Nvidia's local, private AI chatbot is a high-profile step toward cloud independence.
See full article...
See full article...
I run Mixtral 8x7B on two laptops in my house - one is a 3080 with 16gb vram, and the other is a 4070 with only 8gb vram, each with 64gb system ram. I've been using both Faraday and LM Studio and both run well enough for me.Does anyone know if this is able to use Mixtral 8x7B? I know the only cards that'd really be able to put that in memory are the RTX 3090 and RTX 4090 but that'd still be an awesome feat given the results from the linked article. I couldn't find any statement about which Mistral weights were actually in use.
Is there any chance that some targeted deep-dives could become a somewhat more frequent thing? Y'all do a good job with going broad and have a few solid articles about AI/ML as a whole. But I'd dearly love to see articles that go over some of these tools/projects in more detail.
For myself, I'd love a combination of technical exploration/practical usability (ie, I want to use this model myself, what is it good at and how easy is it to work with?) for those projects that are either designed for use by individuals/small teams, whether that's a front end like 'Chat with RTX' or locally-runnable models like OpenLLaMA or the various GPT4ALL incarnations. Dream would be some form of review article based on hands-on experimenting, though I'd be quite happy with something less - said dream sounds like a ton of work up front given the nature of the field.
I remember a movie based on this idea. I had no idea it would end up being so popular a business model would emerge here in the really real world.It's funny that this article is next to this one:
AI-powered romantic chatbots are a privacy nightmare
https://meincmagazine.com/ai/2024/02/ai-powered-romantic-chatbots-are-a-privacy-nightmare/
Perhaps Nvidia's solution solves this problem...
Just run GPT4All from gpt4all.io ... No new hardware (nor OS) needed.I got the hardware to run this (30xx series GPU with 16GB Vram and 32GB ram). But I will need to upgrade to Windows 11, since thats stated as required at the download site.
Damn it, finally I may be forced to upgrade since I want to try this out ......![]()
Mistral or LLaMa?The linked AI model isn't "uncensored". It's trained by a white supremacist who removed refusals for hate speech and for political topics he disagreed with. Please do not promote it. It is a crypto-fascist model. The chat agent's political alignement has been shifted, not just their etiical compass.
I am referring to "Uncensored" llama models on Hugging Face. They are created by filtering instruct/chat datasets for refusals, only the people responsible don't just filter for refusals. They remove any mention of gay and trans people. They remove people of color. They remove the word "feminism" entirely. "Supremacist" and so on. By leaving these concept undefined they leave the harmful biases of the base model, Llama 2.Mistral or LLaMa?
Mistral was founded by Arthur Mensch, Timothée Lacroix and Guillaume Lample and is a French company, so I’m assuming you’re talking about LLaMa? I can’t really find anything about his crypto-fascist tendencies, and really weird when you consider he is Jewish and his wife is Chinese/Vietnamese.
This is like saying black people like Kanye can't be racist. The idea itself is racist. Zuckerberg doesn't care. Why should he? He can survive the world ending and sleeps on a pile of money.really weird when you consider he is Jewish and his wife is Chinese/Vietnamese.
No, that’s not what I meant. The issue is where you have any proof, even if circumstantial, that he is racist?This is like saying black people like Kanye can't be racist. The idea itself is racist. Zuckerberg doesn't care. Why should he? He can survive the world ending and sleeps on a pile of money.
I didn't say either way that I recall. I said the argument was stupid and racist, not that Zuckerberg is specifically.No, that’s not what I meant. The issue is where you have any proof, even if circumstantial, that he is racist?