arxiv:2504.20966
Zayd Muhammad Kawakibi Zuhri PRO
zaydzuhri
AI & ML interests
I really like watching loss go down
Recent Activity
updated
a model
about 3 hours ago
zaydzuhri/vanilla-7B-4096-batch8x2-steps200000-20250614-140420
published
a model
1 day ago
zaydzuhri/vanilla-7B-4096-batch8x2-steps200000-20250614-140420
updated
a model
1 day ago
zaydzuhri/vanilla-7B-4096-batch4x4-steps200000-20250614-125325
Organizations
None yet
Papers
2
models
42
zaydzuhri/vanilla-7B-4096-batch8x2-steps200000-20250614-140420
Updated
zaydzuhri/vanilla-7B-4096-batch4x4-steps200000-20250614-125325
Updated
zaydzuhri/top-340M-4096-batch16-steps100000-20250613-201634
Updated
zaydzuhri/myopic-1B-4096-batch8x2-steps200000-20250603-105229
Updated
zaydzuhri/myopic-1.8B-4096-model
Updated
•
766
zaydzuhri/myopic-1B-4096-batch8x2-steps200000-20250606-190945
Updated
zaydzuhri/myopic-340M-4096-model
Updated
•
25
zaydzuhri/myopic-340M-4096-batch16-steps100000-20250523-085004
Updated
zaydzuhri/softpick-1.8B-4096-model
Updated
•
25
zaydzuhri/softpick-1B-4096-batch8x2-steps200000-20250506-061401
Updated
datasets
5
zaydzuhri/the_pile_tokenized_5percent_truncated_packed_v2
Viewer
•
Updated
•
2.46M
•
47
zaydzuhri/the_pile_tokenized_5percent_truncated_packed
Viewer
•
Updated
•
2.11M
•
36
zaydzuhri/the_pile_tokenized_5percent_truncated
Viewer
•
Updated
•
6M
•
219
zaydzuhri/the_pile_tokenized_5percent
Viewer
•
Updated
•
6M
•
56
zaydzuhri/the_pile_tokenized_6k
Viewer
•
Updated
•
6k
•
43