config.json

{
  "architectures": [
    "GPT2LMHeadModel"
  ],
  "attn_pdrop": 0.1,
  "embd_pdrop": 0.1,
  "initializer_range": 0.02,
  "layer_norm_epsilon": 1e-05,
  "n_ctx": 1024,
  "n_embd": 1024,
  "n_head": 16,
  "n_layer": 24,
  "n_positions": 1024,
  "n_special": 0,
  "predict_special_tokens": true,
  "resid_pdrop": 0.1,
  "vocab_size": 50257
}