All I want is a model with a knowledge cutoff of like, early 2015, which I can feed random facts about current world politics and events and see its shock and horror
Want to talk to the past? Here' an LLM "trained entirely from scratch on a corpus of over 28,000 Victorian-era British texts published between 1837 & 1899, drawn from a dataset made available by the British Library" Quite different from an LLM roleplaying a Victorian. huggingface.co/spaces/tvent...
2 reposts78 likes