Skip Navigation
InitialsDiceBearhttps://github.com/dicebear/dicebearhttps://creativecommons.org/publicdomain/zero/1.0/„Initials” (https://github.com/dicebear/dicebear) by „DiceBear”, licensed under „CC0 1.0” (https://creativecommons.org/publicdomain/zero/1.0/)AU
Posts
1
Comments
80
Joined
2 yr. ago
  • QWQ-32B for most questions, llama-3.1-8B for agents. I'm looking for new models to replace them though, especially the agent one.

    Want to test the new GLM models, but I'd rather wait for llama.cpp to definitely fix the bugs with them first.

  • What I've ultimately converged to without any rigorous testing is:

    • using Q6 if it fits in VRAM+RAM (anything higher is a waste of memory and compute for barely any gain), otherwise either some small quant (rarely) or ignoring the model altogether;
    • not really using IQ quants - afair they depend on a dataset and I don't want the model's behaviour to be affected by some additional dataset;
    • other than the Q6 thing, in any trade-offs between speed and quality I choose quality - my usage volumes are low and I'd better wait for a good result;
    • I load as much as I can into VRAM, leaving 1-3GB for the system and context.
  • Recommending Italo Calvino's Six Memos for the Next Millennium, the lectures he has been preparing shortly before his death.

    Not an assembly guide for a work of literature, but it'll help your own process if it's already ongoing and you want to improve.

    The lectures also have some comments on what Calvino himself was doing here and there and why.

  • Because we have tons of ground-level sensors, but not a lot in the upper layers of the atmosphere, I think?

    Why is this important? Weather processes are usually modelled as a set of differential equations, and you want to know the border conditions in order to solve them and obtain the state of the entire atmosphere. The atmosphere has two boundaries: the lower, which is the planet's surface, and the upper, which is where the atmosphere ends. And since we don't seem to have a lot of data from the upper layers, it reduces the quality of all predictions.

  • Given the fact that there was an unintentional DDOS when federated Lemmy instances were requesting the same preview around the same time, it must be one of LW's servers, not anything on your side.

    The only sure way to get rid of this effect is to use an instance entirely hosted on servers in anglophone countries, I think.

  • This is not to say that Jung wasn't a genius. Jung was THE BOMB DIGGIDITY (which, by the way, I wish was an official term in the Oxford dictionary).

    If they love Jung so much (which I agree they should because Jung was amaaaaazing), why don't they honor him by using the spelling he actually used?

    Love etymological articles with unreliable narrators.

  • Once configured, Tor Hidden Services also just work (you may need to use some fresh bridges in certain countries if ISPs block Tor there though). You don't have to trust any specific third party in this case.

  • If config prompt = system prompt, its hijacking works more often than not. The creators of a prompt injection game (https://tensortrust.ai/) have discovered that system/user roles don't matter too much in determining the final behaviour: see appendix H in https://arxiv.org/abs/2311.01011.

  • Piracy: ꜱᴀɪʟ ᴛʜᴇ ʜɪɢʜ ꜱᴇᴀꜱ @lemmy.dbzer0.com
    Audalin @lemmy.world

    Sheet music resources

    How do you acquire sheet music?

    There're IMSLP and musescore, but many things are just not there.

    Bonus points if you know anything with xenharmonic/microtonal music well-represented.