Blog:

• Handling checkpoints from terminal - some useful tricks.
• Quick reset of my compute pod.
• Recent trends to speed up autoregressive inference of LLMs (unifinished).
• Quick hacks that you might find useful:
  • Speed up your migration to VIM.
  • Matrix Differential Calculus.
• Convex Optimization:
  • Convergence Rates of SGD in convex and non-convex cases.

Some projects:

• Backpropagation from scratch \(\rightarrow\) Github link.
• Randomized Algorithms \(\rightarrow\) Github link.
• Reinforcement Learning \(\rightarrow\) Github link.

Bio/Contact:

I’m Ayoub, I do ML R&D @CAROLL, mainly working on “tiny” LLMs. I’m also enrolled @UniPassau.

• Gmail: ayoub.benayad.467
• LinkedIn, Twitter (new acc), Instagram.