Duplicated from mzltest/gpt2-chinese-composition
18b6863
1
2
3
4
5
6
7
8
9
10
{ "initializer_range": 0.02, "layer_norm_epsilon": 1e-05, "n_ctx": 1024, "n_embd": 768, "n_head": 12, "n_layer": 12, "n_positions": 1024, "vocab_size": 21128 }