The KoboldAI horde bridge is typically configured by copying
KoboldAI-Horde-Bridge/clientData_template.py to clientData.py and
then editing the worker name, api key, and other settings. However
the bridge spawned by the local KoboldAI server was always using
hardcoded "anonymous" worker settings. To make it easier for people
to use their actual API key and specify a worker name, this change
modifies the bridge startup to attempt to import settings from
clientData.py. If clientData.py doesn't exist then we fall back
to using the default settings, and if the user hasn't edited the
worker name then we also generate a randomized name.
Also clear the horde bridge pid when stopping the bridge so that
it can be restarted within the same session.
This is a breaking change that allows 4.25.1 to work because they also have done breaking changes. If you do not make use of our automatic updater please update the dependencies when updating to this build.
This commit restores the chat models menu now we finally have good chat models available again.
Unfortunately huggingface reports back pytorch_model.bin even if the model's name is model.safetensors. I don't have a good way to combat this at the moment, so instead we now do a hack where if the model copy fails it manually tries model.safetensors instead hoping that it will work.
This fixes Pygmalion for now, if new issues arise from this in the future from other models we have to implement a cleaner method.
This commit decouples single line mode, well behaved models no longer need this since we stop at the You:.
There are scenario's however where this potentially breaks chatmode completely or makes models more frustrating to use. Users who experience this can enable the Single Line mode in the formatting menu to restore the old behavior.
I have also allowed token streaming again, since the issues with it have already been resolved.
