Most formidable supercomputer ever is warming up for ChatGPT 5 — thousands of ‘old’ AMD GPU accelerators crunched 1-trillion parameter models
CAT
1 min read
Scientists trained a GPT-4-sized model using much fewer GPUs than you’d ordinarily need.
Most formidable supercomputer ever is warming up for ChatGPT 5 — thousands of ‘old’ AMD GPU accelerators crunched 1-trillion parameter models
Most formidable supercomputer ever is warming up for ChatGPT 5 — thousands of ‘old’ AMD GPU accelerators crunched 1-trillion parameter models
