metadata
license: apache-2.0
datasets:
- 922-Narra/lt_08312023_test_5j1
Pretrained toy model. Made with Andrej Karpathy's NanoGPT, ~2023.
Parameters:
- batch_size = 64
- block_size = 256
- n_layer = 8
- n_head = 8
- n_embd = 768
Everything else is left as is.