Pinned Loading
-
RLHF_in_notebooks
RLHF_in_notebooks PublicRLHF (Supervised fine-tuning, reward model, and PPO) step-by-step in 3 Jupyter notebooks
-
diffusion-gpt
diffusion-gpt PublicFrom baby GPT to diffusion GPT: An annotated implementation of a character-level discrete diffusion model (adapted from Karpathy’s baby GPT).
-
backtracking_gpt
backtracking_gpt PublicOutdated. This was pre- Claude Code. All coding agents use a variant of this technique these days.
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.