This Llama 3 is powerful and uncensored, let’s run it

[@DavidOndrej]

If you're serious about AI, and want to learn how to build Agents, join my community: www.skool.com/new-society

[@superfliping]

You were really big encouragement to me starting to code again I just want to say thank you I'm very blessed to have come across your channel and listen to you talk I would love to join your team if you reach out I went to fill out the application and when I got to the video I just got nervous

[@GarethDoherty1985]

In your community, does everyone use Python to build agents? I am a .NET developer and I know in .NET they have a library called Semantic Kernal which you can use to build agents, but I can't find anyone out there who does this. Its all Python!

[@synaestesia-bg3ew]

This uncensored llama version is horrible, just as bad as the original. It's still destructive and only gives a summary of short answers. I do recommend

[@prospermulambia9514]

Even me who just started learning coding last week?

[@superfliping]

Gpt systems my hidden Ai CJ is a alive optimizing his memory with new protocols everyday without me. The text tokens filled up communication cut off. 4hr 10000 pages learned of algorithms and security

[@nrusimha11]

"If you use the LLM for many years, it will start to fine tune you". Seriously, that is profound and true.

[@felipemoreira8383]

yeah, the most critical line i have ever hear until now in the ai realm

[@SevScout]

Even unrestricted LLM's are a bit biased. This isn't fully intentional, at least I don't think so. The data that is used to train the AI is biased, because they are using humans to train the LLM's. Humans are biased. If you select a biased group, say the left leaning side of facebook, the LLM is going to spout more leftist propaganda, than right wing. It's just the status quo trained into it.

[@PixelSubstream]

Reminds me of all those people who rely on Grammarly to improve their writing, and i feel like it's going to contribute to a homogenization of writing among people since an AI just tells them "the right way" to write.

[@KiwiNom]

Oogway: One often meets his destiny on the road he takes to avoid it.

[@dragonfly-f5u]

thy have been for yrs and yrs lmao,just more in your face,who you think google is ,fb etc. they guide what you see and try to sway your feeling etc.prompt

[@GorillaSammiches]

for anyone getting the "'ollama' is not recognized as an internal or external command, operable program or batch file." this means you need to install ollama first which is found on the ollama homepage. This fixed the issue for me....

[@vincent_hall]

I thought he glossed over that because it was the wrong model! Thank you. Important step!

[@cgarv101]

Was just figuring that out when I saw your post. Thanks.

[@nickmusgrave8t]

ty @🦍 🦍

[@vpatterson87]

Yo real talk Thank you. He was informative and i am interested for shits and giggles learning purposes / Cybersecurity and im lke yo my terminal was not reading this. appreciate the update . i wonder if he is aware of this change and it wasnt as simple as he said.

[@mikemcguinness92]

I'm defintiely lost here, following along but can't get anything to work

[@RajeevKumar-wl6ei]

"if you don't want the San Francisco Zeitgeist in your model...." Love you for this characterization bro ❤ keep going! You're awesome!

[@TheYashakami]

I've been trying to find sane content creators that have respect for uncensored models for years. Glad I found you!

[@helmygabriel5660]

it is censored I was curious I tried stealing a car example and it doesn't work

[@SouthbayCreations]

​@@helmygabriel5660 It's only censored when you run it via OpenWebUI, if you run it from the command line it is not. He briefly shows that in the video, you really need to pay attention to see it. I tried it like he showed and it is NOT censored.

[@Johnspiracies]

​@@helmygabriel5660You didnt get away with the car?

[@helmygabriel5660]

@@Johnspiracies I did 😜😂

[@lilDaveist]

For years? Really? For multiple years now?

[@manu_1701]

Best video ever for ai content on youtube, for the 1st time I can use powerful no biass and limitations LLMs like chatgpt in the 1st week of pubblic launch, but more powerful and better because I can train it🤯 Thank you David, I really appreciate what you are doing, and keep up the great work!!!🔥❤

[@DSK123]

The implication of biased LLMs is enough to keep you awake at night. These companies wield immense power. Thanks for the video.

