🚀🚀 「大模型」2小时完全从0训练64M的小参数GPT!🌏 Train a 64M-parameter GPT from scratch in just 2h!
[update] default model
J
jingyaogong committed
b7e0ae21d6a237e779c33bc127f77661cc0f30a5
Parent: b1865f7
🚀🚀 「大模型」2小时完全从0训练64M的小参数GPT!🌏 Train a 64M-parameter GPT from scratch in just 2h!