polystruct

joined 2 years ago
[–] [email protected] 5 points 1 day ago (1 children)

In Belgium, you need to wait two weeks before donating again (plasma and platelets, 2 months for blood). I regularly donate platelets, and sometimes plasma if the platelet slots are all occupied.

We get thank-you receipts (or public transportation ones) which we can turn in for some goodies. I hoard them up until I can get two tickets for an amusement park that I can visit with my daughter.

I don't know if getting paid for it would be better or more appreciated. I feel that it could lead to more abuse? I am much more happy to know I'm donating for a good cause...

[–] [email protected] 0 points 2 years ago (1 children)

Nice answer! Is there a number of concepts, to your knowledge/experience, where a LORA no longer works? For instance, if I want to make a model that understands all car brands and types, assuming that the base model doesn't of course, would a LORA still be sensible here?

Most LORAs I find have a more specialized narrow focus, and I don't know if I would just start with multiple LORAs dealing with individual concepts (a LORA for a "1931 Minerva 8 AL Rollston Convertible Sedan", a LORA for a "Maybach SW 42, 1939", etc.) or if I should try and generate one LORA to ~~rule~~ know them all...

 

I understand that, when we generate images, the prompt itself is first split into tokens, after which those tokens are used by the model to nudge the image generation in a certain direction. I have the impression that the model gets a higher impact of one token compared to another (although I don't know if I can call it a weight). I mean internally, not as part of the prompt where we can also force a higher weight on a token.

Is it possible to know how much a certain token was 'used' in the generation? I could empirically deduce that by taking a generation, stick to the same prompt, seed, sampling method, etc. and remove words gradually to see what the impact is, but perhaps there is a way to just ask the model? Or adjust the python code a bit and retrieve it there?

I'd like to know which parts of my prompt hardly impact the image (or even at all).