正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Open-source LLMs are getting really good. They’re not as powerful as GPT-4, but they’re improving quickly and worth experimenting with. If you want to run AI models like Mistral-7B on your laptop this is the easiest way to do it.

Mckay Wrigley

227,808 subscribers

575,582 次观看 • 2 年前 •via X (Twitter)

科学技术教育

Anya Rossi• Live Now

Private livecam show

10 条评论

Mckay Wrigley 的头像

Mckay Wrigley2 年前

Mistral-7B last week felt like a major inflection point in OSS LLMs. Exciting for more people to begin playing around with locally running models!

Nick Dobos 的头像

Nick Dobos2 年前

GPT4All and LMStudio are also great app options Recently found LMStudio and its my new fav Better if you want an actual app instead of the command line Both have 1 click drop in local webserver openAi api compatible endpoints -

Yash 🧑‍💻 的头像

Yash 🧑‍💻2 年前

I used the LLM for code, so I still prefer GPT-4 🤖

Mckay Wrigley 的头像

Mckay Wrigley2 年前

Well yeah GPT-4 is the best and definitely what people should use for best results but exploring other LLMs is interesting and will be important going forward

Andrew Ruiz 的头像

Andrew Ruiz2 年前

That’s such a great name. Ollama.

Bland 的头像

Bland2 年前

@mckaywrigley For real - how's 'Bland' though? :D

Sense 的头像

Sense2 年前

Ollama is going to be huge. Feels like Docker, missing some feature still but great start.

Jai Rod 的头像

Jai Rod2 年前

Are these API access?

Mckay Wrigley 的头像

Mckay Wrigley2 年前

Nope they run locally on your machine for free

Max Howell 的头像

Max Howell2 年前

pkgx can run this. Just type `ollama` @pkgxdev

相关视频

The future of AI is open-source. And ollama is the easiest way to build AI applications with open-source LLMs. Here's how to build a free, private RAG app using open-source tools. We'll use: - Ollama for LLMs and embedding models - PostgreSQL for data storage and retrieval - pgai Vectorizer for embedding creation and sync (I use Nomic for embeddings and tinnyllama as my LLM but you can substitute them for any models on Ollama)

The future of AI is open-source. And ollama is the easiest way to build AI applications with open-source LLMs. Here's how to build a free, private RAG app using open-source tools. We'll use: - Ollama for LLMs and embedding models - PostgreSQL for data storage and retrieval - pgai Vectorizer for embedding creation and sync (I use Nomic for embeddings and tinnyllama as my LLM but you can substitute them for any models on Ollama)

Avthar

34,261 次观看 • 1 年前

Create your own local and free AI agent using an open source model You can combine: - IBM's Granite 3.3 8B AI model - LM Studio to run it on a laptop - Smolagents to build your agent Small AI models are now powerful enough to run an autonomous agent. Thanks to IBM France for sponsoring this content!

Create your own local and free AI agent using an open source model You can combine: - IBM's Granite 3.3 8B AI model - LM Studio to run it on a laptop - Smolagents to build your agent Small AI models are now powerful enough to run an autonomous agent. Thanks to IBM France for sponsoring this content!

Paul Couvert

18,890 次观看 • 1 年前

Mistral CEO Arthur Mensch on the need for open-source AI: “If you assume that the entire economy is going to run on AI systems, enterprises will just want to make sure that nobody can turn off their systems.” “If you treat intelligence as electricity, then you just want to make sure that your access to intelligence cannot be throttled.” "The only way in which you can create systems that are effectively using the folklore knowledge of your employees, the knowledge that you've accrued for decades... is to create your own models based on those open-source models." “This is a technology which is so important, that you don’t want to be locked into a single vendor.” Arthur Mensch on Big Technology Podcast

Mistral CEO Arthur Mensch on the need for open-source AI: “If you assume that the entire economy is going to run on AI systems, enterprises will just want to make sure that nobody can turn off their systems.” “If you treat intelligence as electricity, then you just want to make sure that your access to intelligence cannot be throttled.” "The only way in which you can create systems that are effectively using the folklore knowledge of your employees, the knowledge that you've accrued for decades... is to create your own models based on those open-source models." “This is a technology which is so important, that you don’t want to be locked into a single vendor.” Arthur Mensch on Big Technology Podcast

a16z

287,968 次观看 • 5 个月前

Tim Dillon: “AI is coming for your privacy.” “This is not a conspiracy.” “They just come out and say it.” “They’re coming for your property.” “They’re coming for your freedom.” “They’re digitizing everything.” “They’re gonna control your money supply.” “They’re gonna control how you can spend, when you can spend it … where you can travel.” “And if you’re concerned about that … the immediate response will be: well, China!” “We’ve gotta enslave everyone with AI before they do.” “But if you are needing to earn money to live … ” “Or you are concerned about your privacy … ” “Or you’re concerned about AI targeting schools in Iran and blowing up children … ” “If you have any of these concerns, you’re dismissed immediately as a loser, as a Luddite, as a crank, as someone who hates technology.” Tim Dillon

