I'd love to see a tokens per second metric. I always prioritize speed over raw intelligence for flash models.
> 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))
Leave it long enough, and it'll print the work of Shakespear!
> I always prioritize speed over raw intelligence for flash models.
This model might have a perfect speed:
Leave it long enough, and it'll print the work of Shakespear!