วีดีโอ

The llm based sounds interesting but also expensive. I haven’t implemented any RAG yet but this was great food for thought for helping me know where to start! Thanks!

Thank you so much man ! Would it be possible to make a video on how to 'rent' VRAM? That would be awesome! Thanks, bro!

This is probably the last guide on RAG chunking I'll ever need. So well done. Thank you for the walkthrough of the research!

that was fantastic bro , thanks man

This is interesting to see. Especially since multiple articles state when using recursive chunking, chunk_overlap is an important parameter to ensure context between chunks but chroma suggests otherwise. What are your thoughts on this from your RAG experience?

Adam, I'm struggling to find the words to express how grateful I am for the content you share on your channel. Your ability to convey information clearly and without unnecessary speculation is truly brilliant. Thank you very much. If I were not broke, I would support you, but all I can support you with is thanking you.

🎉🎉🎉

is anthropic contextual RAG also can be considered as chunking strategy?

I am trying to build an Agentic RAG Framework with tool calling for Geographic Information System (GIS) Workflows for my Master's Thesis. I spent a lot of time trying to figure out the best chunking strategy and this honesty humbled me. Semantic chunking was a very compute intensive process and theoretically it sort of made sense so I went with that. Although, I am glad that I was only prototyping anyway, and since the dataset I have is huge, this is such a relief! Thanks for covering this Adam! Your content has been a great help.

Haha - I was looking at the code in another tab and just when he said we'd listen to the first audio to see if it sounds like water droplets, a deep narrator voice started talking about something - the commercial was placed just wrong for me to get kinda confused there.. :^D Don't worry - I recovered quickly.

Just what i need, big thanks

That's a great and a quite surprising overview! Thank you :)

U Da Man 😎

i have. an issue to install langchain in my env, upgraded my python too 3.11 but nothing change still the same problem :(

Here I go again, what a great video! You hit it off again, great demo, thank you.

i wish there was an ai that would make an model waterfold and optimise faces. Just that. That would be awsome.

Amazing, Indeed it's mastery the RL!

Thank you so much for this amazing tutorial. Keep up the great work! 🙌😊

This is amazing content! Quite concise and interesting! Thank you so much!!

How long before an LLM is trained specifically to code in OpenSCAD?

Awesome Video! Can you do a similar one for not fine-tuning the retriever but the generator. Like i found sth called "RAFT". When i understand it correctly, its about fine-tuning the actual LLM for RAG, by making it used to additional context to answer questions. For me it would be interesting: - which fine-tuning method is suited best for that (full-finetuning, adapters, ...) - how one does the E2E process

Wow! This is such a power packed video. Thanks for doing this. You deserve a lot more subscribers. Thank you again.

Siiiiick~

Tech nerds will never be great artist .

I wonder how this will impact the gaming industry. @NovemberHotel made a video about the recent move of several AAA studios from inhouse engines to UE5. One reason he brought up was the general focus on photorealism. Since AI tends to be much better with photoreal imagery I reckon that these two things (popularity of UE5 & AI 3D design) will most likely lead to heavy homogenization of gaming assets. I am sure that'll happen. I just hope we get over it fast so we can use this technology to make the tedious parts like retopo or generating base meshes easier instead of limiting the artistic vision.

The best walk through on this topic ever!! Thank you!!!

as a 3d artist im very sad

Thanks for being part of the few non-slop AI research coverage.

Gods work

as far as I'm aware AI has yet to achieve mastery of anything being able to do something does not make you a master Words mean things

If this gives us Auto-retopology I'll fucking throw my money at anyone who can provide it. Talk about the holy grail of 3D design.

Question: Does "load in 4bit"it support any model?

This channel is going to be best channel about AI & stuff for sure. Watching my 3rd video on trot and not a single yawn..

yooo this is great stuff! keep it up! I thought i was watching bycloud for a moment lol

Awsome stuff, I believe we are about to enter a golden age of indie games ! And of course AAA games, if big publishers finally decide to make good games.

Good content!!

Adam your videos rock! Keep up the good work and your channel is one of my favorites.

📚To try everything Brilliant has to offer-free-for a full 30 days, visit brilliant.org/AdamLucek/ You’ll also get 20% off an annual premium subscription! 💡

Had to watch it up to 3 times to get a hang of everything and I just finished my project using Dream booth. I have one question though... Is there a way to load new dataset without going to huggingface? Say, you need to deploy this as a WebApp where you can upload images on the platform.

Hi Adam! There's so much value packed in this video.. Thanks a lot!

Amazing run down on tools. Thanks so much for sharing.

amazing content, thank you so much, looking forward to more

Adam, Thank You!!! You explained this so well.

Thanks for the video. Great content as always! It would have also been nice to hear more details about the performance differences among the frequently used quantization methods such as q5_K_S, q6-K compared to just q4, q8, f16 and so on. As far as I know those indicate that certain layers are treated differently, some needing extra processing, but saving VRAM etc. But there is actually not that much information about that topic online. But I guess that would also fill a completely new video with content.

You are amazing! I always learn so much from your tutorials. Thank you!

I don't code or anything like that I just want to change my voice. I'm very confused by your explanation and this video

Thanks for this Adam - I understood this at a high level but it's nice to see some worked examples and detail of what's actually happening under the hood. Well explained.

one single layer doesn't really do anything two is the holy grail

great brother , what a hard work you did. Really appreciate it . Will share your channel with my friends too. Keep making please, I mean without going too much into maths but what is most important for a person who wanna use these models and understand the concept, u did just what was the best. Thanks