NanoGPT Slowrun: 10x Data Efficiency with Infinite Compute~ai.algorithms.gpt~ai.llms~research> We've achieved 10x data efficiency with NanoGPT Slowrun within a few weeks.… moreqlabs.sh 2 weeks ago
GPT in 200 lines~ai.algorithms.gpt~ai.llms~dev.sourceauthor.andrej karpathypython> This is a brief guide to my new art project microgpt, a single file of 200… morekarpathy.github.io 4 weeks agoTildes