SQCU
/

pgptlformer-tinystories

Model card Files Files and versions Community

pgptlformer-tinystories / dyn_qkrmsnorm_ii-7a038ecd-be98-46cb-abe8-e0f013fd7eed

1 contributor

sling the illustrious and mysterious "attention_II" models. also some layerwise rmsnorm, qkprojection rmsnorm models, one twice as large as the other.

1f45909 verified 23 days ago

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

sling the illustrious and mysterious "attention_II" models. also some layerwise rmsnorm, qkprojection rmsnorm models, one twice as large as the other. 23 days ago

Detected Pickle imports (4)