Besides toxicqa, some kind of (normal) instruction-following dataset may also make her not so stupid.
Will require increasing the max_tokens, should probably update the default value.
Also, I would like to try merging model checkpoints at some point. What I'm doing is training a single QLora on a merged dataset of our own chats + ToxicQA (to make her capable of saying super…
Perhaps it would be a better idea to set the role to each actor's Discord username
Tried it. This doesn't actually seem work as well as I thought, so I switched back. This was before I added…
Currently uses 4-bit quantization with load_in_4bit flag, and the RVC model is loaded in float16 format
devising a new chat template which embeds the contents of the replied-to message if there is one.
Done! 87e9cc39e01d835eeef82f2ab03f833cbbd4667c
