henk717
henk717
Would like to voice my support for this, over at the KoboldAI community we had requests for multi-user support and it would also help out our Horde platform which currently...
7 may not be a bug, the result shown is an accurate representation of the tokens being streamed because of how deeply integrated we are into the actual token process...
This is currently a known issue we are still trying to solve, restarting KoboldAI is currently the best method until we figure out a solution for this.
Setting seed is the last message once its done loading, the link to use the AI is higher up.
I do prefer to have the installation and usage directly visible so people don't read over the link. I assume the same design is possible with a link inside the...
I hope they will do this, our community finetunes models for fiction and we'd love to share finetunes with people. But we have no intent to do this illegally. Right...
Lora is plan B but our tuners did not obtain the model officially yet. Its much easier for everyone if we can give the entire model though. Our software hasn't...
Flexgen is to limiting (Hardcoded OPT models with only a temperature slider), but 8-bit is still being worked on. Flexgen so far I haven't had positive feedback on from the...
For some models this is intentional because the model does not have native new line support. These run in S mode (FSD based models). OPT should be running in NS...
I am fine accepting the disable, but if you can also do this fix for the -cuda version to keep it consistent.