Tim Dillon: “AI is coming for your privacy.” “This is not a conspiracy.” “They just come out and say it.” “They’re coming for your property.” “They’re coming for your freedom.” “They’re digitizing everything.” “They’re gonna control your money supply.” “They’re gonna control how you can spend, when you can spend it … where you can travel.” “And if you’re concerned about that … the immediate response will be: well, China!” “We’ve gotta enslave everyone with AI before they do.” “But if you are needing to earn money to live … ” “Or you are concerned about your privacy … ” “Or you’re concerned about AI targeting schools in Iran and blowing up children … ” “If you have any of these concerns, you’re dismissed immediately as a loser, as a Luddite, as a crank, as someone who hates technology.” Tim Dillon

Holden Culotta

19,957 次观看 • 1 个月前

🚨HOW Widespread is SomaliFraud? It’s EXTENSIVE All you have to do is drive down the street across Columbus and anyone can see it. There’s daycares as far as the eye can see. They’re on every street, every block, but really theres an even simpler way to know it’s a problem. If the stats are accurate, 72% of the Somali community is on welfare. If they’re on welfare, they’re not working. If they’re not working, they don’t need daycare. But somehow the other 28% of the Somali community owns a daycare? The math doesn’t math. The fraud is obvious to anyone who takes even a moment to look. 🇺🇸

🚨HOW Widespread is SomaliFraud? It’s EXTENSIVE All you have to do is drive down the street across Columbus and anyone can see it. There’s daycares as far as the eye can see. They’re on every street, every block, but really theres an even simpler way to know it’s a problem. If the stats are accurate, 72% of the Somali community is on welfare. If they’re on welfare, they’re not working. If they’re not working, they don’t need daycare. But somehow the other 28% of the Somali community owns a daycare? The math doesn’t math. The fraud is obvious to anyone who takes even a moment to look. 🇺🇸

Walter Curt

18,068 次观看 • 5 个月前

Tucker Carlson Goes Biblical on the Global Agenda “What they’re promising you is DEATH.” “If they’re promising you the opportunity to castrate your children, what are they really promising you? No grandchildren. The end of your line. And Solomon and David would instantly recognize that as an act of total war against you and your people — period. Because that’s what that is. “So they can’t say any of this out loud because there’s not one person who wants that product — extinction. There’s not one person who wants that. And so, if they’re going to take and maintain power, they need to get it another way, a non-democratic way. And the way they’re going to do that, and the way they are doing it as we speak, is by changing the population of the country.” Tucker Carlson

Tucker Carlson Goes Biblical on the Global Agenda “What they’re promising you is DEATH.” “If they’re promising you the opportunity to castrate your children, what are they really promising you? No grandchildren. The end of your line. And Solomon and David would instantly recognize that as an act of total war against you and your people — period. Because that’s what that is. “So they can’t say any of this out loud because there’s not one person who wants that product — extinction. There’s not one person who wants that. And so, if they’re going to take and maintain power, they need to get it another way, a non-democratic way. And the way they’re going to do that, and the way they are doing it as we speak, is by changing the population of the country.” Tucker Carlson

The Vigilant Fox 🦊

1,043,560 次观看 • 2 年前

Introducing ambientGPT: an open-source and multimodal MacOS foundation model GUI Run GPT-4o and open-source models with full ambient knowledge of your screen. Foundation models have long been confined to the browser. With ambientGPT, your screen context is directly inferred as part of the query, ensuring you never need to explicitly upload context again! Github:

Introducing ambientGPT: an open-source and multimodal MacOS foundation model GUI Run GPT-4o and open-source models with full ambient knowledge of your screen. Foundation models have long been confined to the browser. With ambientGPT, your screen context is directly inferred as part of the query, ensuring you never need to explicitly upload context again! Github:

Siddharth Sharma

192,766 次观看 • 2 年前

Geoffrey Hinton says I never expected to see an AI speak English as fluently as humans GPT-4 can answer almost any question, acting like a "not very good expert" but it knows thousands of times more than any person its reasoning isn’t perfect, but it’s improving quickly

Geoffrey Hinton says I never expected to see an AI speak English as fluently as humans GPT-4 can answer almost any question, acting like a "not very good expert" but it knows thousands of times more than any person its reasoning isn’t perfect, but it’s improving quickly

Haider.

