Thursday 22 June 2023

GPT4 is 8 x 220B params = 1.7T params

GPT4 is 8 x 220B params = 1.7T params
375 by georgehill | 203 comments


-
Labels:

No comments:

Post a Comment

Subscribe to: Post Comments (Atom)

New exponent functions that make SiLU and SoftMax 2x faster, at full accuracy

New exponent functions that make SiLU and SoftMax 2x faster, at full accuracy 379 by weinzierl | 72 comments