Interesting idea… my first concerns would be of mean reversion kicking in when combining different models, that or overfitting when combining the same one. Have to try it out though
@DiogoNeves16 күн бұрын
That is spot on! You explained it better than I did (when I mentioned "amplifying some weights" I guess that's better expressed with overfitting). Your concerns are exactly why I do not understand how it could work. I am also considering: - Maybe the process of merging has some "unintended" side-effect that may be the cause for better results. (I don't yet know how to test this) - Maybe merging reduced previous overfitting in the network, by applying changes that were not present during training, leading to slightly better generalisation. (This could be tested by disrupting the network with noise, or "merging with a noisy model" and see if the effect persists.) What do you think?
@DiogoNeves17 күн бұрын
Have you tried MergeKit or know of any other alternatives?
@boqoll26 күн бұрын
U need a supercomputer for this. The regular m.2 mac, can’t handle this. Way too slow…
@DiogoNeves26 күн бұрын
It needs a fair bit of memory, I’m running on an M1 Air with 16GB Which models have you tried? Start with a smaller one. How much memory do you have? Soon I am going to show a lighter approach that although slow, runs on a raspberry pi
@yorkie4kАй бұрын
I've been using LM Studio as it just works. Super easy to build plugins with the server as well to get functionalities that aren't in the app.
@DiogoNevesАй бұрын
@@yorkie4k totally! I’m now also looking into Llamafiles and SQLite-vec. Both really cool too, but LM Studio is still the simplest and most accessible I know Do you use LM Studio just for the chatbot? Or are you building something with it? Would love to learn more 😉
@yorkie4kАй бұрын
@@DiogoNeves I've built my own RAG app for it. If you're in the LM Studio discord you'll see my post on it.
@endianAphonesАй бұрын
For me it helps to think that I'm talking to someone I know. Imagine you're in a meeting or something. Not that I'm creating anything.
@DiogoNevesАй бұрын
@@endianAphones thanks 🙏 definitely will use that next time!
@luciferovonnachtosphereАй бұрын
Finally, I found a well-made, no-frills, guide to installing local LLMs!
@DiogoNevesАй бұрын
@@luciferovonnachtosphere thanks 🙏 I really appreciate
@aca95aksАй бұрын
I'm much preferring LM Studio than GPT4All - thanks for the tutorial :)
@DiogoNevesАй бұрын
@@aca95aks thanks 🙏 yes, I really like the simplicity and interface of LM Studio. Have you tried any of the other alternatives like Ollama?
@danielhabibioАй бұрын
This is the first tech tutorial I've ever seen that was recorded in the woods!
@DiogoNevesАй бұрын
@@danielhabibio thanks! The coming videos should also have an outdoor twist too 😉 hopefully gets more people in the flow and woods are just awesome. P.s. I promise I’m not building a bunker in the woods to hide from our AI overlords 😉
@glossyxrose2 ай бұрын
Tysm
@glossyxrose2 ай бұрын
Wow! That looks so cool!
@DiogoNeves2 ай бұрын
We were together this day 😊
@glossyxrose2 ай бұрын
Nice donut!
@mrredfairy1 Жыл бұрын
Adorable.
@zeldafan5515 Жыл бұрын
Awww this is so cute 🥰
@DiogoNeves Жыл бұрын
Thanks!! A friend of mine is considering creating a website so that anyone could easily make these stories. I really like the idea