gpt2-2 / model_config_small.json
mzltest's picture
Duplicate from mzltest/gpt2-chinese-composition
4f52401
{
"initializer_range": 0.02,
"layer_norm_epsilon": 1e-05,
"n_ctx": 1024,
"n_embd": 768,
"n_head": 12,
"n_layer": 10,
"n_positions": 1024,
"vocab_size": 13317
}