Sebastian Raschka
|
534a704364
RoPE increase (#407)
|
16 小时之前 |
Sebastian Raschka
|
75133605c5
Set sampler in DDP example
|
1 天之前 |
Sebastian Raschka
|
38969864e6
Add mean pooling experiment to classifier bonus experiments (#406)
|
2 天之前 |
Sebastian Raschka
|
467197bbf5
Test PyTorch 2.5 (#405)
|
2 天之前 |
Sebastian Raschka
|
1f61aeb7c4
Note about SSL certificates (#404)
|
2 天之前 |
rasbt
|
cd2753a36d
update mmap section
|
1 周之前 |
rasbt
|
08362fd290
add mmap=True comparison
|
1 周之前 |
Sebastian Raschka
|
05b04f2a5a
Memory efficient weight loading (#401)
|
1 周之前 |
rasbt
|
a20ce1b817
remove redundant code line
|
1 周之前 |
Sebastian Raschka
|
b6c4b2f9f1
Update bonus section formatting (#400)
|
1 周之前 |
Sebastian Raschka
|
233a3b0c8b
Update check-links.yml
|
1 周之前 |
rasbt
|
93d9dae95f
update card
|
1 周之前 |
rasbt
|
1f4fca9f8e
update reference numbers
|
1 周之前 |
Sebastian Raschka
|
6d0f59a49c
Add MFU formula as reference material (#395)
|
1 周之前 |
Sebastian Raschka
|
1a8d2929dd
Update check-links.yml
|
2 周之前 |
Sebastian Raschka
|
ec18b6a8a3
Add Llama 3.2 RoPE to CI (#391)
|
2 周之前 |
Sebastian Raschka
|
1eb0b3810a
Introduce buffers to improve Llama 3.2 efficiency (#389)
|
2 周之前 |
Daniel Kleine
|
a0c0c765a8
fixed Llama 2 to 3.2 NBs (#388)
|
2 周之前 |
Sebastian Raschka
|
0972ded530
Add a note about weight tying in Llama 3.2 (#386)
|
2 周之前 |
Sebastian Raschka
|
8a448a4410
Llama 3 (#384)
|
2 周之前 |
Sebastian Raschka
|
8553644440
Llama 3.2 requirements file
|
2 周之前 |
Sebastian Raschka
|
b44096acef
Implement Llama 3.2 (#383)
|
2 周之前 |
Sebastian Raschka
|
a5405c255d
Cos-sin fix in Llama 2 bonus notebook (#381)
|
2 周之前 |
Sebastian Raschka
|
b993c2b25b
Improve rope settings for llama3 (#380)
|
2 周之前 |
rasbt
|
278a50a348
add section numbers
|
3 周之前 |
Sebastian Raschka
|
4caafddb93
Improve DDP on Windows (#376)
|
3 周之前 |
rasbt
|
bfa4215774
llama note
|
3 周之前 |
Sebastian Raschka
|
7ef5129e18
Fix truncation issue in classify_review function (#373)
|
3 周之前 |
Sebastian Raschka
|
b56d0b2942
Add llama2 unit tests (#372)
|
3 周之前 |
rasbt
|
a6d8e93da3
improve formatting
|
3 周之前 |