Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
Reduce Llama 3 RoPE memory requirements (#658)
* Llama3 from scratch improvements * Fix Llama 3 expensive RoPE memory issue * updates * update package * benchmark * remove unused rescale_theta
S
Sebastian Raschka committed
c4cde1c21bc38603cd11b06d55884a82555520b1
Parent: c278745
Committed by GitHub <noreply@github.com>
on 6/12/2025, 4:08:02 PM