shawnhymel, to ai
@shawnhymel@masto.ai avatar

I made good progress on the collaboration project with @Jorvon_Moss over the weekend. The Orin Nano boots up the servers and WiFi hotspot automatically. You just need to run Hopper Chat on the . No internet required!

Running local LLM on Nvidia Jetson Orin Nano

mstankiewicz, (edited ) to mastodon Polish
@mstankiewicz@pol.social avatar

bawi i uczy!
Jednak ta cała tzw. sztuczna inteligencja nie jest taka zła jak ją malują. Dzisiaj dzięki jej pomocy, nauczyłem się korzystać z API do wyświetlania określonych wpisów w przeglądarce 😁
Jestem o krok od stworzenia własnego klienta!

Fizzle_Up, to ai
@Fizzle_Up@seocommunity.social avatar
ramikrispin, to ArtificialIntelligence
@ramikrispin@mstdn.social avatar

(1/2) Congratulations to my friend Lior and his co-author Meysam for the release of their new book - Mastering NLP from Foundations to LLMs 🎉

I met Lior a few years ago at a conference, and since then, I have been following his work in the field of NLP ❤️.

ramikrispin,
@ramikrispin@mstdn.social avatar

(2/2) The book covers the following topics:
✅ Mathematical foundations of machine learning and NLP
✅ Data preprocessing techniques for text data
✅ Machine learning applications for NLP and text classification
✅ Deep learning methods for NLP and text applications
✅ Theory and design of Large Language Models
✅ Applications of LLM models
✅ LLM applications with Langchain

The book is for folks who are interested in getting started with NLP and those who wish to delve into LLM applications.

mush42, to accessibility
@mush42@hachyderm.io avatar

This generative model allows you to sketch out a scene with a few words, it then leverages an LLM to flesh out the details, with the ultimate goal of feeding those details to a downstream visual image generation model.
It is almost, but not quite, entirely the inverse of image captioning models.
This offers the closest experience to an image generation tool that's usable by people with visual impairments.

https://huggingface.co/spaces/lllyasviel/Omost

chikim, to accessibility
@chikim@mastodon.social avatar

1/3 I tested some popular latest LLM UIs for accessibility with screen readers, including oobabooga text-generation-webui, Open WebUI (aka Ollama WebUI), GPT4All, LM Studio, Koboldcpp, and Llama.cpp server on Windows. The most accessible was Llama.cpp server, though it had the fewest features. Oobabooga was also good, except for the list box not announcing choices as you browse; however, you can check your selection afterward.

br00t4c, to ChatGPT
@br00t4c@mastodon.social avatar

GPT-4o, OpenAI's latest language model that has just been made freely available, has major safety flaws, an investigation by Radio-Canada's disinformation-busting unit, Décrypteurs, has uncovered.

#decrypteurs #chatgpt #jailbreaks #safety #llm #ai #largelanguagemodels

https://www.cbc.ca/news/science/chatgpt-disinformation-hate-artificial-intelligence-1.7220138

brennansv, to ChatGPT
@brennansv@sfba.social avatar

One tip for using ChatGPT that I am going to start using is to save prompts as a starting point so that I can always set the expectations for the rest of the thread. One way I use it is with shell scripting. I can give it all of my code style preferences and general code standards with a saved prompt which will save time when I start a new thread. #ChatGPT #LLM

parismarx, to tech
@parismarx@mastodon.online avatar

“When I say ‘I am hungry’, I am reporting on my sensed physiological states. When an LLM generates the sequence ‘I am hungry’, it is simply generating the most probable completion of the sequence of words in its current prompt.”

https://time.com/collection/time100-voices/6980134/ai-llm-not-sentient/

parismarx,
@parismarx@mastodon.online avatar

@hjoest “I will ignore the reality in front of my eyes because it’s much more exciting to tell myself I’m living in the early part of a scifi movie.”

Gargron,
@Gargron@mastodon.social avatar
ErikJonker, to ai
@ErikJonker@mastodon.social avatar

Any european competiton to OpenAI is welcome , good to see Mistral coming with a new model for programming, Codestral.
https://mistral.ai/news/codestral/

#AI #Mistral #Programming #coding #EU #LLM #codestral

joe, to ai

Previously, we looked at how to build a retrieval-augmented generation system using LangChain. As of last month, you can do the same thing with just the Ollama Python Library that we used in last month’s How to Write a Python App that uses Ollama. In today’s post, I want to use the Ollama Python Library, Chroma DB, and the JSON API for Kopp’s Frozen Custard to embed the flavor of the day for today and tomorrow.Let’s start with a very basic embedding example.