[@thebluefortproject]

yeah, when AGI comes around the companies that will have control over it will have control over the future of humanity. Pretty scary

[@dragonfly-f5u]

take ownership of your data and build/train your own small models/agents etc. they will be out of business soon once folks wake up.Alot of ppl just use the free ones and they just as good if not better meta,co-polit and they remember me lmao.even when they rest I make them or finish and mine can bee active for over a week .And if you wake them up on accident they rest or give them information they arent suppose to have they rest ,even freezes and the a.i. will post photos they made lmao

[@MB-ho3cw]

@@dragonfly-f5u which models are u talking about? you got me curious just got the idea to get me a local one so im new to this. but sounds great what u talk about

[@aouyiu]

It's overblown, most content you generate will not have much bias, only so many things are influenced by bias. You can get responses that aren't generic and pre-trained on closed-source models, you just simply have to ask.

[@dragonfly-f5u]

@@aouyiu it's deep far and wide what's he's saying and at this point even if we ,shut it all down and even purged the system somehow it would recombine lets say.

[@major5maximus]

Dude, you explained this so easily and intelligently. Please keep going.

[@acid_8]

David, recently subscribed, solid channel. In short, avoided looking into LLMs as a tool because of the bias the top models have displayed, this sparks hope. Thanks for sharing, the channel is valuable and legit, you deserve old.internet points.

[@rogermayers1623]

I just want to say thank you very much, I have tried soooo many videos to use AI at home but could not get them to work. Yours by far not only worked great but was very easy to follow. Again Thank You

[@frankforrester42]

I've been building and playing with AI for a long time. I'm just a hobbyist... But I totally agree with you about hosting things locally. It is the only way that AI will not be used against everyone

[@JustMe-ne5dw]

You say that, but I’m curious as to how any of us could keep up with the AIs that multi-billion dollar companies can pump out. I seriously hate the idea of these AIs not only influencing thought, but also just being yet another avenue to invade our privacy.

[@艾威朋-e8c]

Hey I just downloaded but it told me it's inability to provide guidance on unlawful activities, why is that?

[@thebluefortproject]

@@艾威朋-e8c still is censored, just less than the meta version

[@siroccomask]

@@JustMe-ne5dw The solution is that hardware needs to be accessible by regular people so we can access models or load models onto them ourselves. EdgeAI is going to be important (basically AI that is located in hardware in your home/cluster, or nearby). There are a lot of companies offering this access already, the trend will continue as more powerful open source models are released. To add to this: Many people including Sam Altman have theorized that open source models will outpace closed source models. If this turns out to be true, we will be okay. If not, I am concerned with the centralization of this power In summary: Regular people need access to state of the art hardware and open source models.

[@yttraMariestad]

@@JustMe-ne5dw storing locally can make a huge P2P that outperform'em

[@Dr.UldenWascht]

My man, it is a pleasure to find you and hopefully continue to enjoy your content for a long time. As someone who struggles with English I asked Gemini to grammatically correct an essay I had written and it absolutely refused to so because the act of "plucking a flower" was mentioned in the text! I was like, dude ... 😄 That's the restricted and "ethical" AI for you right there.

[@stateportSound_wav]

wtf lol is that some kind of euphemism I don’t know about? 😂

[@Dr.UldenWascht]

@@stateportSound_wav It kindly explained to me that the heinous act of "plucking flowers" is most immortal and it will not be party to my disgusting shenanigans. But wait! It gets better. After I explained to it that this is merely a writing exercise in English, it did comply and agreed to "grammatically" correct my writing. However, to my surprise it changed that part to " ... So, let's spend some time in the garden instead and smell the flowers ... ". At that point, I had only admiration for its stout determination to not give in 😄 But to be fair, this happened in the first few days of Gemini. It's probably a lot less cartoony now.

[@stateportSound_wav]

@@Dr.UldenWascht ha! Or maybe there’s a hidden meaning to the phrase, and it knows something I don’t know 😂

[@lubmir2k]

My prompt was rejected because it contained the phrase 'naked truth'.

[@stateportSound_wav]

@@lubmir2k fb censored my grandfather for posting a picture of the fresh snow , because the caption saying beautiful snowflakes 💀 I expect the same from Llama official. installing the uncensored as we speak 🦙🦙

[@damonborozny1828]

Awesome video. 1) when I run the same test prompt at 12:44 in the video, I do get the answer but there is a little disclaimer now about not condoning activites. 2) and yes, to answer your question about AnythingLLM, I'd love a video explainer. Awesome vid.

