{
  "model_type": "gpt2",
  "architectures": [
    "GPT2LMHeadModel"
  ],
  "vocab_size": 16384,
  "n_positions": 1024,
  "n_ctx": 1024,
  "n_embd": 768,
  "n_layer": 12,
  "n_head": 12,
  "n_inner": 3072,
  "activation_function": "gelu_new",
  "resid_pdrop": 0.1,
  "embd_pdrop": 0.1,
  "attn_pdrop": 0.1,
  "layer_norm_epsilon": 0.00001,
  "initializer_range": 0.02,
  "scale_attn_weights": true,
  "scale_attn_by_inverse_layer_idx": false,
  "reorder_and_upcast_attn": false,
  "tie_word_embeddings": true,
  "pad_token_id": 3,
  "eos_token_id": 2,
  "bos_token_id": 1,
  "unk_token_id": 0
}