[concinds]

And it's a 4B model. I worry that nontechnical users will dramatically overestimate its accuracy and underestimate hallucinations, which makes me wonder how it could really be useful for academic research.

[DGoettlich]

valid point. its more of a stepping stone towards larger models. we're figuring out what the best way to do this is before scaling up.

[spicyusername]

If there's very little text before the internet, what would scaling up look like?