Skip to content

Pull requests: Liuhong99/Sophia

Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Assignee
Filter by who’s assigned
Sort

Pull requests list

Use nn.GELU for GELU. Runs a bit faster
#40 opened Jul 21, 2023 by attesaarela Loading…
Use pytorch2 optimized native attention
#39 opened Jul 20, 2023 by attesaarela Loading…
Optimize the gradient step
#35 opened Jul 7, 2023 by vmarkovtsev Loading…
Update prepare.py
#14 opened Jun 2, 2023 by yhgon Loading…
A new configurator?
#13 opened May 31, 2023 by arman-hk Loading…
ProTip! Type g i on any issue or pull request to go back to the issue listing page.