nanochat
A minimal, hackable harness for training LLMs on a single GPU node, covering tokenization, pretraining, finetuning, evaluation and inference. Includes a skill that reads an arXiv paper from its URL.
1 skill60k
@karpathyPlugins
1@karpathySkill
1read-arxiv-paper
Use this skill when asked to read an arxiv paper given an arxiv URL
@karpathyIs this you? Claim your profilePut a plugin at the top of Plugins, from $9