team-awesome
/

nanogpt

Model card Files Files and versions

365 MB

Ctrl+K

Ctrl+K

2 contributors

History: 8 commits

Jmushi's picture

RoPE cosine muon lr max 0.02 min 0.002 s18794 ppl 24.8575

b4ed9a0 verified 5 months ago

.gitattributes
1.56 kB
Upload model.py with huggingface_hub 6 months ago
checkpoint.pt
365 MB
xet

RoPE cosine muon lr max 0.02 min 0.002 s18794 ppl 24.8575 5 months ago
model.py
4.22 kB
xet

RoPE cosine muon lr max 0.02 min 0.002 s18794 ppl 24.8575 5 months ago