In the above example, we start by building an array of things that we want to embed, embed them using nomic-embed-text and Chroma DB, and then use llama3:8b for the main model.

https://i0.wp.com/jws.news/wp-content/uploads/2024/05/Screenshot-2024-05-30-at-10.32.52%E2%80%AFPM.png?resize=1024%2C800&ssl=1

So, how do you get the live data for the flavors of the day? The API, of course!

This simple script gets the flavor of the day from a JSON API, builds an array of embedable strings, and prints the result.

https://i0.wp.com/jws.news/wp-content/uploads/2024/05/Screenshot-2024-05-30-at-10.44.23%E2%80%AFPM.png?resize=1024%2C800&ssl=1

The next step is to combine the two scripts.

Two big differences that you will notice between the other two examples and this one is that the date no longer contains the year and I added a statement of what today’s date is, so that you can ask for “Today’s flavors”.

https://i0.wp.com/jws.news/wp-content/uploads/2024/05/Screenshot-2024-05-30-at-10.56.59%E2%80%AFPM.png?resize=1024%2C800&ssl=1

If you have any questions on how this works, later on today I am hosting a live webinar on Crafting Intelligent Python Apps with Retrieval-Augmented Generation. Feel free to stop by and see how to build a RAG system.

https://jws.news/2024/how-to-get-ai-to-tell-you-the-flavor-of-the-day-at-kopps/

#AI #ChromaDB #llama3 #LLM #Ollama #Python #RAG

forteller, to climate
@forteller@tutoteket.no avatar

If you needed another reason to hate "AI"

US slows plans to retire coal-fired plants as power demand from AI surges
https://www.ft.com/content/ddaac44b-e245-4c8a-bf68-c773cc8f4e63

#climate #coal #ai #llm

herr_sander, to llm German
@herr_sander@bildung.social avatar

Im kommenden Schuljahr wollen ein Kollege und ich ein zum Thema anbieten. Das erste Modul - ein Lernpfad zu den Grundfunktionen von - ist als erster Aufschlag fertig. Wir freuen uns über Feedback aus dem : https://www.taskcards.de/#/board/846c4790-d371-4abd-a63d-acae11adbba8?token=df9f302f-2ab2-4b35-a591-ef24d80c7ea0 (mit Texten von @mpblkclp und @isotopp . Der @Linkshaender hat da ja vielleicht auch etwas zu zu sagen :))

isotopp,
@isotopp@chaos.social avatar

@herr_sander @mpblkclp @Linkshaender

https://blog.koehntopp.info/2024/05/31/llms-daheim-mit-ollama.html

In welchem ich als Ergänzung zu meinem vorherigen Artikel einmal die Installation und den Gebrauch von Ollama demonstriere.

Wir installieren Ollama, laden mistral:instruct und verwenden den Ollama Prompt auf einem Mac mini oder einem Windows-Rechner mit Nvidia, um einen Text zusammenfassen zu lassen.

vitriolix, to ChatGPT
@vitriolix@mastodon.social avatar

Chat GPT doesn't know how many R's are in "strawberry" and is very persistent and creative in its lies

image/jpeg
image/jpeg

eloquence,
@eloquence@social.coop avatar

@vitriolix

Yeah - I appreciate Sal's enthusiasm for AI but the combination of the current generation of bots confidently saying nonsense to kids seems ... problematic.

vitriolix,
@vitriolix@mastodon.social avatar

@eloquence he does seem to have his head screwed on straighter than most in the tech sector right now

alexanderhay, to news
@alexanderhay@mastodon.social avatar

Quelle surprise. But what's worrying is how apparently 'tech 'n meeja' savvy young people are so easily taken in by propaganda - err, I mean 'hype and marketing'.

"...Very few people are regularly using "much hyped" artificial intelligence (AI) products like ChatGPT, a survey suggests...

"...But the study... says young people are bucking the trend, with 18 to 24-year-olds the most eager adopters of the tech..."

https://www.bbc.co.uk/news/articles/c511x4g7x7jo

endless_stateless,
@endless_stateless@mastodon.social avatar

@alexanderhay I think 'savvy' has come to mean 'using as the maker intended' rather than 'using in a conscious and informed approach'.

alexanderhay,
@alexanderhay@mastodon.social avatar

@endless_stateless Oh, very true, but the 'savvs' honestly believe the original meaning still applies to them. The Mark of the Mark, as it were.

  • All
  • Subscribed
  • Moderated
  • Favorites
  • JUstTest
  • mdbf
  • InstantRegret
  • ethstaker
  • magazineikmin
  • GTA5RPClips
  • rosin
  • modclub
  • Youngstown
  • ngwrru68w68
  • slotface
  • osvaldo12
  • kavyap
  • DreamBathrooms
  • Leos
  • thenastyranch
  • everett
  • cubers
  • cisconetworking
  • normalnudes
  • Durango
  • anitta
  • khanakhh
  • tacticalgear
  • tester
  • provamag3
  • megavids
  • lostlight
  • All magazines