A small collection of Transformers with bilinear MLPs, trained on the TinyStories dataset.
Thomas Dooms
tdooms
AI & ML interests
None yet
Organizations
models
34
tdooms/emnist-l8-d256
6.51M
•
Updated
•
8
tdooms/emnist-l1-d256-b
1M
•
Updated
•
8
tdooms/emnist-l1-d256
1M
•
Updated
•
7
tdooms/emnist-l4-d256
3.36M
•
Updated
•
8
tdooms/qwen3-0.6b-base-scope
Updated
tdooms/simple-large-softmax
37.8M
•
Updated
•
16
tdooms/simple-large-sq
37.8M
•
Updated
•
6
tdooms/chess4
33.8M
•
Updated
•
7
tdooms/chess2
33.8M
•
Updated
•
7
tdooms/tiny-single
8.39M
•
Updated
•
21