Llama 3.1 405b Deep Dive | The Best LLM is now Open Source

In this video, we explore the cutting-edge advancements of Meta's new open source LLAMA 3.1 large language models, including the massive 405B model, and compare them to top-tier closed source models like GPT-4 Omni and SONNET 3.5. We discuss the significance of open source AI, how it democratizes access and innovation, and dive into detailed performance benchmarks. Additionally, we evaluate the creative and practical capabilities of these models, running various tests including the generation of creative stories and handling real-world knowledge queries. Learn how these models not only rival but sometimes surpass their closed-source counterparts, and discover how you can use and run them locally.

▼ Link(s) From Today’s Video:

-------------------------------------------------

▼ Extra Links of Interest:

Let's work together!

Thanks for watching Matt Video Productions! I make all sorts of videos here on Youtube! Technology, Tutorials, and Reviews! Enjoy Your stay here, and subscribe!

All Suggestions, Thoughts And Comments Are Greatly Appreciated… Because I Actually Read Them.
00:00 Introduction to Meta's LLAMA 3
01:41 Advantages of Open Source AI
02:51 Meta's Commitment to Open Source
04:37 Model Evaluations and Comparisons
06:38 Running Smaller Models Locally
08:56 Creative Story Generation Test
09:56 Community Reactions and Usage
21:42 Strawberry Test and Model Limitations
31:31 Conclusion and Final Thoughts

[MattVidPro]

Hey folks! Important notice! Towards the end of the video I ran Llava Llama 8b which is a vision tuned version of Llama 8b NOT the new one. So this test is NOT representative of the new model. My bad!!! I must have ran the wrong model.

[MattVidPro]

ZUCC does it again! This lizard man just cannot stop releasing quality open source models!

[augustuslxiii]

Looking forward to the day when this kind of thing will be able to be run locally and quickly on affordable machines.

[MusicalGeniusBar]

Matt had AI Matt as a guest 😂😂😂 I couldn’t tell the difference 😅😅😢😢

[SSLCLIPS-TV]

I told you they're gonna be the best last year and I am 100% right!

[johnwilson]

Tried out the 8B and 70B on my RTX4090 with Ollama and I'm impressed so far. 8B is very fast and while 70B is slow, about one token per second, it is clearly better and useable if you're not in a hurry.

[fabiankliebhan]

I think you tested the old llama 3.0 8b model at the end

[jeffwads]

I tried this model on the HG spaces and wow. Amazing stuff. I asked it "I have a device that's time is 6:20am. An incident took place on that device at 5;34am. If my time now is 9:02am, what time did the incident take place in my time?" and it gave a quick and correct answer of 8:16. GPT4o got it right but its answer was rambling and way too involved.

[Maisonier]

I'm really starting to get concerned about these models and all the latest developments over the past year. While most people say things like 'this is the worst it's going to be, ' 'it's just beginning, imagine what it will be like in a few years, ' or 'the improvement is exponential, ' from everything I see, it looks like this isn't the baseline. It seems like we've already hit the peak of this technology, which is why there isn't much difference between the models. That's why they're looking for new approaches, like using agents or mixture of experts.

[viddarkking]

Yes I have no doubt many long RP session will be had with the updated 8 Billion model and it's many many fine tunes.😉

[rionix]

Downloaded 3.1 8b yesterdy, will test today

[jonmichaelgalindo]

The awesome thing about Llama Guard being a separate model from the GPT, is that you can update and redeploy just that tiny model as new jailbreaks are found, instead of having to retrain everything. Safety done right!

[starblaiz]

Llama 3.1 8b locally and 405b up on Groq, using RouteLLM to switch between them (8b as the weak and the 405b as the strong model, obviously). THEN combine THAT with an agentic framework. Wild power at our fingertips! 😮

[Stuck_in_Spacetime]

For counting total number of letters and counting a specific letter in a word, I used this prompt which works everytime: <Count the letters in the word "STRAWBERRY" and also count how many times "R" has appeared. Do it without using code>

[industrialpunk]

Your comparison at the end was with the old Llama3 (not the new 3.1) model (xtuner Llava Llama also has vision capabilities which you can install from LM Studio - it is fun to use - it'd be nice to see a video on LLM vision, its really powerful!)

[ThomasConover]

Zucc is making robot AI lizards from space great again. ❤

[wardehaj]

Thanks for the great video!
And now there is also mistral2 large available and according to the benchmark it should perform similar to llama3.1 405b!

[CapsAdmin]

You didn't test the new llama3.1 8b model locally, you were testing some custom model that combines llava and llama3.0 8b. The custom model is on huggingface under the name

[Arcticwhir]

liking the new lighting/camera upgrade

[smokedoutmotions_]

Crazy bro hell yeah. Thanks for jailbreak prompt