🧠 两小时从 0 训出你的 64M 大模型。Train your own 64M LLM from scratch in 2 hours.
update torch version
jingyaogong561979c7e34e
diff --git a/requirements.txt b/requirements.txtindex 31cd465..6ffb4d9 100644--- a/requirements.txt+++ b/requirements.txt@@ -26,5 +26,5 @@ trl==0.13.0ujson==5.1.0wandb==0.18.3streamlit==1.30.0-torch==2.2.2-torchvision==0.17.2\ No newline at end of file+torch==2.3.0+torchvision==0.18.0\ No newline at end of file