徽标
我的项目 WeHub 热榜 数据中心
注册 登录
徽标
项目文件夹 工单
mirrors / karpathy--llm.c
项目文件夹 工单

项目文件夹

karpathy--llm.c
karpathy--llm.c mirrors
我的项目 创建
文件
feature/hellaswag
/dev
T
文件历史
Andrej Karpathy 8d55c4a6ac fix a bug, we have to be careful to make sure we evaluate loss at the token just before the first completion token, because that is the prediction for the first token, and its accuracy
2024-05-19 15:45:28 +00:00
..
cpu
Setting up dev/CPU area with the first matmul_forward.c
2024-05-14 18:22:39 -07:00
cuda
Merge pull request #383 from KarhouTam/feature/online-softmax-forward-without-cgs
2024-05-16 21:23:56 +01:00
hellaswag.py
fix a bug, we have to be careful to make sure we evaluate loss at the token just before the first completion token, because that is the prediction for the first token, and its accuracy
2024-05-19 15:45:28 +00:00
mmlu.py
fix a bug, we have to be careful to make sure we evaluate loss at the token just before the first completion token, because that is the prediction for the first token, and its accuracy
2024-05-19 15:45:28 +00:00
unistd.h
a comment and some breathing room
2024-04-20 20:00:24 +00:00
由 wehub 强力驱动
简体中文
English 简体中文
许可证 API