LocalLLaMA
Welcome to LocalLLaMA! Here we discuss running and developing machine learning models at home. Lets explore cutting edge open source neural network technology together.
Get support from the community! Ask questions, share prompts, discuss benchmarks, get hyped at the latest and greatest model releases! Enjoy talking about our awesome hobby.
As ambassadors of the self-hosting machine learning community, we strive to support each other and share our enthusiasm in a positive constructive way.
Rules:
Rule 1 - No harassment or personal character attacks of community members. I.E no namecalling, no generalizing entire groups of people that make up our community, no baseless personal insults.
Rule 2 - No comparing artificial intelligence/machine learning models to cryptocurrency. I.E no comparing the usefulness of models to that of NFTs, no comparing the resource usage required to train a model is anything close to maintaining a blockchain/ mining for crypto, no implying its just a fad/bubble that will leave people with nothing of value when it burst.
Rule 3 - No comparing artificial intelligence/machine learning to simple text prediction algorithms. I.E statements such as "llms are basically just simple text predictions like what your phone keyboard autocorrect uses, and they're still using the same algorithms since <over 10 years ago>.
Rule 4 - No implying that models are devoid of purpose or potential for enriching peoples lives.
view the rest of the comments
I'd love to hear what local model you settle on for lyrics, I've been having a lot of fun with ACE-Step 1.5 but the lyric generator it's bundled with produces semi-nonsense lyrics that have nothing to do with what I prompt it with. Which is actually kind of fun in its own way, I literally never know what the song's going to be about, but I'd like a little control sometimes too. :)
Yeah I completely agree on the lyrics it can generate! That being said I actually haven't tried using the 4b lm model version just yet. I should probably give that a shot...
It's the one I use, so don't expect miraculous improvement. :)
I'm curious, do you have ADG enabled at all? How many steps do you use generally?
ADG == Audio-Driven Guidance? I haven't played around with that part much. I tried it out and couldn't get it to work, but it turned out that the reason ACE Step wasn't working was unrelated to that and I only figured out what was wrong after I stopped experimenting with ADG. So I haven't gone back to try it again.
I'm not really much of a music connoisseur, I just know what I like when I hear it. So mostly I just put together lyrics and then throw them at the wall to see what sounds good. :)
ADG for ace step is Adaptive Dual Guidance. try turning that on + make sure you have thinking enabled, I saw a big difference with both those on (more so thinking)
Ah. After poking around in the Gradio UI a bit, I found an "Enable ADG" but the tooltip says it's "Angle Domain Guidance", same thing?
I'm a programmer, but sometimes with AI I feel like a primitive tribesperson blindly attempting various rituals in an effort to appease the machine spirits. Eventually something works, and then I just keep on doing that.
Edit: I have angered the gods! My ritual failed! When I enabled ADG the spirits smote me with the following:
Guess I won't be trying that for now. :)