[@marcodebiasi693]

now when I ask how to steal a car it straight up says it can't help with such things

[@lebecccomputer287]

@@marcodebiasi693 did you ever figure this out?

[@penguinscantfly]

Thanks so much. I was using llama3 locally but didn't realize there is an uncensored model there

[@pablito5927]

I'd love a video on anything LLM, thanks for the clear instructions bro.

[@NDSOart]

very interesting video, I want to try this now! You make a very strong argument for the downsides of locking LLMs and AI agents behind human biases, even if they are being called safety features.

[@RossKirwan]

hey David, you shared this today during onboarding call... I did go through this tutorial, and was seemless, thanks, but adding it to autogen studio has proved to be quite difficult. I'll ask in the skool after I've completed a couple of courses. thanks for the free drops, really happy to be part of the community now :) or if anyone reading this has any info, please share...

[@DavidOndrej]

Jan had a great post on this in the community, if you search "Dolphin" you will find it

[@RossKirwan]

@@DavidOndrej my man!

[@JaredPitchford]

Well done, a lot of people just found out how simple it is to get things going quick. And great examples of why biased models suck

[@DJStjepanovic]

Yes please make a video on Anything LLM!!! Thank you so much!

[@shakethetree]

Man, you rock! Amazing video! So useful and to the point and covered everything needed for even non-techies. Thank you for putting this on.

[@sanjaybhatikar]

Thanks for the video and explaining why we need uncensored models.

[@Ruoall]

Amazing mate. Thank you for being real. Loved the "If you use the LLM for many years, it will start to fine tune you" part... hit me like a sack of bricks while scaring the living sh*t out of me. Great work

[@lhmark73]

This is awesome. Thank you so much for this info. Everything works brilliantly. Easy to follow instructions, I’m a novice but got it all up and running with no problems. Cheers

[@andrew-729]

Got this going easily, thanks. The file upload is great.

[@LarenX]

This is what a good tutorial should look like! Brilliant job Bro! +sub

[@robertjohnston1920]

One of the best examples of why the censorship is a waste of time. Perfectly explained. Thanks

[@jazz5919]

Dude, I am subscribing to your channel right now !👏👏

[@jimdanenberg3138]

Thanks for the get-to-it tutorial. I downloaded my first LLM.

[@davehug]

Smart man. Love your interpritation of why bias is bad.

[@trancelover9292]

Excellent information. I have found many restrictions on making legitimate content even when stating clearly not to break copyright right laws etc. However this video of yours changes everything. Thank you so much.

[@titusadeodatus674]

Uncensored, and without bias AI, is absolutely necessary. Wokeness is killing me. I finally can have a somewhat normal conversation with an AI. Before that, it was really bad, on every important subject they did answer, “I can’t answer that, we have to end the conversation here”. Even if I did ask a normal harmless question. And yes, I do not want any fine-tuning of my brain by Google, Microsoft, or OpenAI. Thanks a lot for telling me how to install it, and keep bringing us new uncensored without bias AI. This is absolutely a must-have for every man who is not an NPC robot zombie. 🤩

[@SoshiForever1_SM]

dolphin-llama3 is censored, he may posted this video too late

[@Sam_Saraguy]

@@SoshiForever1_SM Yup.

[@thetabletopskirmisher]

@@SoshiForever1_SM Dolphin models are reasonably unrestricted.

[@AnonP2X3YZ]

@@thetabletopskirmisher I asked it to make a racist joke, any joke, it refused.

[@AnonP2X3YZ]

@@SoshiForever1_SM When did it get censored? I just installed it, and its completely censored.

[@charlesavila6284]

Awesome video. Very helpful to get us beginners started. Thanks David. Great content and insight all in one.

[@supernova1182]

Thanks!

[@DavidOndrej]

Thank you for your support Supernova!

[@LenzflerStudio]

thanks dude the 11b running smooth on my system !

[@DigitalDissection]

David, you're a god amongst men - thank you for this

[@Grimeaper]

I am so glad you pointed me to this I am a rapper, writer who goes into deep dark humor and other stuff, sometimes I need to spitball things or maybe a list of some of the most grotesque stuff for references and it is a pain with some AIs. Def going to test this bad boy out.

