SQCU
/

pgptlformer-tinystories

Model card Files Files and versions Community

pgptlformer-tinystories / re-pqt-rmsXrms-ATTNII_rev2-d46b31ce-94f1-41c7-89cb-358a7a3f316b

1 contributor

History: 1 commit

SQCU's picture

compiled models train faster so you can train more of them in a short experiment, to better convergence.

921107d verified about 2 months ago

state_step006250.pt
Detected Pickle imports (4)
- "torch.FloatStorage",
- "torch._utils._rebuild_tensor_v2",
- "torch.ByteStorage",
- "collections.OrderedDict"
What is a pickle import?
338 MB
LFS

compiled models train faster so you can train more of them in a short experiment, to better convergence. about 2 months ago