| Commit message (Collapse) | Author | Age | Files | Lines |
|---|
| |
|
|
|
|
|
|
| |
This might be useful if your server is misbehaving, or if you wish to
write your HTML by hand.
Alternative options (like client-side preprocessing) can also be added
in the future using this setting as a framework.
|
| | |
|
| |
|
|
|
|
| |
This was a planned feature since the introduction of LLM
enhancements. Some users need a sobering reminder that LLMs are not
intelligent, because it is really easy to believe otherwise.
|
| |
|
|
|
|
|
|
|
| |
There's no preferences dialog, so you can't really adjust the prompt
or the model it uses. The default settings work well for me. You may
want to tweak them depending on your model preferences and compute
budget. (Not many can afford to run Llama3-8B at high
quantization. Conversely, you might have a better GPU than me and wish
to run a 27B model or bigger.)
|
| | |
|
| |
|
|
|
| |
Empty for now, but I am planning to include setting up the API
endpoints and prompts for Smart Summary, among other things.
|
|
|
This took a while and had me scratching my head often. But I managed
to combine the best parts of Crane and Meson together, allowing me to
have blazing fast Nix builds.
This also adds initial scaffolding for gettext and other cool things.
|