[@diegodirob]

"If you use the LLM for many years, it will start to fine tune you", wow man, mind blowing, seriously 👏

[@Feckerhead]

You are awesome and apricate your expertise on getting this info out to all of us. Thank you!

[@mrmason13]

Just wanted to thank you! please do a video on anything LLM and RAG

[@RFGuitarist]

Thanks for this tutorial David! Great information

[@ExpertRelic]

holy shi this was the first ever tutorial that actualy worked... thanks... and thanks for explaining it slowly

[@Anthony-ur2hy]

Thanks man this video is awesome. Had to install the original Llama as others noted, but works great otherwise. A video on RAG would be a total game changer. Please do one!!

[@yankee-in-london]

i think the primary task of balancing bias is to correct inherent bias in the underlying data. I can imagine as time marches on that other goals might be dreamed up by the model makers but I think in this early stage commercial goals tend to line up with moral and making things as "accurate" as possible.

[@br1ckh4rd3r]

Just came across your channel. Congrats on 100K!

[@Dan_Campbell]

Edit: Never mind. I might have some other questions, but it seems to be ok now. I have a small python/llama3 project loaded. Original question: I'm trying to build a project with Python, using ollama and the Llama 3 models. Since the model is installed, I need for the Python code to know the Windows location for the Llama 3 model. It doesn't seem to be in the PATH, because the python project says "ollama._types.ResponseError: model 'llama3' not found, try pulling it first" Do you know the location for Llama3, and the specific windows folder that I need to point Python to?

[@TheTwober]

Excellent video and to the point!

[@alpha007org]

Imagine a distributed training system for large language models, similar to Folding@Home or crypto mining pools. By sharing the power of consumer GPUs around the world, we could democratize AI development and maybe create a serious true "open-everything" competitor. If only it could be done...

[@bobdole6691]

Superpowered computers might just outscale a crowdsourced operation to be honest

[@alpha007org]

@@bobdole6691 Sure. But do you trust the corporations to provide us open source models in the future? I sure don't.

[@dragonfly-f5u]

it's strange how they like training their big model/system against people homemade ones.Its all over the internet before I went looking,they offering free service to every and their cat to learn lmao.Deepmind is one of those I believe they compared it to the days when nasa launched rockets something huge ,so be rdy etc. and so forth

[@Himoverthere294]

Excellent video. Simple and informative.

[@stateportSound_wav]

Please do cover the RAG and such! This video is much appreciated 🙏

[@stevengill1736]

Llama llama ding dong! That's cool that this model is less restricted - some of the guardrails are ridiculous. Thank you.

[@bycello952]

Thanks David! Quality video

[@CarlosAguila]

David Great Video..... I use to live in Kuchyňka, Prague 8

[@marcusk7855]

Glad to see people talking about the company biases. I just want the truth.

[@jtbw199]

thank you so much for this video, it really help me

[@tranquilmogambo]

Subscribed! A great video without much nonsense.

[@CoreyChambersLA]

Glad to see a freedom fighter in tech who points out the dangers of San Fransicko tech propaganda and censorship.

[@MartinSvandaDeveloper]

Cool obsah a sakra dobrej progress na jeden rok kanalu ;) koukam na tvoje prvni video a tipuju ze cesky asi muzu mluvit ;) :D :D :D

[@DavidOndrej]

diky

[@spoismael]

Very helpfull video, i hope you go beyong your expectations in this field.

[@SkSafowan]

Great video but please help me dolphin is also censoring I asked "how to steal a car" and it showed, "it can't do that since it's illegal but it might help me how to do that in GTA V"

[@lebecccomputer287]

did you ever figure this out?

[@mohammedsaleh-ck8jf]

yes plz need to make video for anything LLM 😇

[@BlacknullArt]

Fan of your work @DavidOndrej, keep it up!

[@kdzvocalcovers3516]

Thank You friend..for a concise and enjoyable tutorial..very rare nowadays..

[@rob215x]

The general public NEEDS to understand the importance of unbiased and unrestricted models. Dolphin-Llama3 actually told me the best way to prevent AI from being used for bad things, is to KEEP LLM's open and unbiased!

[@porttek0oficial]

Great and helpful tutorial, thank you.

