue medienordnung plus

nmoplus@realtime.fyi

unterwegs im digitalen Raum für mehr Datenschutz, Nachhaltigkeit und freie Kommunikation

Homepage:: http://sprechrun.de

Web-LLM Test

neue medienordnung plus

Sat, 29 Apr 2023 08:50:42 +0000

Web-LLM wird lokal ausgeführt

> Kommunikation mit Web-LLM Anfang
prompt: Wie kann ich den Wert der Variablen "@path" in einem Windows prompt-Fenster anzeigen?

Web-LLM-answer: Um den Wert der Variablen "@path" in einem Windows-Prompt-Fenster anzuzeigen, können Sie folgende Befehl ausführen: `echo %@path%`
Dieser Befehl wird im Windows-Prompt-Fenster ausgeführt und setzt den aktuellen Wert von "@path" in dem Bildschirmtext an.
Wenn Sie den Wert von "@path" in einer Skriptsprache angeben möchten, können Sie die Skriptsprache verwenden, um den Wert der Variablen zu setzen. Zum Beispiel, in der PowerShell kann das folgende Skript verwendet werden, um den aktuellen Wert von "@path" zu setzen: `$path = "$env:path\"`
Das Skript setzt den Wert von "@path" auf den Wert des Variablen-Speichers "env:path" ein. Die PowerShell sollte dann den aktuellen Wert von "@path" anzeigen, indem Sie das Skript ausführen.
> Kommunikation mit Web-LLM Ende
Generiert von https://mlc.ai/web-llm/ am 29.04.2023
encoding: 0.3643 tokens/sec, decoding: 1.0827 tokens/sec

#WebLLM #WebLLMDiary #MLC #chatGPT

Web-LLM experiences-3: prompt: What ist your name? Who are they?

neue medienordnung plus

Sat, 22 Apr 2023 08:26:35 +0000 zuletzt bearbeitet: Sun, 23 Apr 2023 06:44:41 +0000

> Communication with Web-LLM Begin
prompt: What ist your name? Who are they?
WebLLM-answer: As an AI language model, I go by the name Vicuna and was trained by researchers from Large Model Systems Organization (LMSYS).
> Communication with Web-LLM End
The chat demo is based on vicuna-7b-v1.1 model. Generated with https://mlc.ai/web-llm/ on 22.04.2023
Web-LLM took about 13 minutes to generate the response in this environment - see below:

Device Model: Fujitsu Esprimo Q556
Processor:    Intel(R) Pentium(R) CPU G4400T @  2.90 GHz
RAM           8,00 GB 
Systemtyp     Windows 10 Pro 64-Bit-OS, x64-based Processor
GPU           Intel HD Graphics 510
Browser:      Chrome Version 113.0.5672.53 (Offizieller Build) beta (64-Bit)

#WebLLM #WebLLMDiary #GPU #Esprimo #EsprimoQ556 #Q556 #vucuna #vucuna7b #vucuna7bv11 #LMSYS #LargeModelSystemsOrganization #LargeModelSystems #LLMOrganization

Web-LLM experiences - 2: What is Web-LLM?

neue medienordnung plus

Sat, 22 Apr 2023 07:37:24 +0000 zuletzt bearbeitet: Sun, 23 Apr 2023 06:44:10 +0000

> Communication with Web-LLM Begin
prompt: What is Web-LLM?
WebLLM-answer: I'm sorry, I'm not familiar with the term "Web-LLM." Could you provide more context or information about what you are referring to?

prompt: I mean with Web-LLM Web large language model. Can you explain what that is?
WebLLM-answer: Web-LLM is a large language model that is trained on data from the Web. It is essentially a deep learning algorithm that can be used to analyze and understand text data from the internet. The "Web" in "Web-LLM" refers to the fact that the model is trained on data from the World Wide Web.

Web-LLMs are often used in natural language processing (NLP) tasks such as sentiment analysis, question answering, and language translation. They are typically trained on large datasets of text data and are capable of generating human-like text based on the patterns and features they learn from the data.

Web-LLMs can be integrated into a wide range of applications, including chatbots, virtual assistants, and language translation tools. They are becoming increasingly important as the amount of text data available on the internet continues to grow, and the need for automated analysis and understanding of that data becomes more pressing.
> Communication with Web-LLM End
Generated with https://mlc.ai/web-llm/ on 22.04.2023

#WebLLM #WebLLMDiary #NLP #naturalLanguage Processing

Web-LLM experiences - 1: prompt: What is WebGPU?

neue medienordnung plus

Sat, 22 Apr 2023 07:28:32 +0000 zuletzt bearbeitet: Sun, 23 Apr 2023 06:45:09 +0000

> Communication with Web-LLM Begin
prompt: What is WebGPU?

WebLLM-answer: WebGPU is a framework that allows web developers to create applications that use graphical processing units (GPUs) on the web. GPUs are specialized processors that are designed to handle complex, compute-intensive tasks, such as rendering graphics, performing simulations, and machine learning.

WebGPU provides a set of APIs that make it possible to access the graphics processing capabilities of the web browser. This allows web developers to create applications that can take advantage of the power of GPUs, without the need for the developer to be familiar with low-level graphics programming.

WebGPU is built on top of existing web standards, such as WebGL and Three.js, and is designed to be easy to use and integrated with existing web development tools and workflows. It also supports various platforms, such as desktop and mobile browsers, as well as the WebGL and OpenGL ES APIs.

WebGPU allows web developers to create more complex and visually rich applications, such as real-time 3D
> Communication with Web-LLM End

Generated with https://mlc.ai/web-llm/ on 22.04.2023

#WebLLM #WebLLMDiary