NanoGPT Ladder v3 - completed pretrained models Collection 57 completed pretrained models, 8M–128M parameters, five data mixtures, 10/30/100 TPP. Original PyTorch weights and generation scripts. • 57 items • Updated 2 days ago
davidheineman/nanogpt-ladder-v3-web-heavy-32m-100tpp-seed-1337 Text Generation • Updated 2 days ago • 40
NanoGPT Ladder v3 - completed pretrained models Collection 57 completed pretrained models, 8M–128M parameters, five data mixtures, 10/30/100 TPP. Original PyTorch weights and generation scripts. • 57 items • Updated 2 days ago
davidheineman/nanogpt-ladder-v3-web-heavy-64m-30tpp-seed-1337 Text Generation • Updated 2 days ago • 39
davidheineman/nanogpt-ladder-v3-web-heavy-32m-100tpp-seed-1337 Text Generation • Updated 2 days ago • 40
NanoGPT Ladder v3 - completed pretrained models Collection 57 completed pretrained models, 8M–128M parameters, five data mixtures, 10/30/100 TPP. Original PyTorch weights and generation scripts. • 57 items • Updated 2 days ago
davidheineman/nanogpt-ladder-v3-web-heavy-64m-10tpp-seed-1337 Text Generation • Updated 2 days ago • 37
davidheineman/nanogpt-ladder-v3-web-heavy-64m-30tpp-seed-1337 Text Generation • Updated 2 days ago • 39
NanoGPT Ladder v3 - completed pretrained models Collection 57 completed pretrained models, 8M–128M parameters, five data mixtures, 10/30/100 TPP. Original PyTorch weights and generation scripts. • 57 items • Updated 2 days ago
davidheineman/nanogpt-ladder-v3-web-heavy-32m-30tpp-seed-1337 Text Generation • Updated 2 days ago • 38
davidheineman/nanogpt-ladder-v3-web-heavy-64m-10tpp-seed-1337 Text Generation • Updated 2 days ago • 37
NanoGPT Ladder v3 - completed pretrained models Collection 57 completed pretrained models, 8M–128M parameters, five data mixtures, 10/30/100 TPP. Original PyTorch weights and generation scripts. • 57 items • Updated 2 days ago
davidheineman/nanogpt-ladder-v3-web-heavy-32m-10tpp-seed-1337 Text Generation • Updated 2 days ago • 36
NanoGPT Ladder v3 - completed pretrained models Collection 57 completed pretrained models, 8M–128M parameters, five data mixtures, 10/30/100 TPP. Original PyTorch weights and generation scripts. • 57 items • Updated 2 days ago
davidheineman/nanogpt-ladder-v3-web-heavy-16m-100tpp-seed-1337 Text Generation • Updated 2 days ago • 35
davidheineman/nanogpt-ladder-v3-web-heavy-32m-30tpp-seed-1337 Text Generation • Updated 2 days ago • 38