The `dynamic_processor_wrap` makes it so that the repetition penalty is
read directly from `vars`, but this only works if the initial repetition
sent to `generator` is not equal to 1. So we are now forcing the initial
repetition penalty to be something other than 1.
Expands the handling of the stories to userscripts and softprompts (Since I expect us to ship an example softprompt in the future). Now also copies the examples to your Google Drive if they are not already present.
This enables the use of a Lua 5.4 feature where you can have Lua
auto-close a file when exiting a block. For example:
```
do
local f <close> = kobold.get_config_file()
end
```
If we exit from the `do` block under any circumstances, including via an
error or return statement, the `FILE*` `f` automatically closes right
before that happens.
This commit exposes antemplates to the model config, this lets authors specify what kind of authors notes template they would like to use for their model. Users can still change it if they desire.
A user expressed positive feedback when trying higher than 2 repetition penalty on some models, lets allow people the freedom to do so. If there is a demonstrable benefit to running higher than 3 I am open to raising it again.
Blank lines appear often in chatmode so it is best played with blank line removal turned on, this is now forced. Its not compatible with Adventure mode, so they now turn each other off.
Added more models in the menu, all the popular community models are now easily accessible. I also re-ordered the menu from large to small to have it make a bit more sense.
* Error messages are now shown when memory, author's note, etc. exceeds
budget by itself
* Formatting options no longer break if there are empty chunks in the
story (although there shouldn't be any in the first place)
* Number of generated tokens is now kept track of from Python
Gnome Ann
henk717