69,773 次观看 • 1 年前

You may hear Democrats defending these foreign nationals… calling them “victims” or “new Americans”… But let me give you the truth: They’re not here to assimilate. They’re here to dominate. And you, Mr. and Mrs. American, are the obstacle standing in their way. They don’t care about your Constitution—they’re teaching their children how to circumvent it, challenge it, and ultimately replace it with their own laws, their own language, their own authority. This isn’t immigration. It’s infiltration. And the left is cheering it on because they hate this country as much as its enemies do. Make no mistake: they’re not here to become Americans. They’re here to rule over Americans. #InvasionNotImmigration #NoAssimilationNoCitizenship #14thAmendmentFraud #AmericaUnderSiege #DearbornCaliphate #StopTheReplacement

You may hear Democrats defending these foreign nationals… calling them “victims” or “new Americans”… But let me give you the truth: They’re not here to assimilate. They’re here to dominate. And you, Mr. and Mrs. American, are the obstacle standing in their way. They don’t care about your Constitution—they’re teaching their children how to circumvent it, challenge it, and ultimately replace it with their own laws, their own language, their own authority. This isn’t immigration. It’s infiltration. And the left is cheering it on because they hate this country as much as its enemies do. Make no mistake: they’re not here to become Americans. They’re here to rule over Americans. #InvasionNotImmigration #NoAssimilationNoCitizenship #14thAmendmentFraud #AmericaUnderSiege #DearbornCaliphate #StopTheReplacement

A Gene Robinson

32,937 次观看 • 1 年前

Many of these leftist are absolute losers who don’t like our country and do not want to see it do well. They’re very smug and think they’re morally superior. They’re not. They’re just annoying and destructive to the good fabric of our society.

Many of these leftist are absolute losers who don’t like our country and do not want to see it do well. They’re very smug and think they’re morally superior. They’re not. They’re just annoying and destructive to the good fabric of our society.

Jeffery Mead

93,734 次观看 • 2 天前

“if people don’t want to like you, for whatever reason, they’re gonna find any reason not to. it can be the easiest, dumbest, littlest thing. so, you know, the people that do like you and do support you and love you, those are the people to focus on, and that’s all that matters.” 🫂❤️‍🩹

“if people don’t want to like you, for whatever reason, they’re gonna find any reason not to. it can be the easiest, dumbest, littlest thing. so, you know, the people that do like you and do support you and love you, those are the people to focus on, and that’s all that matters.” 🫂❤️‍🩹

sabrina daily

89,386 次观看 • 7 天前

“Your leaders are telling you to endure for another 4 years but they’re living in luxury, why is the endurance not across board?” I’ve said it before, if as a religious leader in this country, you’re not preaching like this in this HORRIBLE times, you’re suspect.

“Your leaders are telling you to endure for another 4 years but they’re living in luxury, why is the endurance not across board?” I’ve said it before, if as a religious leader in this country, you’re not preaching like this in this HORRIBLE times, you’re suspect.

SportsDokita (Odogwu ☝️)

13,389 次观看 • 2 个月前

Today’s a big day! We have something really exciting to share with the open-source community. We’re launching two open-weight language models: gpt-oss-120b and gpt-oss-20b. They’re incredible models, built for developers, trained for reasoning, efficiency, and real-world use.🧵

Today’s a big day! We have something really exciting to share with the open-source community. We’re launching two open-weight language models: gpt-oss-120b and gpt-oss-20b. They’re incredible models, built for developers, trained for reasoning, efficiency, and real-world use.🧵

Romain Huet

34,187 次观看 • 10 个月前

SITUATION EXPLAINED: What happens to open source when the US restricts access to frontier AI models? We asked Adrian Dittmann: "China is releasing these models [open source] to gain international dominance, people will work on these things and say, 'Hey, maybe I can contribute to this if it's open source.' This is the thing that actually gets them talent." "If you're not allowed into the next GPT release or you're not allowed to use Fable, then what are you gonna do? You're stuck with the existing stuff, or you will have to use an open source model that might have subtly better capabilities." "The United States will catch up to open source in some form as well. They seem to just be maximizing product creation." "The problem with open source models is you have to be kind of a nerd in order to use them properly. Consumer facing, the effects will be minimal because the average person doesn't care about open source models. They only care whether or not they can do a quick search with Gemini or ChatGPT."

SITUATION EXPLAINED: What happens to open source when the US restricts access to frontier AI models? We asked Adrian Dittmann: "China is releasing these models [open source] to gain international dominance, people will work on these things and say, 'Hey, maybe I can contribute to this if it's open source.' This is the thing that actually gets them talent." "If you're not allowed into the next GPT release or you're not allowed to use Fable, then what are you gonna do? You're stuck with the existing stuff, or you will have to use an open source model that might have subtly better capabilities." "The United States will catch up to open source in some form as well. They seem to just be maximizing product creation." "The problem with open source models is you have to be kind of a nerd in order to use them properly. Consumer facing, the effects will be minimal because the average person doesn't care about open source models. They only care whether or not they can do a quick search with Gemini or ChatGPT."

