Hacker News new | ask | show | jobs
by Lwerewolf 10 days ago
Well, just ran said gguf on the GeneralsX codebase with a pretty open-ended "Explain this codebase to me, and the general game loop." prompt, and...

  Let me also look at the GameLogic::update() to see the rest of the update flow, especially the object update loop.

  Actually, I think I have enough information now. Let me also check the GameLogic::UPDATE to understand the full update flow.
...repeating forever.

Since they mentioned that they're working on new quants, guess I'll wait. From earlier tests on work stuff, it's definitely capable.
1 comments
Lwerewolf 10 days ago
Right:

https://huggingface.co/poolside/Laguna-S-2.1-FP8/discussions...

Wait time.

link
embedding-shape 10 days ago
More updates from the Discord (also mostly about the NVFP4):

> we've got an NVFP4 checkpoint that has a KD of 0.135 relative to the BF16 checkpoint (for W4A4, on some GSM8K prompts). [...] We're still seeing some looping on W4A4 (although much less than before), whereas for W4A16 we've not been able to make it loop. Given that W4A4 is still a little broken, we won't make this an official release (we have one more idea planned to fix that). [...] The RC1 for NVFP4 is reachable as poolside/Laguna-S-2.1-NVFP4 @ RC1

Seems to be available already indeed: https://huggingface.co/poolside/Laguna-S-2.1-NVFP4/tree/RC1

link
Lwerewolf 9 days ago
Tool calling in pi completely broke with the updated q4 gguf (spinquant-less). Guessing it'll take some time.
link
Lwerewolf 9 days ago
...they'd messed something up in that quant, apparently fixed promptly. ds4 now supports it as well and it's... well, context-limited (<=250k on a 128gb machine) but it positively flies on an m5 max - the 60tok/s decode / ~500tok/s prefill is real.
link