Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on Gemma 2: Improving Open Language Models at a Practical Size [pdf]. Parent comment
The Google API models support 1M+ tokens, but these are just 8K. Is there a fundamental architecture difference, training set, something else?
There are no comments on this comment yet.
The Google API models support 1M+ tokens, but these are just 8K. Is there a fundamental architecture difference, training set, something else?