MTS

14,406 次观看 • 4 天前

Our AI started with games. ♟️ But it didn’t end there. 🌐 Meet MuZero and AlphaZero, two powerful models which have evolved to transform computing itself. They’re already optimising data centres, improving the way we watch videos, and much more. How? 🧵

Our AI started with games. ♟️ But it didn’t end there. 🌐 Meet MuZero and AlphaZero, two powerful models which have evolved to transform computing itself. They’re already optimising data centres, improving the way we watch videos, and much more. How? 🧵

Google DeepMind

329,571 次观看 • 3 年前

Run state-of-the-art RAG applications locally on your computer with ollama and use all the fantastic open-source models like llama3, msk's awesome models, or Command R from cohere With Verba 1.0, we put it all in your hands 🙌 Get on board for a wild open-source ride, we're bridging any moat as open-source is here to win

Run state-of-the-art RAG applications locally on your computer with ollama and use all the fantastic open-source models like llama3, msk's awesome models, or Command R from cohere With Verba 1.0, we put it all in your hands 🙌 Get on board for a wild open-source ride, we're bridging any moat as open-source is here to win

Philip Vollet

41,375 次观看 • 2 年前

In between major AI model breakthroughs, new models still ship, but they’re not fundamentally expanding what you can do with them. Braintrust CEO Ankur Goyal says that’s exactly when open source starts to surge: "When new models come out, people forget about open source and forget about economics because it changes fundamentally what you can do." "Programming is a good example. The workflow today is completely different than it was a year ago. If you tried to use models from a year ago today, you wouldn't be able to do crazy stuff like OpenClaw or whatever people are building nowadays." "When models don't change at that speed, people optimize the performance on the use cases that they have." "If you look at usage on our platform, almost half the token usage is coming from open source models from a very small number of companies that have figured out how to optimize use cases really well."

In between major AI model breakthroughs, new models still ship, but they’re not fundamentally expanding what you can do with them. Braintrust CEO Ankur Goyal says that’s exactly when open source starts to surge: "When new models come out, people forget about open source and forget about economics because it changes fundamentally what you can do." "Programming is a good example. The workflow today is completely different than it was a year ago. If you tried to use models from a year ago today, you wouldn't be able to do crazy stuff like OpenClaw or whatever people are building nowadays." "When models don't change at that speed, people optimize the performance on the use cases that they have." "If you look at usage on our platform, almost half the token usage is coming from open source models from a very small number of companies that have figured out how to optimize use cases really well."

TBPN

16,294 次观看 • 4 个月前

Joe Rogan: "The best way to get good at jiu-jitsu is to strangle blue belts. You go and you find people that are just learning but they’re not as good as you and you choke the f*ck out of them." Brb, going to BJJ class.

Joe Rogan: "The best way to get good at jiu-jitsu is to strangle blue belts. You go and you find people that are just learning but they’re not as good as you and you choke the f*ck out of them." Brb, going to BJJ class.

Joe Rogan Podcast News

495,621 次观看 • 1 年前

SCP:GALLIONIC's trailer is releasing in just 5 days! We really really (really) want to make this, but absolutely need your help with it, as we can't do this alone. 🫵 Therefore, if you want to help us, make sure to go to our pre-launch page and select "Notify me on Launch", that way Kickstarter knows YOU are interested! The link to the page is in below ▼ #scp #SCPTheAnime #indie_anime

SCP:GALLIONIC's trailer is releasing in just 5 days! We really really (really) want to make this, but absolutely need your help with it, as we can't do this alone. 🫵 Therefore, if you want to help us, make sure to go to our pre-launch page and select "Notify me on Launch", that way Kickstarter knows YOU are interested! The link to the page is in below ▼ #scp #SCPTheAnime #indie_anime

soem studios

23,545 次观看 • 4 个月前

Ansem explains the thesis behind Dolphin AI “Dolphin is the provider of the uncensored model that Venice uses” “ChatGPT, Claude, all of the big labs have very strict rules on what you can ask the models, they’re censored very heavily” “We’re not in control of what that censorship is and what they’re telling the models not to say” “One of crypto’s core tenets is not having to rely on some centralized entity deciding what you can and cannot do” “They want the technology to be free and open to everyone. Uncensored models are one way crypto is looking at doing that”

Ansem explains the thesis behind Dolphin AI “Dolphin is the provider of the uncensored model that Venice uses” “ChatGPT, Claude, all of the big labs have very strict rules on what you can ask the models, they’re censored very heavily” “We’re not in control of what that censorship is and what they’re telling the models not to say” “One of crypto’s core tenets is not having to rely on some centralized entity deciding what you can and cannot do” “They want the technology to be free and open to everyone. Uncensored models are one way crypto is looking at doing that”

Market Bubble

20,688 次观看 • 1 个月前