 Sebastian Raschka
|
4e61dc4224
Fix d_out code comment in bonus materials (#715)
|
4 mesiacov pred |
|
Sebastian Raschka
|
d37ddb668a
Fix code comment: embed_dim -> d_out (#698)
|
5 mesiacov pred |
|
Sebastian Raschka
|
96ca2fcb2f
Update mha plot (#560)
|
8 mesiacov pred |
|
Sebastian Raschka
|
a08d7aaa84
Uv workflow improvements (#531)
|
9 mesiacov pred |
 Daniel Kleine
|
5ff72c2850
fixed typos (#414)
|
1 rok pred |
|
Daniel Kleine
|
ef4018181e
updates for PyTorch 2.5 (#408)
|
1 rok pred |
|
Daniel Kleine
|
2ee3df622e
nbviewer links / typo (#346)
|
1 rok pred |
|
Sebastian Raschka
|
ad12c8da06
Einsum multi-head attention (#345)
|
1 rok pred |
|
Daniel Kleine
|
c65928f7dc
added std error bars (#320)
|
1 rok pred |
 Jeroen Van Goey
|
76e6910a1a
Small typo fix (#313)
|
1 rok pred |
|
Sebastian Raschka
|
3f6652d87e
update attention benchmarks (#307)
|
1 rok pred |
|
Jeroen Van Goey
|
48bd72c890
fix typos, add codespell pre-commit hook (#264)
|
1 rok pred |
|
rasbt
|
71831890a0
update mha dim
|
1 rok pred |
|
rasbt
|
050c8b7b73
update pr
|
1 rok pred |
|
rasbt
|
98d453b666
update formatting
|
1 rok pred |
|
Sebastian Raschka
|
4adb96d7ee
Make code more consistent and add projection layer (#131)
|
1 rok pred |
|
Sebastian Raschka
|
2de60d1bfb
Rename variable to context_length to make it easier on readers (#106)
|
1 rok pred |
|
Sebastian Raschka
|
cf39abac04
Add and link bonus material (#84)
|
1 rok pred |
|
Sebastian Raschka
|
a2cd8436cb
Ch05 supplementary code (#81)
|
1 rok pred |
|
rasbt
|
0d517e98b9
update
|
1 rok pred |
|
rasbt
|
569f6bc7f0
benchmark numbers
|
1 rok pred |
 taihaozesong
|
f1fa9df15c
Fix mha wrapper implementations in ch03 bonus
|
1 rok pred |
|
rasbt
|
321f3d33f9
add cuda warmup
|
1 rok pred |
|
rasbt
|
da33ce8054
remove redundant unsqueeze in mask
|
1 rok pred |
|
rasbt
|
6ba97adaee
add PyTorch version
|
1 rok pred |
|
rasbt
|
5ca60321c4
add a100 numbers
|
1 rok pred |
|
rasbt
|
29ca41799a
use need_weights=False
|
1 rok pred |
|
rasbt
|
5643c88db9
add pytorch mha
|
1 rok pred |
|
rasbt
|
404f48aa74
automatically run on gpu or cpu
|
1 rok pred |
|
rasbt
|
99a5e28def
rename q,k,v for consistency with chapter 3
|
1 rok pred |