Comment Comment by xiphias2 George Hotz already implemented LLaMA 7B and 15B on Twitch yesterday on GPU in Tunygrad llama branch:https://github.com/geohot/tinygrad/tree/llamaThe only problem is that it's swapping on 16GB Macbook, so you need at least 24GB in practice. parent xiphias2 3 years ago
https://github.com/geohot/tinygrad/tree/llama
The only problem is that it's swapping on 16GB Macbook, so you need at least 24GB in practice.