Heating consumes a lot, because of this at least in some of Europe we still use natural gas over electricity. This allows your only energy spending to basically become a television and a fridge, sometimes your washing machine and dishwasher.
Absolutely, even for personal use sometimes you need API access like letting a local model access the internet or even a small python script to search and filter related research papers to your thesis. Limiting all API access behind another paywall is dirty.
I do not like these "surgical removals" and would rather prefer a pass over from a tool like Heretic. These surgical removals often trigger and analyze the activated neurons and erase them. This worked fine on older models where a single refusal vector existed. Now these "abliterated" models all suffer from catastrophic breakage because they are not as simple anymore. HauhauCS (on HF) for example, makes great uncensored models although they often work on smaller models rather than large ones like this.
> Heretic is a tool that removes censorship (aka "safety alignment") from transformer-based language models without expensive post-training. It combines an advanced implementation of directional ablation, also known as "abliteration", with a TPE-based parameter optimizer powered by Optuna.
> This approach enables Heretic to work completely automatically. Heretic finds high-quality abliteration parameters by co-minimizing the number of refusals and the KL divergence from the original model. This results in a decensored model that retains as much of the original model's intelligence as possible. Using Heretic does not require an understanding of transformer internals. In fact, anyone who knows how to run a command-line program can use Heretic to decensor language models.
Abliteration seems to be what Heretic does?
> Now these "abliterated" models all suffer from catastrophic breakage because they are not as simple anymore.
I'm not knowledgeable about each step in the process of making these abliterated models, but some more popular ones with steps after Heretic, seem to improve on the benchmarks tried of the base model:
I'm not seeing any similar benchmarks of the HauhauCS models, at least the ones I checked, so I assumed the opinion is based on your own trials, but then you argue in favour Heretic. Is the based on pre-Heretic abliteration techniques? Which might then not be appliable to this "Proprietary weight-level abliteration developed by the dealignai research team."?
Heretic is an awesome tool and I'd prefer Heretic over the "Proprietary weight-level abliteration developed by the dealignai research team" or manual labor model surgery. Since Heretic models are not often called "Abiterated" on HF but are called "Uncensored" or "Heretic" I may have gotten a bit confused there. From what I know, HauhauCS also uses Heretic so it should be the same as Heretic ones in benchmarks.
Non-zero chance if LLMs have access to the data required to make a bioweapon a regular person can do so too. Non-zero chance every second a meteor could hit you.
If it lets people play League on Linux thats a deal most will take. Tech people overestimate how much a normie cares about the anticheat or their data being sent to wherever.
I suggest you watch Scott Shafer's video on him for both the Lego and this investigation. His community posts also explain how Reckless Ben's ways are not okay.
reply