互关秒回.不骗人 pfp

互关秒回.不骗人

@ens445

726 Following
1360 Followers


互关秒回.不骗人 pfp
互关秒回.不骗人
@ens445
好像是错误来着
0 reply
0 recast
0 reaction

互关秒回.不骗人 pfp
互关秒回.不骗人
@ens445
索拉拉拉
0 reply
0 recast
0 reaction

互关秒回.不骗人 pfp
互关秒回.不骗人
@ens445
必须满分
0 reply
0 recast
0 reaction

派大星 pfp
派大星
@feisdfwe59
这个打多少分兄弟们
2 replies
1 recast
1 reaction

互关秒回.不骗人 pfp
互关秒回.不骗人
@ens445
0 reply
0 recast
0 reaction

Vladosito pfp
Vladosito
@vladosito
1 reply
10 recasts
108 reactions

互关秒回.不骗人 pfp
互关秒回.不骗人
@ens445
zk大佬又自由了
0 reply
0 recast
1 reaction

互关秒回.不骗人 pfp
互关秒回.不骗人
@ens445
llm.c training stabilized and achieves parity with PyTorch training (but faster) 💪 During the last few iters of training in my previous post, there were increases in loss. it was due to gradient norm clipping, and @karpathy fixed the bug🎉. With the latest llm.c code, GPT-2 (124M) achieved 35.3% ac
0 reply
1 recast
0 reaction

互关秒回.不骗人 pfp
互关秒回.不骗人
@ens445
llm.c training stabilized and achieves parity with PyTorch training (but faster) 💪 During the last few iters of training in my previous post, there were increases in loss. it was due to gradient norm clipping, and @karpathy fixed the bug🎉. With the latest llm.c code, GPT-2 (124M) achieved 35.3% ac
0 reply
1 recast
0 reaction