Hacker Newsnew | past | comments | ask | show | jobs | submit | drittich's commentslogin

Interesting - have you done MiMo-v2.6-flash?

Not yet. But can do so if there is interest.

Often the smartest thing is to do nothing.


Or know when to shut up.

A tangent, but can anyone ELI5 how models "know" when to stop generating tokens? Or what the method to stop them at the right point is?


The model doesn't "know" how to generate tokens any more than it knows how to stop generating tokens. The sampler simply stops pulling values when it outputs a "stop token", which is a token the same way every other token is.

That is to say, it stops when it's statistically the most likely to.


OK thanks, so the neural net (that no one can explain fully) generates a "stop" signal at a certain point.


I might be out of date but my understanding was that STOP was just another token that gets predicted.


API Error: 529 Overlorded


There are certainly challenges. When setting up a new model, I get AI to walk me through the commands using llama-benchmark that determine the best parameters for my particular configuration and needs. Once you've got that it's pretty easy to port those parameters to llama-server. It takes me about an hour to run through this process. It would be great if there was a registry of hardware, models, configuration parameters, and resulting tokens per second. Maybe one day we'll get there.


What kind of parameters do you end up changing, and how much difference does it make. Perhaps I am missing something and get more tok/sec, but I usually just do a git pull, then rebuild the latest whenever I get a new model.

In the past, I had to play with chat templates for some models to work with agents for tool calling. But I've never had to do anything other than specify the model, and tweaking the context size in some cases.


Things like the number of GPU layers, whether to use flash attention or not, enabling MTP, playing with context size.


And I thought I was killing it just saving some install disk images!


Nanobanana for scale.



...is the camera you have with you.


I used to invent TLAs on the spot for fun, and when someone asked what it was, would respond, "It's a PUA", eventually revealing that meant "previously unknown acronym". It was even more annoying that it sounds.


I think the point is to reproduce the sound of those hundreds of feet of standard run-of-the-mill cabling as faithfully as possible ;)


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: