Comment by hootz

2 days ago

I'd love to see a tokens per second metric. I always prioritize speed over raw intelligence for flash models.

2 comments

hootz

> I always prioritize speed over raw intelligence for flash models.

This model might have a perfect speed:

    for i in range(100):
      print(random.choices(words))

OsrsNeedsf2P 2 days ago

Leave it long enough, and it'll print the work of Shakespear!