Open wereretot opened 2 months ago
This is happening with 70B IQ_2_XS
Removing the newlines causes the model to stop as expected.
I will remove the newlines from the llama 3 format in the next version. Seems to be generally negative.
@LostRuins Yeah, even though I'm pretty sure the official format says to do it.
Hi, Should be fixed in the latest version, turns out this was due to a bad tokenizer merge. Try it again with a freshly reconverted GGUF.
Having newlines in the end sequence causes the model to continue as it doesn't put newlines down most of the time, so usually it starts moralizing.