trashpanda-org/Llama3-24B-Mullein-v1

Updated 6 days ago • 182

Note No longer as unhinged as v0, so we're discontinuing the instruct version. Varied rerolls, good character/scenario handling, almost no user impersonation now. Huge dependence on intro message quality, but lets it follow up messages from larger models quite nicely. Currently considering it as an overall improvement over v0 as far as tester feedback is concerned. Still seeing some slop and an occasional bad reroll response, though. Cursed for some reason to be good with Llama 3 instruct/context 💀