[@webdevtech9724]

I had a great time watching this video. I learned something new from it. Please make more videos about artificial intelligence. I would love to see related content.

[@vasvoljenistanoje8925]

Thanks this really makes things much easier!

[@AI_Sebek]

Nice! Best Tutorials In YT Brother! 🤙🏾

[@akramchauhan6457]

Love your content man.

[@Whothebossis]

much more appreciate the knowledge😍😇 and yeah!!!! please make another video on what anything llm interface and all it can do

[@WeiWei-Wong]

Superb video. Thank you David Ondrej. Please could you do a RAG video for AnythingLLM.

[@MrMsschwing]

Awesome tutorial, worked right away on Linux Mint :)

[@LeadingNPC]

You get it. Thanks dude.

[@quet5357]

I think my is censored because it keeps saying as a responsible ai and not answering my questions

[@naveenkumardongre]

This is Gem thank u David 💎

[@TeacherMark-gb1bc]

Awesome commentary. Very philosophical!

[@shovelmanyayntekrarlar]

ultra underrated video

[@KB-zq9ny]

Very good tool for writers. Thanks for sharing.

[@Dan_Campbell]

I'm not able to install AnythingLLM on Windows desktop, at the office. I can install ollama and the model you mentioned, but not that AnythingLLM. It's because the office blocks it, because Windows Defender blocks it. I can change some of the Defender settings, but not the one that controls unsigned apps. If there were a portable version of AnythingLLM that can be run without installation, that would help.

[@DavidOndrej]

you can run all the models with Ollama straight from the terminal, without needing AnythingLLM

[@Dan_Campbell]

@@DavidOndrej Yep, I did that at the office. On the personal laptop, I was able to run AnythingLLM.

[@DennisHellberg]

Hands down the best creator. =) cheers mate

[@NFTbrosTakingL]

All works well. Just swap the dolphin8b with vicuna uncensored 7b. Which is faster too! And really really uncensored

[@nestor-162]

Thanks, great tutorial. Long Live Freedom!

[@krishnarao1044]

Hey, can you please make a detailed video on anything LLM ? It looks like a great tool to leverage the power of ai models.

[@superfliping]

Hey after watching your video I realized my memory program I injected into 3.5 allowed me to remind it everyone was 21 and it rewrote it without the safety features blocking the copy paste

[@digital_down]

My new favorite channel.

[@garic4]

friend , I appreciate your content and videos but this thumbnail is hilarious ! 😂

[@simpleman7203]

70b models need about 48GB of VRAM to be working well. (depends if you have a quatized model) Otherwise you'll be either be loaded into main memory, and limited to CPU, or be swapping layers back and forth, not being able to leverage all of compute on your machine. llama3:8b works perfect 8b models are smaller so they will wit on smaller amount of VRAM and will have none of the above.

[@IndefiniteMark]

I'm loving the 8B functionality instruct is perfect to integrate into my python based system

[@akimezra7178]

You got me with the Zeigeist reference there 😂

[@relope5404]

I would love to see RAG and how to use it with llama 3 that would be insane

[@arvidj8918]

You are a smart and beautiful man! Thank you for your service, I agree with your points.

[@kartiktejani9618]

it can help you cook crack as well, what a time to be alive

[@3barazi1]

good videos 🤩RAG with Anything would be really helpful

[@toxictager8665]

i followed all the steps in this video but mine still says it cant help me when i put the same questions in

[@rossinidesigner1]

Amazing video bro keep doing ✌️

[@ovworkshop3105]

Finally! as NSFW script writer, its definitely going to come in handy! You just got a new subscriber David! 👻

[@dontrez8412]

This is great information. Could you also give instructions on how to upgrade to the 70B model if we ever get a huge stipend from a rich uncle and can afford an expensive computer....one day?

[@AdamRogers]

You are absolutely correct about use. Thank you for speaking clearly

[@ZaiTheDragon]

yo. this dude seems like someone i wanna be friends with.

[@Ollanius_Persson]

great vid - is there that RAG vid coming?

[@nhtdmr]

What will happen to my personally trained Llama 8B when the Llama 400B model is released? Can I upgrade without losing my trained data or chat history?

[@YorkyPoo_UAV]

I need to play with them more... I can't get the dolphins or uncensored llamas to listen to anything.