kazord

Did you take a look at https://github.com/Noeda/rllama works ? doesn't have q4 yet but i have got decent result cpu and opencl on my radeon. It supports spliting job cpu/gpu...

same probleme with delete contacts ([keep it] / [delete]) confirmation

It s one of beta tester program, and yes it s the same problem as #229

Did you take in consideration that windows end of line is but model generation will go for new line with only lf ?

Would it be faster to ignore the ending space.s in reverse prompt check ? ie : "###" + " Human" + ":" and handle thoses finals spaces internally, generate token...

as mention Green-sky, the token generation, the space is special , as it's include in the token (" theword" unlike tab, newline ...) then at least pop a warning to...