Pinned Loading

1. RLHF_in_notebooks RLHF_in_notebooks Public

   RLHF (Supervised fine-tuning, reward model, and PPO) step-by-step in 3 Jupyter notebooks

   Jupyter Notebook 249 31

2. diffusion-gpt diffusion-gpt Public

   From baby GPT to diffusion GPT: An annotated implementation of a character-level discrete diffusion model (adapted from Karpathy’s baby GPT).

   Jupyter Notebook 259 22

3. backtracking_gpt backtracking_gpt Public

   A GPT agent with a Text Interface tool

   Python 15 1