top | item 46206748

(no title)

pwython | 2 months ago

For those that have homebrewed a base model, does your output have the same AI-isms like overusing em dashes? If so/not, what dataset did you use?

discuss

order

itissid|2 months ago

Does yours also use the oxford comma and generally more commas?

miki123211|2 months ago

AFAIK, those are mostly a consequence of posttraining.

whimsicalism|2 months ago

that is a post-training artifact