Re:Meta Llama 3
by gliched_robot on Friday April 19, 2024 @01:00AM
(#40083570)
Disagree on Nvidia, most folks fine-tune model. Proof: there are about 20k models in huggingface derived from llama 2, all of them trained on Nvidia GPUs.
[ Parent
| on HN ]
Fine tuning can take a fraction of the resources required for training, so I think the original point stands.