Zos_Kia

I’ve only had issues with fitgirl repacks i think there’s an optimisation they use for low RAM machines that doesn’t play well with proton

I had the same feeling with planet crafter. After a while you learn to run around with just enough materials to build a room and a door and bam, the whole oxygen management mechanic is neutralized.

If I understand these things correctly, the context window only affects how much text the model can “keep in mind” at any one time. It should not affect task performance outside of this factor.

Yeh, i did some looking up in the meantime and indeed you’re gonna have a context size issue. That’s why it’s only summarizing the last few thousand characters of the text, that’s the size of its attention.

There are some models fine-tuned to 8K tokens context window, some even to 16K like this Mistral brew. If you have a GPU with 8G of VRAM you should be able to run it, using one of the quantized versions (Q4 or Q5 should be fine). Summarizing should still be reasonably good.

If 16k isn’t enough for you then that’s probably not something you can perform locally. However you can still run a larger model privately in the cloud. Hugging face for example allows you to rent GPUs by the minute and run inference on them, it should just net you a few dollars. As far as i know this approach should still be compatible with Open WebUI.

There are not that many use cases where fine tuning a local model will yield significantly better task performance.

My advice would be to choose a model with a large context window and just throw in the prompt the whole text you want summarized (which is basically what a rag would do anyway).

Same. I remember playing the original on an Amstrad in the 90s and it was already mind blowing. I was so happy they remade it, and even happier that they barely changed anything about it.