This. ChatGPT also agrees with you: "74 GB weight read is per pass, not per token." I was checking the math in this blog post with GPT to understand it better and it seems legit for the given assumptions.
This. ChatGPT also agrees with you: "74 GB weight read is per pass, not per token." I was checking the math in this blog post with GPT to understand it better and it seems legit for the given assumptions.